Radiation and immune checkpoint inhibitor-mediated pneumonitis risk stratification in patients with locally advanced non-small cell lung cancer: role of functional lung radiomics?

Radiation and immune checkpoint inhibitor-mediated pneumonitis risk stratification in patients with locally advanced non-small cell lung cancer: role of functional lung radiomics? | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Radiation and immune checkpoint inhibitor-mediated pneumonitis risk stratification in patients with locally advanced non-small cell lung cancer: role of functional lung radiomics? Hannah Mary T Thomas, Daniel S Hippe, Parisa Forouzannezhad, Balu Krishna Sasidharan, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1680696/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background: Patients undergoing chemoradiation and immune checkpoint inhibitor (ICI) therapy for locally advanced non-small cell lung cancer (LA-NSCLC) experience pulmonary toxicity at higher rates than historical reports. We investigated the role of novel functional lung radiomics, relative to functional lung dosimetry and clinical characteristics, for pneumonitis risk stratification in LA-NSCLC. Methods: Thirty-nine patients with LA-NSCLC were prospectively enrolled on the FLARE-RT trial (NCT02773238). All received concurrent chemoradiation using functional lung avoidance planning, while 21/39 received consolidation durvalumab ICI. Within tumour-subtracted lung regions, 110 radiomics features (shape, intensity, texture) were extracted on pre-treatment [ 99m Tc]MAA SPECT/CT perfusion (PERF) images using fixed-bin-width discretization. The performance of functional lung radiomics for pneumonitis (CTCAEv4 grade 2 or higher) risk stratification was benchmarked against previously reported lung dosimetric parameters and clinical risk factors. Multivariate least absolute shrinkage and selection operator (LASSO) Cox models of time-varying pneumonitis risk were constructed, and prediction performance was evaluated using optimism-adjusted concordance index (c-index) with 95% confidence interval reporting throughout. Results : Pneumonitis occurred in 16/39 (41%) patients. Among clinical characteristics and anatomic/functional lung dosimetry variables, only the presence of baseline chronic obstructive pulmonary disease (COPD) was significantly associated with the development of pneumonitis (HR 4.59 [1.69-12.49]) and served as the primary prediction benchmark model (c-index 0.69 [0.59-0.80]). Discrimination of time-varying pneumonitis risk was numerically higher when combining COPD with perfused lung radiomics size (c-index 0.77 [0.65-0.88]) or shape feature classes (c-index 0.79 [0.66-0.91]) but did not reach statistical significance compared to benchmark models (p>0.26). COPD was associated with perfused lung radiomics size features, including patients with larger lung volumes (AUC 0.75 [0.59-0.91]). Perfused lung radiomic texture features were correlated with lung volume (adj R 2 =0.84-1.00), representing surrogates rather than independent predictors of pneumonitis risk. Conclusions : In patients undergoing chemoradiation with functional lung avoidance therapy and optional consolidative immune checkpoint inhibitor (ICI) therapy for LA-NSCLC, the strongest predictor of pneumonitis was the presence of baseline chronic obstructive pulmonary disease. Our results support functional lung radiomics as surrogates of COPD. Further study of clinical, dosimetric, and radiomic feature combinations for radiation and immune-mediated pneumonitis in larger patient populations is warranted. functional lung imaging radiomics SPECT pneumonitis radiation therapy immunotherapy machine learning Figures Figure 1 Figure 2 Figure 3 Introduction Pneumonitis is an adverse event following lung-directed radiation and immune checkpoint inhibitor (ICI) therapy ( 1 ). Clinically symptomatic radiation pneumonitis manifests in 30–40% of patient within weeks to months following concurrent chemoradiation regimens, with most cases being reported within the first 6–8 months ( 2 ). Based on the outcome of the PACIFIC trial ( 3 ), the standard-of-care for treating unresectable locally advanced non-small cell lung cancer (LA-NSCLC) has evolved to include consolidation anti-PD-L1 ICI, which conferred a clinically meaningful survival advantage when administered after chemoradiation ( 4 ). However, this regimen has led to increased pneumonitis incidence and treatment interruptions in some patients, potentially blunting clinical benefits ( 5 – 9 ). Predictive risk models of radiation pneumonitis are primarily based on clinical parameters and radiation dosimetry. Reported risk factors include advanced age, gender, performance status, history of smoking, tumour location, underlying pulmonary comorbidities, radiation treatment regimen, and concurrent chemotherapy ( 10 – 12 ). Common radiation dosimetric predictors include mean lung dose (MLD), dose-volumes (V20, V30, V40), total radiation lung dose, and daily radiation dose ( 10 , 13 – 17 ). Other risk factors include race, dose to the heart and trachea or bronchus ( 12 , 18 , 19 ). These risk factors can be combined in normal tissue complication probability models with weighted non-parametric decision trees 19,20 . Beyond conventional radiation dosimetry, functional lung dosimetry derived from positron emission tomography (PET), four-dimensional respiratory-correlated CT (4DCT), single photon emission computed tomography (SPECT) or magnetic resonance (MR) imaging can be used to limit dose to well-perfused or well-ventilated lung under functional tissue avoidance planning paradigms ( 20 – 27 ). Functional lung dosimetric predictors of pneumonitis include functional MLD, functional V5, V20, V30, V40, and total lung perfusion receiving dose above 20 Gy ( 14 , 28 – 31 ). Other quantitative imaging biomarkers, based primarily on CT radiomic texture features, have also improved pneumonitis risk stratification relative to traditional dosimetry ( 32 – 36 ). Unlike validated radiation pneumonitis modelling, identifying risk factors for combined radiation and ICI-mediated pneumonitis is plagued by a paucity of data and limited diagnostic accuracy based on specific clinical or radiographic markers ( 37 ). Inoue et al reported that typical clinical and dose-volume parameters failed to show correlation to pneumonitis following radiation therapy (RT) and anti-PD-L1 ICI ( 38 ). Modern chemoradiation and ICI-therapy regimens require discovery of novel biomarkers that can capture differential presentations of radiation and immune-mediated pneumonitis ( 7 ) at overlapping time intervals. We investigated the utility of functional lung radiomics for pneumonitis risk stratification in the setting of chemoradiation and ICI-therapy for patients with LA-NSCLC enrolled on a prospective clinical trial of functional lung avoidance and response-adaptive escalation (FLARE) RT. Our aim is to explore the role of functional lung radiomics, relative to functional lung dosimetry and clinical characteristics, for pneumonitis risk stratification in LA-NSCLC. Methods And Material Patient population and treatment characteristics Thirty-nine patients with histologically confirmed LA-NSCLC enrolled onto the prospective FLARE-RT clinical trial. All patients received concurrent chemotherapy. Functional lung avoidance radiation treatment was planned to limit dose to well-perfused lung regions defined on 99m Tc-labled macro-aggregated albumin (MAA) SPECT. Adaptive dose escalation was planned to residual FDG-PET-avid regions in select patients based on mid-treatment response assessment ( 39 , 40 ). Mid-PET responders and non-responders were prescribed doses of 60 Gy and 74 Gy, respectively, to planning target volumes. Approximately half of patients (20/39) received pencil beam scanned proton therapy, while the remaining patients received photon IMRT/VMAT. Following the transition to a new standard-of-care pathway, 23/39 patients received consolidative durvalumab anti-PD-L1 ICI-therapy after completion of chemoradiation. ICI-therapy was started with a median delay of 22 days with 13/23 starting within 22 days after chemoradiation. Patients had median follow-up of 16.6 months (7-50.6 months), with 29/39 exceeding one-year follow-up. Patients were dichotomized for pulmonary toxicity based on the presence or absence of grade ≥ 2 pneumonitis (GR2 + pneumonitis) defined by CTCAE v4. Due to the brief time interval between completion of chemoradiation and initiation of consolidation durvalumab in most patients, we did not distinguish between radiation pneumonitis and immune-mediated pneumonitis events. The study was reviewed and approved by the institutional review board. Table 1 Patient demographics and clinical characteristics stratified by pneumonitis status. GR2 + Pneumonitis Characteristics All (N = 39) No (N = 23) Yes (N = 16) Age, years 63 (48–78) 62 (48–76) 67 (52–78) Gender Male 18 (46) 10 (43) 8 (50) Female 21 (54) 13 (57) 8 (50) Clinical stage IIB 1 (3) 0 (0) 1 (6) IIIA 19 (49) 9 (39) 10 (62) IIIB 13 (33) 9 (39) 4 (25) Recurrence 6 (15) 5 (22) 1 (6) Treatment modality IMRT/VMAT 19 (49) 11 (48) 8 (50) PBT 20 (51) 12 (52) 8 (50) NSCLC histology Squamous cell carcinoma 14 (36) 6 (26) 8 (50) Adenocarcinoma 23 (59) 16 (70) 7 (44) NOS 2 (5) 1 (4) 1 (6) COPD Yes 13 (33) 4 (17) 9 (56) No 26 (67) 19 (83) 7 (44) Chemotherapy Carboplatin-paclitaxel 23 (59) 12 (52) 11 (69) Others 16 (41) 11 (48) 5 (31) Immunotherapy Yes 21 (54) 11 (48) 10 (62) No 18 (46) 12 (52) 6 (38) Smoking status Non-smoker 5 (13) 3 (13) 2 (12) Former 30 (77) 16 (70) 14 (88) Current 4 (10) 4 (17) 0 (0) Mid-treatment PET response Responder 25 (64) 14 (61) 11 (69) ICI-therapy 15 (60) 9 (64) 6 (55) No ICI-therapy 10 (40) 5 (36) 5 (45) Non-responder 14 (36) 9 (39) 5 (31) ICI-therapy 6 (43) 2 (22) 4 (80) No ICI-therapy 8 (57) 7 (78) 1 (20) Values are median (range) or no. (%); IMRT = intensity-modulated radiation therapy; VMAT = volumetric modulated arc therapy; PBT = proton-beam therapy; NSCLC = non-small cell lung cancer NOS = not otherwise specified; COPD = chronic obstructive pulmonary disease; ICI = immune-checkpoint inhibitor. Image acquisition and processing All 39 patients underwent pre-treatment [ 99 mTc] MAA perfusion SPECT/CT on a Precedence (Philips Healthcare, Cleveland, OH) 16-slice CT scanner with a dual-head gamma camera to extract candidate radiomic predictors of pneumonitis. All imaging data was acquired with patients reproducibly immobilized in radiation treatment position. Patients received a fixed intravenous injected activity (185 MBq nominal), followed by a time-averaged SPECT (64 views, 20 seconds per view, 180-degree arc) acquired under quiescent free-breathing conditions. SPECT images were corrected for scatter, collimator-detector response, and attenuation using helical CT images. Images were reconstructed using the Astonish™ (Philips Healthcare, Cleveland, OH) ordered subset expectation-maximization (OSEM) iterative algorithm on 4.64 mm isotropic grids with spatial resolution recovery and 10 mm cut-off Hanning filter. The CT elements of SPECT/CT pre-and post-treatment images were rigidly co-registered to planning 4DCT average intensity projection images in MIM 6.8™ (MIM Software Inc., Cleveland, OH) using mutual information. The spatial transformations estimated from CT-to-CT registration were subsequently applied to the respective SPECT images. Lung ROI definition and dosimetry Internal gross tumour volumes (IGTV) were delineated as the union of contours from respiratory-correlated 4DCT phases by board-certified radiation oncologists. The normal lung was defined as the Boolean subtraction of internal gross tumour volume from the lung (Lung-IGTV) on the planning 4DCT average intensity projection. Using the linear-quadratic model, the radiation dose to the normal lung was converted to 2 Gy fraction biologically equivalent voxel dose distributions (EQD2Lung) for a clinical endpoint of pneumonitis (α/β = 3) to account for variability in fractional dose across patients. All proton therapy doses were calculated with a commercial Monte-Carlo treatment planning algorithm appropriate for lung tissue ( 41 , 42 ) and a constant radiobiological effectiveness (RBE) of 1.1. From the Lung-IGTV ROI, we extracted five previously reported EQD2Lung dosimetry parameters: (i) mean lung dose (MLD), (ii) volume of lung receiving ≥ 20 Gy (V20), (iii) perfused mean lung dose (pMLD), (iv) perfused lung volume receiving ≥ 20 Gy (pV20), and (v) fraction of integral lung function receiving ≥ 20 Gy (pF20). These metrics were identified as predictors for pneumonitis in patients undergoing conventional radiation therapy for NSCLC ( 25 ). Perfusion radiomics feature extraction Pre-treatment MAA SPECT perfusion images, co-registered 3-month post-treatment MAA SPECT perfusion images, and co-registered normal lung RT structures were loaded in 3D Slicer ( 43 ). Within the Lung-IGTV contours, 110 features were extracted using the Radiomics module made available by the PyRadiomics community ( 44 ) ( Fig. 1 ). The features were extracted at the native voxel size (4.64 mm isotropic) without any resampling or filtering, yielding a median of 34,644 voxels (range 20,043–78,484 voxels) per Lung-IGTV contour. We used fixed bin width (FBW = 25 CNTS) SPECT intensity discretization techniques which produced discrete intensity bins with sufficient voxel sampling for neighborhood texture calculation ( 44 ). In all, 19 first-order, 16 shape and 75 texture features were computed from the grey-level co-occurrence (GLCM), grey-level dependence (GLDM), grey-level run length (GLRLM), grey-level size zone (GLSZM) and neighbourhood grey-tone difference (NGTDM) matrices. The GLCM was calculated using the PyRadiomics default symmetrical setting. Wavelet filtered features were not computed to limit dimensionality in this discovery phase study with modest patient sample size. Statistical analysis Clinical and dosimetric parameters were compared between groups using Fisher’s exact test for categorical variables and the Mann-Whitney U-test for continuous variables. Associations of clinical characteristics and dosimetric parameters with GR2 + pneumonitis were estimated using Cox regression models, with time to GR2 + pneumonitis censored by distant metastasis and death. ICI therapy was treated as a binary time-varying covariate in the models that was initialized to 0 (has not started therapy) and became 1 when therapy was initiated. The correlation of candidate pre-treatment functional lung radiomic biomarkers with clinical variables were performed using Spearman rank correlation and Mann-Whitney tests. The least absolute shrinkage and selection operator (LASSO) was used for multivariable modeling. The LASSO was selected as the machine learning technique as it simultaneously performs both feature selection and parameter regularization to limit overfitting ( 45 ). LASSO-Cox models were used for predicting GR2 + pneumonitis risk and LASSO-logistic models were used for evaluating associations with COPD at baseline. Six primary models were generated for each outcome based on ( 1 ) clinical parameters only, ( 2 ) lung dosimetry parameters only 3) combination of both clinical and lung dosimetry parameters 4) radiomics feature class only, and ( 5 ) combination of radiomics feature classes and significant clinical feature 6) volume and all parameters from ( 5 ). The prediction performance of the models was evaluated using the concordance index (c-index) ( 46 ). The c-index was optimism-adjusted using the bootstrap, an internal validation technique to account for training and testing models using the same data set ( 47 ). All statistical calculations were performed using the statistical computing language R (version 4.0.3; R Foundation for Statistical Computing, Vienna, Austria). Throughout, two-sided tests were used, and parameters were considered statistically significant when p < 0.05. Results Demographic and clinical characteristics of the patient cohort, along with patients who experienced GR2 + pneumonitis versus those who did not, are shown in Table 1 . Patients who received consolidation ICI-therapy had similar characteristics to those who did not (Supplementary Table A1). Table 2 shows that on univariate analysis of the clinical characteristics, and anatomic/functional lung dosimetry parameters, only the presence of baseline chronic obstructive pulmonary disease (COPD) appeared as a significant predictor for radiation pneumonitis, (HR 4.59 [95% CI: 1.69–12.49], p = 0.003). Multivariate LASSO-Cox proportional hazards model also showed that COPD independently associated with the development of pneumonitis when including clinical features only (HR 2.33) and when including clinical and antomical/functional dosimetric features (HR 2.18). The predictive performance of the COPD-only model (c-index 0.69, 95% CI: 0.59–0.80) was used as a benchmark for multivariable prediction models that incorporated pre-treatment lung perfusion radiomic features. Table 2 Univariable and multivariable associations of clinical factors and lung dosimetric parameters with pneumonitis risk in the setting of functional lung avoidance radiation treatment planning. Univariable LASSO HR* Clinical Feature HR (95% CI) P-value Clinical Only Dosimetry Only Clinical + Dosimetry Male 1.31 (0.49–3.50) 0.59 - - Age, per 10-year increase 1.67 (0.84–3.29) 0.14 - - COPD 4.59 (1.69–12.49) 0.003 2.33 2.18 Stage IIIb 0.55 (0.18–1.72) 0.31 - - PBT 1.05 (0.39–2.81) 0.92 - - Chemotherapy Carboplatin + paclitaxel 1.69 (0.59–4.88) 0.33 - - ICI 1.71 (0.58–5.01) 0.33 - - Dosimetric Feature MLD, per 1-SD increase 1.24 (0.75–2.06) 0.41 - - V20, per 1-SD increase 1.29 (0.78–2.13) 0.33 1.02 - sqrt(pMLD), per 1-SD increase 1.07 (0.67–1.73) 0.77 - - sqrt(pV20), per 1-SD increase 1.06 (0.66–1.71) 0.81 - - pF20, per 1-SD increase 1.13 (0.71–1.80) 0.61 - - HR = hazard ratio; LASSO = least absolute shrinkage and selection operator; COPD = chronic pulmonary obstructive disease; PBT = proton-beam therapy; ICI = immune checkpoint inhibitor; MLD = mean lung dose; V20 = volume of lung receiving > 20 Gy; pMLD = perfused mean lung dose; pV20 = perfused lung volume receiving ≥ 20 Gy; pF20 = fraction of integral lung function receiving ≥ 20 Gy; *HR from LASSO-Cox model; a dash (-) indicates the corresponding feature was included in the model but the LASSO did not select it in the final model (HR = 1); blank cells indicate the features were not included in the LASSO-Cox model. Figure 2 shows the LASSO-multivariable models of time-varying pneumonitis risk from pre-treatment lung perfusion radiomics features independently or with other factors such as COPD and lung volume. Models including only the radiomics features (orange points) with each feature class could not discriminate between patients with and without pneumonitis (c-index 0.34–0.48). However, when perfused lung radiomics shape (c-index 0.77 [95% CI: 0.65–0.88], p = 0.27 vs. benchmark COPD-only model) and size feature classes (c-index 0.79 [95% CI: 0.66–0.91], p = 0.26 vs. benchmark COPD-only model) were combined with COPD (blue points) the discrimination of time-varying pneumonitis risk improved but did not reach statistical significance compared to benchmark models. The addition of lung voxel volume to perfusion lung radiomics features and COPD (green points) had little impact on discrimination of time-varying pneumonitis risk (Fig. 2 ). Since COPD was the dominant risk factor for pneumonitis, we investigated its correlation to radiomic features. Figure 3 shows the LASSO logistic regression models for COPD prediction based on perfused lung radiomics features. The models included radiomic feature classes separately. COPD was marginally significantly associated with perfused lung radiomics size features (AUC 0.69 [95% CI: 0.50–0.89], p = 0.051) but not with the features in the other radiomic feature classes (AUC 0.36–0.70, p > 0.11 for all). Since COPD largely correlated to radiomic size feature class, we also examined a model with lung voxel volume as the only predictor (AUC 0.75 [95% CI: 0.59–0.91]) and added lung voxel volume to each class-specific model (blue points in Fig. 3 ). While lung voxel volume alone was significantly associated with COPD (p = 0.002), none of the models which combined voxel volume with perfused lung radiomic features were statistically significantly predictive of COPD (AUC 0.61–0.66, p > 0.15 for all). As shown in Fig. 3 , perfused lung radiomic texture features were highly correlated with lung volume (adj R 2 = 0.84-1.00). Table 3 Correlation of lung voxel volume with perfused lung radiomic features within each feature class. Correlation between Volume and All Features within a Class Feature Class Number of Features in Class adj .R 2 P-value Size* 9 1.00 < 0.001 Shape 4 0.93 < 0.001 First Order 17 1.00 < 0.001 GLCM 23 0.87 < 0.001 GLDM 14 0.99 < 0.001 GLRLM 16 1.00 < 0.001 GLSZM 16 0.98 < 0.001 NGTDM 5 0.84 < 0.001 *Voxel volume is excluded from the set of size features in the calculations. Discussion To our knowledge, we present the first study exploring the role of MAA-SPECT lung perfusion radiomics for pneumonitis risk stratification. A unique cohort of LA-NSCLC patients enrolled on the FLARE-RT protocol (NCT02773238) and received chemoradiation guided by functional lung avoidance planning and selective dose escalation based on mid-treatment fluorodeoxyglucose-PET response status, with half of patients receiving consolidation anti-PD-L1 ICI-therapy. In this cohort, we evaluated clinical and reported lung dosimetry parameters independently and in combination with perfused lung radiomic features derived from MAA-SPECT for pneumonitis risk stratification. Moran et al evaluated GLCM-texture and first-order features to assess their ability to distinguish between oncologist-defined post-SBRT lung injury, with GLCM features outperforming first-order features ( 34 ). Cunliffe et al observed CT-texture changes in high dose regions that correlated strongly to radiation pneumonitis status, while dosimetric parameters failed to show any association. Krafft et al reported that the addition of CT-based texture features along with clinical and dosimetric features improved the performance of pneumonitis prediction models ( 33 ). Our investigation revealed that none of the radiomics features classes showed promise in predicting risk of pneumonitis independently. However, when radiomics shape and size class features were combined with COPD, the discrimination of time-varying risk prediction of pneumonitis improved (c-index = 0.77–0.79) although it did not reach statistical significance. Similar to cancer radiomics where tumour volume is a confounding feature ( 48 ), many perfused lung radiomic features showed marked dependencies with volume of the lung, which is the organ at risk in our study, suggesting the radiomic features may serve as size surrogates rather than independent predictors of pneumonitis risk. In the era of ICI consolidation therapy for LA-NSCLC, few studies have evaluated clinical and dosimetric risk factors for pneumonitis. Shaverdian et al found that validated pulmonary toxicity models underestimated the incidence of pneumonitis in the setting of consolidation durvalumab ICI ( 37 ). Inoue et al reported that clinical and dosimetric parameters were not significant predictors of pneumonitis in LA-NSCLC treated with the chemoradiation and durvalumab regimen ( 38 ). Our findings in the FLARE-RT cohort were concordant with these studies, as our anatomic and perfused lung dosimetry failed to predict pneumonitis incidence. We observed that COPD or pre-existing emphysema was the dominant risk factor for the development of pneumonitis in this cohort of patients. These results are similar to the study reported by Zhou et al who observed that pulmonary emphysema was a risk factor for NSCLC patients with squamous cell carcinoma ( 49 ). Patients with COPD have been known to exhibit increases in lung volume due to limited expiratory airflow ( 50 , 51 ). In this study, we found that COPD was more prevalent in patients with larger lung volumes, which is consistent with the lung physiology as reported in the studies above. Our study has some limitations. In this preliminary discovery phase, we report on a modest patient cohort, with only half of patients receiving ICI-therapy. Nonetheless, very few reports are available on the incidence of immunotherapy-related pneumonitis following chemoradiation for locally advanced non-small cell lung cancer, and none incorporated functional lung avoidance planning techniques or functional lung radiomics. Moreover, our study lacks external validation of the functional lung radiomic pneumonitis prediction model. There is opportunity to validate the findings of this study in a larger cohort of patients receiving chemoradiation and ICI-therapy to further elucidate the influence of COPD, perfused lung dosimetry, and perfused lung radiomics on pneumonitis risk. Lastly, while we relied on SPECT CNTS data, the latest generation SPECT scanners will enable calculation of SPECT standardized uptake values (SUV) that are analogous to PET SUV, thus facilitating quantitative SPECT radiomics. Future quantitative SPECT radiomic approaches should consider the effects of total lung volume and perfused lung available for MAA tracer distribution on SPECT SUV calculations. Conclusion As immune modulating therapies grow more influential in the management of unresectable locally advanced non-small cell lung cancer, modelling of pneumonitis risk secondary to radiation and systemic therapy requires investigation of biomarkers and factors beyond conventional radiation dosimetry. Combinations of clinical, dosimetric, and radiomic features may support personalized treatments to mitigate the risk of developing pneumonitis. In this work, we identified the presence of underlying pulmonary disease as a strong predictor radiation and immune-mediated pneumonitis risk and observed that perfused lung radiomics may represent lung volume surrogates rather than independent predictors of pneumonitis risk. Further investigation of functional lung radiomics is warranted. Declarations Ethical Approval and Consent to participate: The study was reviewed and approved by the institutional review board. All patients included have consented to the study. Consent for publication: All authors consent for manuscript to be published in Radiation Oncology, if accepted. Availability of supporting data: The datasets from the current study are not publicly available prior to reporting of mature outcomes from the parent clinical trial. Requests for data and materials should be sent to the corresponding author. Competing interests: JZ and RR serve as consultants to Astrazeneca. PEK declares support from GE Healthcare and is co-founder of PET/X, LLC. RSM and HJV declare support from Philips Healthcare and serve as consultants for MIM Software Funding: This investigation was supported by NIH/NCI R01CA204301. Authors' contributions: The authors confirm contribution to the paper as follows: study conception and design: SRB, PK, RSM, HJV, JZ, SRB; data collection: HMT, PF, BS; analysis and interpretation of results HMT, DSH, PF, BS, SRB; draft manuscript preparation: HMT, DSH, SRB; manuscript review and revision PK, RSM, HJV, RR. All authors reviewed the results and approved the final version of the manuscript. Acknowledgements: This investigation was supported by NIH/NCI R01CA204301. The authors gratefully acknowledge the patients who participated in the FLARE-RT clinical trial (NCT02773238). This research was also supported by the Biostatistics Shared Resource of the Fred Hutch/University of Washington Cancer Consortium (P30 CA015704). We thank Priya Vissamraju and Christina Lo for coordinating FLARE-RT protocol imaging and curating the study database. We acknowledge the efforts of Nuclear Medicine, Radiation Oncology, and Proton Center staff during SPECT/CT acquisitions, radiation therapy planning, and image-guided radiation therapy delivery. References Schoenfeld JD, Nishino M, Severgnini M, Manos M, Mak RH, Hodi FS. Pneumonitis resulting from radiation and immune checkpoint blockade illustrates characteristic clinical, radiologic and circulating biomarker features. Journal for ImmunoTherapy of Cancer . 2019;7(1): 112. https://doi.org/10.1186/s40425-019-0583-3. Jain V, Berman AT. Radiation Pneumonitis: Old Problem, New Tricks. Cancers . 2018;10(7). https://doi.org/10.3390/cancers10070222. Antonia SJ, Villegas A, Daniel D, Vicente D, Murakami S, Hui R, et al. Durvalumab after Chemoradiotherapy in Stage III Non-Small-Cell Lung Cancer. The New England Journal of Medicine . 2017;377(20): 1919–1929. https://doi.org/10.1056/NEJMoa1709937. Ahn M-J. Consolidation of immunotherapy becomes new standard of care in unresectable stage III non-small cell lung cancer. Journal of Thoracic Disease . 2018;10(3): 1205–1206. https://doi.org/10.21037/jtd.2018.03.55. Cadranel J, Canellas A, Matton L, Darrason M, Parrot A, Naccache J-M, et al. Pulmonary complications of immune checkpoint inhibitors in patients with nonsmall cell lung cancer. European Respiratory Review . 2019;28(153). https://doi.org/10.1183/16000617.0058-2019. Davis R m., Patel P, Ikladios O i. Immune-Mediated Pneumonitis Due to Nivolumab: Is It Worth Using? In: D35. DRUG INDUCED LUNG DISEASE: CASE REPORTS . American Thoracic Society; 2018. p. A6609–A6609. https://doi.org/10.1164/ajrccm-conference.2018.197.1_MeetingAbstracts.A6609. [Accessed 24th August 2020]. Naidoo J, Nishino M, Patel SP, Shankar B, Rekhtman N, Illei P, et al. Immune-Related Pneumonitis After Chemoradiotherapy and Subsequent Immune Checkpoint Blockade in Unresectable Stage III Non–Small-Cell Lung Cancer. Clinical Lung Cancer . 2020; https://doi.org/10.1016/j.cllc.2020.02.025. Shohdy KS, Abdel-Rahman O. Risk of pneumonitis with different immune checkpoint inhibitors in NSCLC. Annals of Translational Medicine . 2017;5(17). https://doi.org/10.21037/atm.2017.06.67. Zhong L, Altan M, Shannon VR, Sheshadri A. Immune-Related Adverse Events: Pneumonitis. Immunotherapy . 2020;1244: 255–269. https://doi.org/10.1007/978-3-030-41008-7_13. Wang S, Liao Z, Wei X, Liu HH, Tucker SL, Hu C, et al. Analysis of clinical and dosimetric factors associated with treatment-related pneumonitis (TRP) in patients with non–small-cell lung cancer (NSCLC) treated with concurrent chemotherapy and three-dimensional conformal radiotherapy (3D-CRT). International Journal of Radiation Oncology*Biology*Physics . 2006;66(5): 1399–1407. https://doi.org/10.1016/j.ijrobp.2006.07.1337. Kong F-M (Spring), Wang S. Nondosimetric Risk Factors for Radiation-Induced Lung Toxicity. Seminars in Radiation Oncology . 2015;25(2): 100–109. https://doi.org/10.1016/j.semradonc.2014.12.003. von Reibnitz D, Yorke ED, Oh JH, Apte AP, Yang J, Pham H, et al. Predictive Modeling of Thoracic Radiotherapy Toxicity and the Potential Role of Serum Alpha-2-Macroglobulin. Frontiers in Oncology . 2020;10. https://doi.org/10.3389/fonc.2020.01395. Palma DA, Senan S, Tsujino K, Barriger RB, Rengan R, Moreno M, et al. Predicting Radiation Pneumonitis After Chemoradiation Therapy for Lung Cancer: An International Individual Patient Data Meta-analysis. International Journal of Radiation Oncology*Biology*Physics . 2013;85(2): 444–450. https://doi.org/10.1016/j.ijrobp.2012.04.043. Lee HJ, Zeng J, Vesselle HJ, Patel SA, Rengan R, Bowen SR. Correlation of Functional Lung Heterogeneity and Dosimetry to Radiation Pneumonitis using Perfusion SPECT/CT and FDG PET/CT Imaging. International Journal of Radiation Oncology • Biology • Physics . 2018;0(0). https://doi.org/10.1016/j.ijrobp.2018.05.051. Yorke ED, Jackson A, Rosenzweig KE, Merrick SA, Gabrys D, Venkatraman ES, et al. Dose-volume factors contributing to the incidence of radiation pneumonitis in non-small-cell lung cancer patients treated with three-dimensional conformal radiation therapy. International Journal of Radiation Oncology*Biology*Physics . 2002;54(2): 329–339. https://doi.org/10.1016/S0360-3016(02)02929-2. Marks LB, Hollis D, Munley M, Bentel G, Garipagaoglu M, Fan M, et al. The role of lung perfusion imaging in predicting the direction of radiation-induced changes in pulmonary function tests. Cancer . 2000;88(9): 2135–2141. https://doi.org/10.1002/(SICI)1097-0142(20000501)88:93.0.CO;2-H. Wen G, Tan Y-T, Lan X-W, He Z-C, Huang J-H, Shi J-T, et al. New Clinical Features and Dosimetric Predictor Identification for Symptomatic Radiation Pneumonitis after Tangential Irradiation in Breast Cancer Patients. Journal of Cancer . 2017;8(18): 3795–3802. https://doi.org/10.7150/jca.21158. Valdes G, Solberg TD, Heskel M, Ungar L, Simone CB. Using machine learning to predict radiation pneumonitis in patients with stage I non-small cell lung cancer treated with stereotactic body radiation therapy. Physics in Medicine and Biology . 2016;61(16): 6105–6120. https://doi.org/10.1088/0031-9155/61/16/6105. Chen S, Zhou S, Yin F-F, Marks LB, Das SK. Investigation of the support vector machine algorithm to predict lung radiation-induced pneumonitis. Medical Physics . 2007;34(10): 3808–3814. https://doi.org/10.1118/1.2776669. Ament SJ, Maus S, Reber H, Buchholz HG, Bausbacher N, Brochhausen C, et al. PET lung ventilation/perfusion imaging using (68)Ga aerosol (Galligas) and (68)Ga-labeled macroaggregated albumin. Recent Results in Cancer Research. Fortschritte Der Krebsforschung. Progres Dans Les Recherches Sur Le Cancer . 2013;194: 395–423. https://doi.org/10.1007/978-3-642-27994-2_22. Siva S, Callahan J, Kron T, Martin OA, MacManus MP, Ball DL, et al. A prospective observational study of Gallium-68 ventilation and perfusion PET/CT during and after radiotherapy in patients with non-small cell lung cancer. BMC Cancer . 2014;14. https://doi.org/10.1186/1471-2407-14-740. Hoover DA, Capaldi DP, Sheikh K, Palma DA, Rodrigues GB, Dar AR, et al. Functional lung avoidance for individualized radiotherapy (FLAIR): study protocol for a randomized, double-blind clinical trial. BMC Cancer . 2014;14(1): 934. https://doi.org/10.1186/1471-2407-14-934. Siva S, Devereux T, Ball DL, MacManus MP, Hardcastle N, Kron T, et al. Ga-68 MAA Perfusion 4D-PET/CT Scanning Allows for Functional Lung Avoidance Using Conformal Radiation Therapy Planning. Technology in Cancer Research & Treatment . 2016;15(1): 114–121. https://doi.org/10.1177/1533034614565534. Vinogradskiy Y, Schubert L, Diot Q, Waxweiller T, Koo P, Castillo R, et al. Regional Lung Function Profiles of Stage I and III Lung Cancer Patients: An Evaluation for Functional Avoidance Radiation Therapy. International Journal of Radiation Oncology, Biology, Physics . 2016;95(4): 1273–1280. https://doi.org/10.1016/j.ijrobp.2016.02.058. Lee E, Zeng J, Miyaoka RS, Saini J, Kinahan PE, Sandison GA, et al. Functional lung avoidance and response-adaptive escalation (FLARE) RT: multimodality plan dosimetry of a precision radiation oncology strategy. Medical physics . 2017;44(7): 3418–3429. https://doi.org/10.1002/mp.12308. Bucknell NW, Hardcastle N, Bressel M, Hofman MS, Kron T, Ball D, et al. Functional lung imaging in radiation therapy for lung cancer: A systematic review and meta-analysis. Radiotherapy and Oncology . 2018; https://doi.org/10.1016/j.radonc.2018.07.014. Farr KP, West K, Yeghiaian-Alvandi R, Farlow D, Stensmyr R, Chicco A, et al. Functional perfusion image guided radiation treatment planning for locally advanced lung cancer. Physics and Imaging in Radiation Oncology . 2019;11: 76–81. https://doi.org/10.1016/j.phro.2019.08.007. Faught AM, Yamamoto T, Castillo R, Castillo E, Zhang J, Miften M, et al. Evaluating Which Dose-Function Metrics Are Most Critical for Functional-Guided Radiation Therapy. International Journal of Radiation Oncology, Biology, Physics . 2017;99(1): 202–209. https://doi.org/10.1016/j.ijrobp.2017.03.051. Vinogradskiy Y, Castillo R, Castillo E, Tucker SL, Liao Z, Guerrero T, et al. Use of 4-Dimensional Computed Tomography-Based Ventilation Imaging to Correlate Lung Dose and Function With Clinical Outcomes. International journal of radiation oncology, biology, physics . 2013;86(2). https://doi.org/10.1016/j.ijrobp.2013.01.004. Seppenwoolde Y, De Jaeger K, Boersma LJ, Belderbos JSA, Lebesque JV. Regional differences in lung radiosensitivity after radiotherapy for non-small-cell lung cancer. International Journal of Radiation Oncology, Biology, Physics . 2004;60(3): 748–758. https://doi.org/10.1016/j.ijrobp.2004.04.037. O’Reilly S, Jain V, Huang Q, Cheng C, Teo B-KK, Yin L, et al. Dose to Highly Functional Ventilation Zones Improves Prediction of Radiation Pneumonitis for Proton and Photon Lung Cancer Radiation Therapy. International Journal of Radiation Oncology, Biology, Physics . 2020;107(1): 79–87. https://doi.org/10.1016/j.ijrobp.2020.01.014. Bousabarah K, Temming S, Hoevels M, Borggrefe J, Baus WW, Ruess D, et al. Radiomic analysis of planning computed tomograms for predicting radiation-induced lung injury and outcome in lung cancer patients treated with robotic stereotactic body radiation therapy. Strahlentherapie und Onkologie . 2019;195(9): 830–842. https://doi.org/10.1007/s00066-019-01452-7. Krafft SP, Rao A, Stingo F, Briere TM, Court LE, Liao Z, et al. The utility of quantitative CT radiomics features for improved prediction of radiation pneumonitis. Medical Physics . 2018;45(11): 5317–5324. https://doi.org/10.1002/mp.13150. Moran A, Daly ME, Yip SSF, Yamamoto T. Radiomics-based Assessment of Radiation-induced Lung Injury After Stereotactic Body Radiotherapy. Clinical Lung Cancer . 2017;18(6): e425–e431. https://doi.org/10.1016/j.cllc.2017.05.014. Cunliffe A, Armato SG, Castillo R, Pham N, Guerrero T, Al-Hallaq HA. Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. International Journal of Radiation Oncology, Biology, Physics . 2015;91(5): 1048–1056. https://doi.org/10.1016/j.ijrobp.2014.11.030. Anthony GJ, Cunliffe A, Castillo R, Pham N, Guerrero T, Armato SG, et al. Incorporation of pre-therapy 18F-FDG uptake data with CT texture features into a radiomics model for radiation pneumonitis diagnosis. Medical Physics . 2017;44(7): 3686–3694. https://doi.org/10.1002/mp.12282. Shaverdian N, Thor M, Shepherd AF, Offin MD, Jackson A, Wu AJ, et al. Radiation pneumonitis in lung cancer patients treated with chemoradiation plus durvalumab. Cancer Medicine . 2020;9(13): 4622–4631. https://doi.org/10.1002/cam4.3113. Inoue H, Ono A, Kawabata T, Mamesaya N, Kawamura T, Kobayashi H, et al. Clinical and radiation dose-volume factors related to pneumonitis after treatment with radiation and durvalumab in locally advanced non-small cell lung cancer. Investigational New Drugs . 2020; https://doi.org/10.1007/s10637-020-00917-2. Horn K, Tomas H, Vesselle H, Kinahan P, Miyaoka R, Rengan R, et al. Concordance of quantitative FDG PET/CT imaging biomarkers for classifying early response to chemoradiotherapy in patients with locally advanced non-small cell lung cancer. Journal of Nuclear Medicine . 2020;61(supplement 1): 1333–1333. Sasidharan BK, Bowen SR, Rengan R, Patel SA, Thomas HMT, Miyaoka RS, et al. Early PET/CT Response Assessment for Selective FDG PET-Guided Dose Escalation in Locally Advanced NSCLC Patients Enrolled on the FLARE-RT Protocol. International Journal of Radiation Oncology • Biology • Physics . 2018;102(3): e703–e704. https://doi.org/10.1016/j.ijrobp.2018.07.1891. Saini J, Traneus E, Maes D, Regmi R, Bowen SR, Bloch C, et al. Advanced Proton Beam Dosimetry Part I: review and performance evaluation of dose calculation algorithms. Translational Lung Cancer Research . 2018;7(2): 171–179. https://doi.org/10.21037/tlcr.2018.04.05. Maes D, Saini J, Zeng J, Rengan R, Wong T, Bowen SR. Advanced proton beam dosimetry part II: Monte Carlo vs. pencil beam-based planning for lung cancer. Translational Lung Cancer Research . 2018;7(2): 114–121. https://doi.org/10.21037/tlcr.2018.04.04. Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin J-C, Pujol S, et al. 3D Slicer as an Image Computing Platform for the Quantitative Imaging Network. Magnetic resonance imaging . 2012;30(9): 1323–1341. https://doi.org/10.1016/j.mri.2012.05.001. van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Research . 2017;77(21): e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339. Tibshirani R. Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society. Series B (Methodological) . 1996;58(1): 267–288. Harrell FE, Lee KL, Mark DB. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Statistics in Medicine . 1996;15(4): 361–387. https://doi.org/10.1002/(SICI)1097-0258(19960229)15:43.0.CO;2-4. Steyerberg EW, Harrell FE, Borsboom GJ, Eijkemans MJ, Vergouwe Y, Habbema JD. Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. Journal of Clinical Epidemiology . 2001;54(8): 774–781. https://doi.org/10.1016/s0895-4356(01)00341-9. Traverso A, Kazmierski M, Zhovannik I, Welch M, Wee L, Jaffray D, et al. Machine learning helps identifying volume-confounding effects in radiomics. Physica Medica . 2020;71: 24–30. https://doi.org/10.1016/j.ejmp.2020.02.010. Zhou Z, Song X, Wu A, Liu H, Wu H, Wu Q, et al. Pulmonary emphysema is a risk factor for radiation pneumonitis in NSCLC patients with squamous cell carcinoma after thoracic radiation therapy. Scientific Reports . 2017;7(1): 2748. https://doi.org/10.1038/s41598-017-02739-4. Physiology and consequences of lung hyperinflation in COPD | European Respiratory Society . https://err.ersjournals.com/content/15/100/61 [Accessed 15th February 2022]. Biselli P, Grossman PR, Kirkness JP, Patil SP, Smith PL, Schwartz AR, et al. The effect of increased lung volume in chronic obstructive pulmonary disease on upper airway obstruction during sleep. Journal of Applied Physiology . 2015;119(3): 266–271. https://doi.org/10.1152/japplphysiol.00455.2014. Additional Declarations Competing interest reported. JZ and RR serve as consultants to Astrazeneca. PEK declares support from GE Healthcare and is co-founder of PET/X, LLC. RSM and HJV declare support from Philips Healthcare and serve as consultants for MIM Software Supplementary Files Appendix.docx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-1680696","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":108597451,"identity":"1cbb2bcb-1cd6-47d6-bb42-f1830882bced","order_by":0,"name":"Hannah Mary T Thomas","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hannah","middleName":"Mary T","lastName":"Thomas","suffix":""},{"id":108597452,"identity":"af327005-d201-4c3a-8760-72aaec8d4d22","order_by":1,"name":"Daniel S Hippe","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"S","lastName":"Hippe","suffix":""},{"id":108597453,"identity":"b98098f2-c32e-4043-b53f-846d2426474d","order_by":2,"name":"Parisa Forouzannezhad","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Parisa","middleName":"","lastName":"Forouzannezhad","suffix":""},{"id":108597456,"identity":"dabfdc3d-5d41-43c0-b777-fb575bb1478a","order_by":3,"name":"Balu Krishna Sasidharan","email":"","orcid":"","institution":"Christian Medical College, Vellore","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Balu","middleName":"Krishna","lastName":"Sasidharan","suffix":""},{"id":108597458,"identity":"3b316500-197c-4aef-9054-3cf3c9c5e9cc","order_by":4,"name":"Paul E Kinahan","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Paul","middleName":"E","lastName":"Kinahan","suffix":""},{"id":108597460,"identity":"ee8a75fc-a8e6-4ead-a5e8-ab08980e5e05","order_by":5,"name":"Robert S Miyaoka","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Robert","middleName":"S","lastName":"Miyaoka","suffix":""},{"id":108597462,"identity":"8c3b1260-3627-4f6d-aef9-f2ff01eeb00d","order_by":6,"name":"Hubert J Vesselle","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hubert","middleName":"J","lastName":"Vesselle","suffix":""},{"id":108597465,"identity":"b8d97856-edc2-41cd-ac09-fc5d30a88717","order_by":7,"name":"Ramesh Rengan","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ramesh","middleName":"","lastName":"Rengan","suffix":""},{"id":108597469,"identity":"b3fcd161-38fc-45cd-a8f9-aad0a52fa0d1","order_by":8,"name":"Jing Zeng","email":"","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Zeng","suffix":""},{"id":108597473,"identity":"89d81339-0b44-4cdf-99b7-486420d70b1a","order_by":9,"name":"Stephen R Bowen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAApklEQVRIiWNgGAWjYFACHjAph8QmUosx6VoSG4jWIj/77MHHPBV30jfcSGB88LaNCC0G5/KSjXnOPMsFamE2nEuUFh4eM+nctsO5G24nsEnzEqNFvgek5d/hdIPbCey/idLCcAakpeFwAlALGzNRWgzO8CUb/zl22HDm/YfNknPOEeUw3oMPZ9Qcluc7c/jghzdlxDgMARgbSFM/CkbBKBgFowA3AAAAAzWDW5meygAAAABJRU5ErkJggg==","orcid":"","institution":"University of Washington School of Medicine","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Stephen","middleName":"R","lastName":"Bowen","suffix":""}],"badges":[],"createdAt":"2022-05-22 01:59:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1680696/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1680696/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":21962557,"identity":"3db35274-5182-43ac-a362-a0c53557eed5","added_by":"auto","created_at":"2022-05-27 14:05:49","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":30326,"visible":true,"origin":"","legend":"\u003cp\u003eFunctional lung radiomics and machine learning pipeline for pneumonitis risk stratification\u003c/p\u003e\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-1680696/v1/13dd5e935fec9656914aaab7.png"},{"id":21962139,"identity":"c4dfce51-e191-4d82-9fc5-9eae3b7953fe","added_by":"auto","created_at":"2022-05-27 14:00:49","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":26953,"visible":true,"origin":"","legend":"\u003cp\u003ePerformance of LASSO-Cox multivariable models for pneumonitis prediction based on lung radiomic features only (orange) or in conjunction with chronic obstructive pulmonary disease (COPD) (blue) or COPD and voxel volume (VV) (green) as added features. Each class of radiomic features was considered separately. The horizontal dotted line indicates the null value (c-index = 0.5) and the horizontal dashed line indicates the benchmark COPD-only model (c-index = 0.69). GLCM = gray-level co-occurance matrix; GLDM = gray-level dependence matrix; GLRLM = gray-level run-length matrix; GLSZM = gray-level size zone matrix; NGTDM = neighboring gray-tone difference matrix.\u003c/p\u003e\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-1680696/v1/c4e71c922ef439f9ef1f6a90.png"},{"id":21962137,"identity":"9afc4c4c-7589-4b87-812a-5e5a56ed722a","added_by":"auto","created_at":"2022-05-27 14:00:49","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":23545,"visible":true,"origin":"","legend":"\u003cp\u003ePerformance of LASSO-logistic multivariable models for chronic obstructive pulmonary disease (COPD) prediction based on lung radiomic features only (orange) or in conjunction with voxel volume (VV) (blue) as an added feature. GLCM = gray-level co-occurance matrix; GLDM = gray-level dependence matrix; GLRLM = gray-level run-length matrix; GLSZM = gray-level size zone matrix; NGTDM = neighboring gray-tone difference matrix.\u003c/p\u003e\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-1680696/v1/ba641ec492a64eb70c2447bd.png"},{"id":22019045,"identity":"987bc687-845b-4b3c-a6c4-b59dfe14cb09","added_by":"auto","created_at":"2022-05-30 07:29:19","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":612879,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1680696/v1/64e91be5-2cc7-4188-8e98-84f83471b6e5.pdf"},{"id":21962136,"identity":"90589fa6-1641-443a-b8b3-addea063f71a","added_by":"auto","created_at":"2022-05-27 14:00:49","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":27785,"visible":true,"origin":"","legend":"","description":"","filename":"Appendix.docx","url":"https://assets-eu.researchsquare.com/files/rs-1680696/v1/a67bb7983be520aff3d670f3.docx"}],"financialInterests":"Competing interest reported. JZ and RR serve as consultants to Astrazeneca. PEK declares support from GE Healthcare and is co-founder of PET/X, LLC. RSM and HJV declare support from Philips Healthcare and serve as consultants for MIM Software","formattedTitle":"Radiation and immune checkpoint inhibitor-mediated pneumonitis risk stratification in patients with locally advanced non-small cell lung cancer: role of functional lung radiomics?","fulltext":[{"header":"Introduction","content":"\u003cp\u003ePneumonitis is an adverse event following lung-directed radiation and immune checkpoint inhibitor (ICI) therapy (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e). Clinically symptomatic radiation pneumonitis manifests in 30\u0026ndash;40% of patient within weeks to months following concurrent chemoradiation regimens, with most cases being reported within the first 6\u0026ndash;8 months (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e). Based on the outcome of the PACIFIC trial (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e), the standard-of-care for treating unresectable locally advanced non-small cell lung cancer (LA-NSCLC) has evolved to include consolidation anti-PD-L1 ICI, which conferred a clinically meaningful survival advantage when administered after chemoradiation (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e). However, this regimen has led to increased pneumonitis incidence and treatment interruptions in some patients, potentially blunting clinical benefits (\u003cspan additionalcitationids=\"CR6 CR7 CR8\" citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e).\u003c/p\u003e \u003cp\u003ePredictive risk models of radiation pneumonitis are primarily based on clinical parameters and radiation dosimetry. Reported risk factors include advanced age, gender, performance status, history of smoking, tumour location, underlying pulmonary comorbidities, radiation treatment regimen, and concurrent chemotherapy (\u003cspan additionalcitationids=\"CR11\" citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e). Common radiation dosimetric predictors include mean lung dose (MLD), dose-volumes (V20, V30, V40), total radiation lung dose, and daily radiation dose (\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan additionalcitationids=\"CR14 CR15 CR16\" citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e). Other risk factors include race, dose to the heart and trachea or bronchus (\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e). These risk factors can be combined in normal tissue complication probability models with weighted non-parametric decision trees\u003csup\u003e19,20\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eBeyond conventional radiation dosimetry, functional lung dosimetry derived from positron emission tomography (PET), four-dimensional respiratory-correlated CT (4DCT), single photon emission computed tomography (SPECT) or magnetic resonance (MR) imaging can be used to limit dose to well-perfused or well-ventilated lung under functional tissue avoidance planning paradigms (\u003cspan additionalcitationids=\"CR21 CR22 CR23 CR24 CR25 CR26\" citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e). Functional lung dosimetric predictors of pneumonitis include functional MLD, functional V5, V20, V30, V40, and total lung perfusion receiving dose above 20 Gy (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan additionalcitationids=\"CR29 CR30\" citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e). Other quantitative imaging biomarkers, based primarily on CT radiomic texture features, have also improved pneumonitis risk stratification relative to traditional dosimetry (\u003cspan additionalcitationids=\"CR33 CR34 CR35\" citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eUnlike validated radiation pneumonitis modelling, identifying risk factors for combined radiation and ICI-mediated pneumonitis is plagued by a paucity of data and limited diagnostic accuracy based on specific clinical or radiographic markers (\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e). Inoue et al reported that typical clinical and dose-volume parameters failed to show correlation to pneumonitis following radiation therapy (RT) and anti-PD-L1 ICI (\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e). Modern chemoradiation and ICI-therapy regimens require discovery of novel biomarkers that can capture differential presentations of radiation and immune-mediated pneumonitis (\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e) at overlapping time intervals.\u003c/p\u003e \u003cp\u003eWe investigated the utility of functional lung radiomics for pneumonitis risk stratification in the setting of chemoradiation and ICI-therapy for patients with LA-NSCLC enrolled on a prospective clinical trial of functional lung avoidance and response-adaptive escalation (FLARE) RT. Our aim is to explore the role of functional lung radiomics, relative to functional lung dosimetry and clinical characteristics, for pneumonitis risk stratification in LA-NSCLC.\u003c/p\u003e"},{"header":"Methods And Material","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003ePatient population and treatment characteristics\u003c/h2\u003e \u003cp\u003eThirty-nine patients with histologically confirmed LA-NSCLC enrolled onto the prospective FLARE-RT clinical trial. All patients received concurrent chemotherapy. Functional lung avoidance radiation treatment was planned to limit dose to well-perfused lung regions defined on \u003csup\u003e99m\u003c/sup\u003eTc-labled macro-aggregated albumin (MAA) SPECT. Adaptive dose escalation was planned to residual FDG-PET-avid regions in select patients based on mid-treatment response assessment (\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e, \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e). Mid-PET responders and non-responders were prescribed doses of 60 Gy and 74 Gy, respectively, to planning target volumes. Approximately half of patients (20/39) received pencil beam scanned proton therapy, while the remaining patients received photon IMRT/VMAT. Following the transition to a new standard-of-care pathway, 23/39 patients received consolidative durvalumab anti-PD-L1 ICI-therapy after completion of chemoradiation. ICI-therapy was started with a median delay of 22 days with 13/23 starting within 22 days after chemoradiation. Patients had median follow-up of 16.6 months (7-50.6 months), with 29/39 exceeding one-year follow-up. Patients were dichotomized for pulmonary toxicity based on the presence or absence of grade\u0026thinsp;\u0026ge;\u0026thinsp;2 pneumonitis (GR2\u0026thinsp;+\u0026thinsp;pneumonitis) defined by CTCAE v4. Due to the brief time interval between completion of chemoradiation and initiation of consolidation durvalumab in most patients, we did not distinguish between radiation pneumonitis and immune-mediated pneumonitis events. The study was reviewed and approved by the institutional review board.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePatient demographics and clinical characteristics stratified by pneumonitis status.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003eGR2\u0026thinsp;+\u0026thinsp;Pneumonitis\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCharacteristics\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u003cb\u003eAll\u003c/b\u003e\u003c/p\u003e \u003cp\u003e\u003cb\u003e(N\u0026thinsp;=\u0026thinsp;39)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003eNo\u003c/b\u003e\u003c/p\u003e \u003cp\u003e\u003cb\u003e(N\u0026thinsp;=\u0026thinsp;23)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003eYes\u003c/b\u003e\u003c/p\u003e \u003cp\u003e\u003cb\u003e(N\u0026thinsp;=\u0026thinsp;16)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, years\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e63 (48\u0026ndash;78)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e62 (48\u0026ndash;76)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e67 (52\u0026ndash;78)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGender\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18 (46)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10 (43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8 (50)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (54)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e13 (57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8 (50)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClinical stage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIIB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIIIA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19 (49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9 (39)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e10 (62)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIIIB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13 (33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9 (39)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e4 (25)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRecurrence\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (15)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5 (22)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTreatment modality\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIMRT/VMAT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19 (49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11 (48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8 (50)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePBT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20 (51)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12 (52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8 (50)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNSCLC histology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSquamous cell carcinoma\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e14 (36)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6 (26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8 (50)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdenocarcinoma\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23 (59)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e16 (70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e7 (44)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNOS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1 (4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOPD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13 (33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4 (17)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e9 (56)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26 (67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e19 (83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e7 (44)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChemotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCarboplatin-paclitaxel\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23 (59)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12 (52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e11 (69)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOthers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (41)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11 (48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (31)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (54)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11 (48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e10 (62)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18 (46)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12 (52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e6 (38)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmoking status\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNon-smoker\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5 (13)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3 (13)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2 (12)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFormer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30 (77)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e16 (70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e14 (88)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCurrent\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (10)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4 (17)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMid-treatment PET response\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eResponder\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e25 (64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e14 (61)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e11 (69)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICI-therapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e15 (60)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9 (64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e6 (55)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo ICI-therapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (40)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5 (36)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (45)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNon-responder\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e14 (36)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9 (39)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (31)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICI-therapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2 (22)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e4 (80)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo ICI-therapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7 (78)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (20)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003eValues are median (range) or no. (%);\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003eIMRT\u0026thinsp;=\u0026thinsp;intensity-modulated radiation therapy; VMAT\u0026thinsp;=\u0026thinsp;volumetric modulated arc therapy; PBT\u0026thinsp;=\u0026thinsp;proton-beam therapy; NSCLC\u0026thinsp;=\u0026thinsp;non-small cell lung cancer NOS\u0026thinsp;=\u0026thinsp;not otherwise specified; COPD\u0026thinsp;=\u0026thinsp;chronic obstructive pulmonary disease; ICI\u0026thinsp;=\u0026thinsp;immune-checkpoint inhibitor.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eImage acquisition and processing\u003c/h2\u003e \u003cp\u003eAll 39 patients underwent pre-treatment [\u003csup\u003e99\u003c/sup\u003emTc] MAA perfusion SPECT/CT on a Precedence (Philips Healthcare, Cleveland, OH) 16-slice CT scanner with a dual-head gamma camera to extract candidate radiomic predictors of pneumonitis. All imaging data was acquired with patients reproducibly immobilized in radiation treatment position. Patients received a fixed intravenous injected activity (185 MBq nominal), followed by a time-averaged SPECT (64 views, 20 seconds per view, 180-degree arc) acquired under quiescent free-breathing conditions. SPECT images were corrected for scatter, collimator-detector response, and attenuation using helical CT images. Images were reconstructed using the Astonish\u0026trade; (Philips Healthcare, Cleveland, OH) ordered subset expectation-maximization (OSEM) iterative algorithm on 4.64 mm isotropic grids with spatial resolution recovery and 10 mm cut-off Hanning filter. The CT elements of SPECT/CT pre-and post-treatment images were rigidly co-registered to planning 4DCT average intensity projection images in MIM 6.8\u0026trade; (MIM Software Inc., Cleveland, OH) using mutual information. The spatial transformations estimated from CT-to-CT registration were subsequently applied to the respective SPECT images.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eLung ROI definition and dosimetry\u003c/h2\u003e \u003cp\u003eInternal gross tumour volumes (IGTV) were delineated as the union of contours from respiratory-correlated 4DCT phases by board-certified radiation oncologists. The normal lung was defined as the Boolean subtraction of internal gross tumour volume from the lung (Lung-IGTV) on the planning 4DCT average intensity projection. Using the linear-quadratic model, the radiation dose to the normal lung was converted to 2 Gy fraction biologically equivalent voxel dose distributions (EQD2Lung) for a clinical endpoint of pneumonitis (α/β\u0026thinsp;=\u0026thinsp;3) to account for variability in fractional dose across patients. All proton therapy doses were calculated with a commercial Monte-Carlo treatment planning algorithm appropriate for lung tissue (\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e) and a constant radiobiological effectiveness (RBE) of 1.1. From the Lung-IGTV ROI, we extracted five previously reported EQD2Lung dosimetry parameters: (i) mean lung dose (MLD), (ii) volume of lung receiving\u0026thinsp;\u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003e\u0026ge;\u003c/span\u003e\u0026thinsp;20 Gy (V20), (iii) perfused mean lung dose (pMLD), (iv) perfused lung volume receiving\u0026thinsp;\u0026ge;\u0026thinsp;20 Gy (pV20), and (v) fraction of integral lung function receiving\u0026thinsp;\u0026ge;\u0026thinsp;20 Gy (pF20). These metrics were identified as predictors for pneumonitis in patients undergoing conventional radiation therapy for NSCLC (\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003ePerfusion radiomics feature extraction\u003c/h2\u003e \u003cp\u003ePre-treatment MAA SPECT perfusion images, co-registered 3-month post-treatment MAA SPECT perfusion images, and co-registered normal lung RT structures were loaded in 3D Slicer (\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e). Within the Lung-IGTV contours, 110 features were extracted using the Radiomics module made available by the PyRadiomics community (\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e) \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u003cb\u003e).\u003c/b\u003e The features were extracted at the native voxel size (4.64 mm isotropic) without any resampling or filtering, yielding a median of 34,644 voxels (range 20,043\u0026ndash;78,484 voxels) per Lung-IGTV contour. We used fixed bin width (FBW\u0026thinsp;=\u0026thinsp;25 CNTS) SPECT intensity discretization techniques which produced discrete intensity bins with sufficient voxel sampling for neighborhood texture calculation (\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e). In all, 19 first-order, 16 shape and 75 texture features were computed from the grey-level co-occurrence (GLCM), grey-level dependence (GLDM), grey-level run length (GLRLM), grey-level size zone (GLSZM) and neighbourhood grey-tone difference (NGTDM) matrices. The GLCM was calculated using the PyRadiomics default symmetrical setting. Wavelet filtered features were not computed to limit dimensionality in this discovery phase study with modest patient sample size.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eClinical and dosimetric parameters were compared between groups using Fisher\u0026rsquo;s exact test for categorical variables and the Mann-Whitney U-test for continuous variables. Associations of clinical characteristics and dosimetric parameters with GR2\u0026thinsp;+\u0026thinsp;pneumonitis were estimated using Cox regression models, with time to GR2\u0026thinsp;+\u0026thinsp;pneumonitis censored by distant metastasis and death. ICI therapy was treated as a binary time-varying covariate in the models that was initialized to 0 (has not started therapy) and became 1 when therapy was initiated. The correlation of candidate pre-treatment functional lung radiomic biomarkers with clinical variables were performed using Spearman rank correlation and Mann-Whitney tests.\u003c/p\u003e \u003cp\u003eThe least absolute shrinkage and selection operator (LASSO) was used for multivariable modeling. The LASSO was selected as the machine learning technique as it simultaneously performs both feature selection and parameter regularization to limit overfitting (\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e). LASSO-Cox models were used for predicting GR2\u0026thinsp;+\u0026thinsp;pneumonitis risk and LASSO-logistic models were used for evaluating associations with COPD at baseline. Six primary models were generated for each outcome based on (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) clinical parameters only, (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) lung dosimetry parameters only 3) combination of both clinical and lung dosimetry parameters 4) radiomics feature class only, and (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e) combination of radiomics feature classes and significant clinical feature 6) volume and all parameters from (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e). The prediction performance of the models was evaluated using the concordance index (c-index) (\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e). The c-index was optimism-adjusted using the bootstrap, an internal validation technique to account for training and testing models using the same data set (\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eAll statistical calculations were performed using the statistical computing language R (version 4.0.3; R Foundation for Statistical Computing, Vienna, Austria). Throughout, two-sided tests were used, and parameters were considered statistically significant when p\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003eDemographic and clinical characteristics of the patient cohort, along with patients who experienced GR2\u0026thinsp;+\u0026thinsp;pneumonitis versus those who did not, are shown in Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e. Patients who received consolidation ICI-therapy had similar characteristics to those who did not (Supplementary Table A1).\u003c/p\u003e\n\u003cp\u003eTable \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e shows that on univariate analysis of the clinical characteristics, and anatomic/functional lung dosimetry parameters, only the presence of baseline chronic obstructive pulmonary disease (COPD) appeared as a significant predictor for radiation pneumonitis, (HR 4.59 [95% CI: 1.69\u0026ndash;12.49], p\u0026thinsp;=\u0026thinsp;0.003). Multivariate LASSO-Cox proportional hazards model also showed that COPD independently associated with the development of pneumonitis when including clinical features only (HR 2.33) and when including clinical and antomical/functional dosimetric features (HR 2.18). The predictive performance of the COPD-only model (c-index 0.69, 95% CI: 0.59\u0026ndash;0.80) was used as a benchmark for multivariable prediction models that incorporated pre-treatment lung perfusion radiomic features.\u0026nbsp;\u003c/p\u003e\u0026nbsp;\u003ctable border=\"1\" id=\"Tab2\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eUnivariable and multivariable associations of clinical factors and lung dosimetric parameters with pneumonitis risk in the setting of functional lung avoidance radiation treatment planning.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eUnivariable\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"3\"\u003e\n \u003cp\u003eLASSO HR*\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eClinical Feature\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eHR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003e(95% CI)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eP-value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eClinical\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eOnly\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eDosimetry\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eOnly\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eClinical +\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eDosimetry\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.49\u0026ndash;3.50)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge, per 10-year increase\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.84\u0026ndash;3.29)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCOPD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(1.69\u0026ndash;12.49)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.003\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStage IIIb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.18\u0026ndash;1.72)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePBT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.05\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.39\u0026ndash;2.81)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eChemotherapy Carboplatin\u0026thinsp;+\u0026thinsp;paclitaxel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.59\u0026ndash;4.88)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eICI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.71\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.58\u0026ndash;5.01)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eDosimetric Feature\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMLD, per 1-SD increase\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.75\u0026ndash;2.06)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eV20, per 1-SD increase\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.78\u0026ndash;2.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.02\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003esqrt(pMLD), per 1-SD increase\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.67\u0026ndash;1.73)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003esqrt(pV20), per 1-SD increase\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.06\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.66\u0026ndash;1.71)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003epF20, per 1-SD increase\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(0.71\u0026ndash;1.80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"11\"\u003eHR\u0026thinsp;=\u0026thinsp;hazard ratio; LASSO\u0026thinsp;=\u0026thinsp;least absolute shrinkage and selection operator; COPD\u0026thinsp;=\u0026thinsp;chronic pulmonary obstructive disease; PBT\u0026thinsp;=\u0026thinsp;proton-beam therapy; ICI\u0026thinsp;=\u0026thinsp;immune checkpoint inhibitor; MLD\u0026thinsp;=\u0026thinsp;mean lung dose; V20\u0026thinsp;=\u0026thinsp;volume of lung receiving\u0026thinsp;\u0026gt;\u0026thinsp;20 Gy; pMLD\u0026thinsp;=\u0026thinsp;perfused mean lung dose; pV20\u0026thinsp;=\u0026thinsp;perfused lung volume receiving\u0026thinsp;\u0026ge;\u0026thinsp;20 Gy; pF20\u0026thinsp;=\u0026thinsp;fraction of integral lung function receiving\u0026thinsp;\u0026ge;\u0026thinsp;20 Gy;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"11\"\u003e*HR from LASSO-Cox model; a dash (-) indicates the corresponding feature was included in the model but the LASSO did not select it in the final model (HR\u0026thinsp;=\u0026thinsp;1); blank cells indicate the features were not included in the LASSO-Cox model.\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e shows the LASSO-multivariable models of time-varying pneumonitis risk from pre-treatment lung perfusion radiomics features independently or with other factors such as COPD and lung volume. Models including only the radiomics features (orange points) with each feature class could not discriminate between patients with and without pneumonitis (c-index 0.34\u0026ndash;0.48). However, when perfused lung radiomics shape (c-index 0.77 [95% CI: 0.65\u0026ndash;0.88], p\u0026thinsp;=\u0026thinsp;0.27 vs. benchmark COPD-only model) and size feature classes (c-index 0.79 [95% CI: 0.66\u0026ndash;0.91], p\u0026thinsp;=\u0026thinsp;0.26 vs. benchmark COPD-only model) were combined with COPD (blue points) the discrimination of time-varying pneumonitis risk improved but did not reach statistical significance compared to benchmark models. The addition of lung voxel volume to perfusion lung radiomics features and COPD (green points) had little impact on discrimination of time-varying pneumonitis risk (Fig. \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eSince COPD was the dominant risk factor for pneumonitis, we investigated its correlation to radiomic features. Figure \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e shows the LASSO logistic regression models for COPD prediction based on perfused lung radiomics features. The models included radiomic feature classes separately. COPD was marginally significantly associated with perfused lung radiomics size features (AUC 0.69 [95% CI: 0.50\u0026ndash;0.89], p\u0026thinsp;=\u0026thinsp;0.051) but not with the features in the other radiomic feature classes (AUC 0.36\u0026ndash;0.70, p\u0026thinsp;\u0026gt;\u0026thinsp;0.11 for all). Since COPD largely correlated to radiomic size feature class, we also examined a model with lung voxel volume as the only predictor (AUC 0.75 [95% CI: 0.59\u0026ndash;0.91]) and added lung voxel volume to each class-specific model (blue points in Fig. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e). While lung voxel volume alone was significantly associated with COPD (p\u0026thinsp;=\u0026thinsp;0.002), none of the models which combined voxel volume with perfused lung radiomic features were statistically significantly predictive of COPD (AUC 0.61\u0026ndash;0.66, p\u0026thinsp;\u0026gt;\u0026thinsp;0.15 for all). As shown in Fig. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e, perfused lung radiomic texture features were highly correlated with lung volume (adj R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;0.84-1.00).\u0026nbsp;\u003c/p\u003e\u0026nbsp;\u003ctable border=\"1\" id=\"Tab3\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eCorrelation of lung voxel volume with perfused lung radiomic features within each feature class.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eCorrelation between\u003c/p\u003e\n \u003cp\u003eVolume and\u003c/p\u003e\n \u003cp\u003eAll Features within a Class\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eFeature Class\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eNumber of\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eFeatures in Class\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eadj .R\u003c/strong\u003e\u003csup\u003e\u003cstrong\u003e2\u003c/strong\u003e\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eP-value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSize*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.00\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eShape\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFirst Order\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.00\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGLCM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGLDM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGLRLM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.00\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGLSZM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.98\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNGTDM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\"\u003e*Voxel volume is excluded from the set of size features in the calculations.\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003ctable border=\"1\" id=\"Tab4\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003c/caption\u003e\n\u003c/table\u003e\n"},{"header":"Discussion","content":"\u003cp\u003eTo our knowledge, we present the first study exploring the role of MAA-SPECT lung perfusion radiomics for pneumonitis risk stratification. A unique cohort of LA-NSCLC patients enrolled on the FLARE-RT protocol (NCT02773238) and received chemoradiation guided by functional lung avoidance planning and selective dose escalation based on mid-treatment fluorodeoxyglucose-PET response status, with half of patients receiving consolidation anti-PD-L1 ICI-therapy. In this cohort, we evaluated clinical and reported lung dosimetry parameters independently and in combination with perfused lung radiomic features derived from MAA-SPECT for pneumonitis risk stratification.\u003c/p\u003e \u003cp\u003eMoran et al evaluated GLCM-texture and first-order features to assess their ability to distinguish between oncologist-defined post-SBRT lung injury, with GLCM features outperforming first-order features (\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e). Cunliffe et al observed CT-texture changes in high dose regions that correlated strongly to radiation pneumonitis status, while dosimetric parameters failed to show any association. Krafft et al reported that the addition of CT-based texture features along with clinical and dosimetric features improved the performance of pneumonitis prediction models (\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e). Our investigation revealed that none of the radiomics features classes showed promise in predicting risk of pneumonitis independently. However, when radiomics shape and size class features were combined with COPD, the discrimination of time-varying risk prediction of pneumonitis improved (c-index\u0026thinsp;=\u0026thinsp;0.77\u0026ndash;0.79) although it did not reach statistical significance. Similar to cancer radiomics where tumour volume is a confounding feature (\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e), many perfused lung radiomic features showed marked dependencies with volume of the lung, which is the organ at risk in our study, suggesting the radiomic features may serve as size surrogates rather than independent predictors of pneumonitis risk.\u003c/p\u003e \u003cp\u003eIn the era of ICI consolidation therapy for LA-NSCLC, few studies have evaluated clinical and dosimetric risk factors for pneumonitis. Shaverdian et al found that validated pulmonary toxicity models underestimated the incidence of pneumonitis in the setting of consolidation durvalumab ICI (\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e). Inoue et al reported that clinical and dosimetric parameters were not significant predictors of pneumonitis in LA-NSCLC treated with the chemoradiation and durvalumab regimen (\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e). Our findings in the FLARE-RT cohort were concordant with these studies, as our anatomic and perfused lung dosimetry failed to predict pneumonitis incidence. We observed that COPD or pre-existing emphysema was the dominant risk factor for the development of pneumonitis in this cohort of patients. These results are similar to the study reported by Zhou et al who observed that pulmonary emphysema was a risk factor for NSCLC patients with squamous cell carcinoma (\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e). Patients with COPD have been known to exhibit increases in lung volume due to limited expiratory airflow (\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e, \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e). In this study, we found that COPD was more prevalent in patients with larger lung volumes, which is consistent with the lung physiology as reported in the studies above.\u003c/p\u003e \u003cp\u003eOur study has some limitations. In this preliminary discovery phase, we report on a modest patient cohort, with only half of patients receiving ICI-therapy. Nonetheless, very few reports are available on the incidence of immunotherapy-related pneumonitis following chemoradiation for locally advanced non-small cell lung cancer, and none incorporated functional lung avoidance planning techniques or functional lung radiomics. Moreover, our study lacks external validation of the functional lung radiomic pneumonitis prediction model. There is opportunity to validate the findings of this study in a larger cohort of patients receiving chemoradiation and ICI-therapy to further elucidate the influence of COPD, perfused lung dosimetry, and perfused lung radiomics on pneumonitis risk. Lastly, while we relied on SPECT CNTS data, the latest generation SPECT scanners will enable calculation of SPECT standardized uptake values (SUV) that are analogous to PET SUV, thus facilitating quantitative SPECT radiomics. Future quantitative SPECT radiomic approaches should consider the effects of total lung volume and perfused lung available for MAA tracer distribution on SPECT SUV calculations.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eAs immune modulating therapies grow more influential in the management of unresectable locally advanced non-small cell lung cancer, modelling of pneumonitis risk secondary to radiation and systemic therapy requires investigation of biomarkers and factors beyond conventional radiation dosimetry. Combinations of clinical, dosimetric, and radiomic features may support personalized treatments to mitigate the risk of developing pneumonitis. In this work, we identified the presence of underlying pulmonary disease as a strong predictor radiation and immune-mediated pneumonitis risk and observed that perfused lung radiomics may represent lung volume surrogates rather than independent predictors of pneumonitis risk. Further investigation of functional lung radiomics is warranted.\u003c/p\u003e "},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthical Approval and Consent to participate:\u003c/strong\u003e The study was reviewed and approved by the institutional review board. All patients included have consented to the study. \u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication:\u003c/strong\u003e All authors consent for manuscript to be published in Radiation Oncology, if accepted. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of supporting data:\u003c/strong\u003e The datasets from the current study are not publicly available prior to reporting of mature outcomes from the parent clinical trial. Requests for data and materials should be sent to the corresponding author.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests:\u003c/strong\u003e JZ and RR serve as consultants to Astrazeneca. PEK declares support from GE Healthcare and is co-founder of PET/X, LLC. RSM and HJV declare support from Philips Healthcare and serve as consultants for MIM Software\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding:\u003c/strong\u003e This investigation was supported by NIH/NCI R01CA204301.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026apos; contributions:\u003c/strong\u003e The authors confirm contribution to the paper as follows: study conception and design: SRB, PK, RSM, HJV, JZ, SRB; data collection: HMT, PF, BS; analysis and interpretation of results HMT, DSH, PF, BS, SRB; draft manuscript preparation: HMT, DSH, SRB; manuscript review and revision PK, RSM, HJV, RR. \u0026nbsp;All authors reviewed the results and approved the final version of the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements:\u003c/strong\u003e This investigation was supported by NIH/NCI R01CA204301. The authors gratefully acknowledge the patients who participated in the FLARE-RT clinical trial (NCT02773238). \u0026nbsp; This research was also supported by the Biostatistics Shared Resource of the Fred Hutch/University of Washington Cancer Consortium (P30 CA015704). We thank Priya Vissamraju and Christina Lo for coordinating FLARE-RT protocol imaging and curating the study database. We acknowledge the efforts of Nuclear Medicine, Radiation Oncology, and Proton Center staff during SPECT/CT acquisitions, radiation therapy planning, and image-guided radiation therapy delivery.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eSchoenfeld JD, Nishino M, Severgnini M, Manos M, Mak RH, Hodi FS. Pneumonitis resulting from radiation and immune checkpoint blockade illustrates characteristic clinical, radiologic and circulating biomarker features. \u003cem\u003eJournal for ImmunoTherapy of Cancer\u003c/em\u003e. 2019;7(1): 112. https://doi.org/10.1186/s40425-019-0583-3.\u003c/li\u003e\n\u003cli\u003eJain V, Berman AT. Radiation Pneumonitis: Old Problem, New Tricks. \u003cem\u003eCancers\u003c/em\u003e. 2018;10(7). https://doi.org/10.3390/cancers10070222.\u003c/li\u003e\n\u003cli\u003eAntonia SJ, Villegas A, Daniel D, Vicente D, Murakami S, Hui R, et al. Durvalumab after Chemoradiotherapy in Stage III Non-Small-Cell Lung Cancer. \u003cem\u003eThe New England Journal of Medicine\u003c/em\u003e. 2017;377(20): 1919\u0026ndash;1929. https://doi.org/10.1056/NEJMoa1709937.\u003c/li\u003e\n\u003cli\u003eAhn M-J. Consolidation of immunotherapy becomes new standard of care in unresectable stage III non-small cell lung cancer. \u003cem\u003eJournal of Thoracic Disease\u003c/em\u003e. 2018;10(3): 1205\u0026ndash;1206. https://doi.org/10.21037/jtd.2018.03.55.\u003c/li\u003e\n\u003cli\u003eCadranel J, Canellas A, Matton L, Darrason M, Parrot A, Naccache J-M, et al. Pulmonary complications of immune checkpoint inhibitors in patients with nonsmall cell lung cancer. \u003cem\u003eEuropean Respiratory Review\u003c/em\u003e. 2019;28(153). https://doi.org/10.1183/16000617.0058-2019.\u003c/li\u003e\n\u003cli\u003eDavis R m., Patel P, Ikladios O i. Immune-Mediated Pneumonitis Due to Nivolumab: Is It Worth Using? In: \u003cem\u003eD35. DRUG INDUCED LUNG DISEASE: CASE REPORTS\u003c/em\u003e. American Thoracic Society; 2018. p. A6609\u0026ndash;A6609. https://doi.org/10.1164/ajrccm-conference.2018.197.1_MeetingAbstracts.A6609. [Accessed 24th August 2020].\u003c/li\u003e\n\u003cli\u003eNaidoo J, Nishino M, Patel SP, Shankar B, Rekhtman N, Illei P, et al. Immune-Related Pneumonitis After Chemoradiotherapy and Subsequent Immune Checkpoint Blockade in Unresectable Stage III Non\u0026ndash;Small-Cell Lung Cancer. \u003cem\u003eClinical Lung Cancer\u003c/em\u003e. 2020; https://doi.org/10.1016/j.cllc.2020.02.025.\u003c/li\u003e\n\u003cli\u003eShohdy KS, Abdel-Rahman O. Risk of pneumonitis with different immune checkpoint inhibitors in NSCLC. \u003cem\u003eAnnals of Translational Medicine\u003c/em\u003e. 2017;5(17). https://doi.org/10.21037/atm.2017.06.67.\u003c/li\u003e\n\u003cli\u003eZhong L, Altan M, Shannon VR, Sheshadri A. Immune-Related Adverse Events: Pneumonitis. \u003cem\u003eImmunotherapy\u003c/em\u003e. 2020;1244: 255\u0026ndash;269. https://doi.org/10.1007/978-3-030-41008-7_13.\u003c/li\u003e\n\u003cli\u003eWang S, Liao Z, Wei X, Liu HH, Tucker SL, Hu C, et al. Analysis of clinical and dosimetric factors associated with treatment-related pneumonitis (TRP) in patients with non\u0026ndash;small-cell lung cancer (NSCLC) treated with concurrent chemotherapy and three-dimensional conformal radiotherapy (3D-CRT). \u003cem\u003eInternational Journal of Radiation Oncology*Biology*Physics\u003c/em\u003e. 2006;66(5): 1399\u0026ndash;1407. https://doi.org/10.1016/j.ijrobp.2006.07.1337.\u003c/li\u003e\n\u003cli\u003eKong F-M (Spring), Wang S. Nondosimetric Risk Factors for Radiation-Induced Lung Toxicity. \u003cem\u003eSeminars in Radiation Oncology\u003c/em\u003e. 2015;25(2): 100\u0026ndash;109. https://doi.org/10.1016/j.semradonc.2014.12.003.\u003c/li\u003e\n\u003cli\u003evon Reibnitz D, Yorke ED, Oh JH, Apte AP, Yang J, Pham H, et al. Predictive Modeling of Thoracic Radiotherapy Toxicity and the Potential Role of Serum Alpha-2-Macroglobulin. \u003cem\u003eFrontiers in Oncology\u003c/em\u003e. 2020;10. https://doi.org/10.3389/fonc.2020.01395.\u003c/li\u003e\n\u003cli\u003ePalma DA, Senan S, Tsujino K, Barriger RB, Rengan R, Moreno M, et al. Predicting Radiation Pneumonitis After Chemoradiation Therapy for Lung Cancer: An International Individual Patient Data Meta-analysis. \u003cem\u003eInternational Journal of Radiation Oncology*Biology*Physics\u003c/em\u003e. 2013;85(2): 444\u0026ndash;450. https://doi.org/10.1016/j.ijrobp.2012.04.043.\u003c/li\u003e\n\u003cli\u003eLee HJ, Zeng J, Vesselle HJ, Patel SA, Rengan R, Bowen SR. Correlation of Functional Lung Heterogeneity and Dosimetry to Radiation Pneumonitis using Perfusion SPECT/CT and FDG PET/CT Imaging. \u003cem\u003eInternational Journal of Radiation Oncology \u0026bull; Biology \u0026bull; Physics\u003c/em\u003e. 2018;0(0). https://doi.org/10.1016/j.ijrobp.2018.05.051.\u003c/li\u003e\n\u003cli\u003eYorke ED, Jackson A, Rosenzweig KE, Merrick SA, Gabrys D, Venkatraman ES, et al. Dose-volume factors contributing to the incidence of radiation pneumonitis in non-small-cell lung cancer patients treated with three-dimensional conformal radiation therapy. \u003cem\u003eInternational Journal of Radiation Oncology*Biology*Physics\u003c/em\u003e. 2002;54(2): 329\u0026ndash;339. https://doi.org/10.1016/S0360-3016(02)02929-2.\u003c/li\u003e\n\u003cli\u003eMarks LB, Hollis D, Munley M, Bentel G, Garipagaoglu M, Fan M, et al. The role of lung perfusion imaging in predicting the direction of radiation-induced changes in pulmonary function tests. \u003cem\u003eCancer\u003c/em\u003e. 2000;88(9): 2135\u0026ndash;2141. https://doi.org/10.1002/(SICI)1097-0142(20000501)88:9\u0026lt;2135::AID-CNCR20\u0026gt;3.0.CO;2-H.\u003c/li\u003e\n\u003cli\u003eWen G, Tan Y-T, Lan X-W, He Z-C, Huang J-H, Shi J-T, et al. New Clinical Features and Dosimetric Predictor Identification for Symptomatic Radiation Pneumonitis after Tangential Irradiation in Breast Cancer Patients. \u003cem\u003eJournal of Cancer\u003c/em\u003e. 2017;8(18): 3795\u0026ndash;3802. https://doi.org/10.7150/jca.21158.\u003c/li\u003e\n\u003cli\u003eValdes G, Solberg TD, Heskel M, Ungar L, Simone CB. Using machine learning to predict radiation pneumonitis in patients with stage I non-small cell lung cancer treated with stereotactic body radiation therapy. \u003cem\u003ePhysics in Medicine and Biology\u003c/em\u003e. 2016;61(16): 6105\u0026ndash;6120. https://doi.org/10.1088/0031-9155/61/16/6105.\u003c/li\u003e\n\u003cli\u003eChen S, Zhou S, Yin F-F, Marks LB, Das SK. Investigation of the support vector machine algorithm to predict lung radiation-induced pneumonitis. \u003cem\u003eMedical Physics\u003c/em\u003e. 2007;34(10): 3808\u0026ndash;3814. https://doi.org/10.1118/1.2776669.\u003c/li\u003e\n\u003cli\u003eAment SJ, Maus S, Reber H, Buchholz HG, Bausbacher N, Brochhausen C, et al. PET lung ventilation/perfusion imaging using (68)Ga aerosol (Galligas) and (68)Ga-labeled macroaggregated albumin. \u003cem\u003eRecent Results in Cancer Research. Fortschritte Der Krebsforschung. Progres Dans Les Recherches Sur Le Cancer\u003c/em\u003e. 2013;194: 395\u0026ndash;423. https://doi.org/10.1007/978-3-642-27994-2_22.\u003c/li\u003e\n\u003cli\u003eSiva S, Callahan J, Kron T, Martin OA, MacManus MP, Ball DL, et al. A prospective observational study of Gallium-68 ventilation and perfusion PET/CT during and after radiotherapy in patients with non-small cell lung cancer. \u003cem\u003eBMC Cancer\u003c/em\u003e. 2014;14. https://doi.org/10.1186/1471-2407-14-740.\u003c/li\u003e\n\u003cli\u003eHoover DA, Capaldi DP, Sheikh K, Palma DA, Rodrigues GB, Dar AR, et al. Functional lung avoidance for individualized radiotherapy (FLAIR): study protocol for a randomized, double-blind clinical trial. \u003cem\u003eBMC Cancer\u003c/em\u003e. 2014;14(1): 934. https://doi.org/10.1186/1471-2407-14-934.\u003c/li\u003e\n\u003cli\u003eSiva S, Devereux T, Ball DL, MacManus MP, Hardcastle N, Kron T, et al. Ga-68 MAA Perfusion 4D-PET/CT Scanning Allows for Functional Lung Avoidance Using Conformal Radiation Therapy Planning. \u003cem\u003eTechnology in Cancer Research \u0026amp; Treatment\u003c/em\u003e. 2016;15(1): 114\u0026ndash;121. https://doi.org/10.1177/1533034614565534.\u003c/li\u003e\n\u003cli\u003eVinogradskiy Y, Schubert L, Diot Q, Waxweiller T, Koo P, Castillo R, et al. Regional Lung Function Profiles of Stage I and III Lung Cancer Patients: An Evaluation for Functional Avoidance Radiation Therapy. \u003cem\u003eInternational Journal of Radiation Oncology, Biology, Physics\u003c/em\u003e. 2016;95(4): 1273\u0026ndash;1280. https://doi.org/10.1016/j.ijrobp.2016.02.058.\u003c/li\u003e\n\u003cli\u003eLee E, Zeng J, Miyaoka RS, Saini J, Kinahan PE, Sandison GA, et al. Functional lung avoidance and response-adaptive escalation (FLARE) RT: multimodality plan dosimetry of a precision radiation oncology strategy. \u003cem\u003eMedical physics\u003c/em\u003e. 2017;44(7): 3418\u0026ndash;3429. https://doi.org/10.1002/mp.12308.\u003c/li\u003e\n\u003cli\u003eBucknell NW, Hardcastle N, Bressel M, Hofman MS, Kron T, Ball D, et al. Functional lung imaging in radiation therapy for lung cancer: A systematic review and meta-analysis. \u003cem\u003eRadiotherapy and Oncology\u003c/em\u003e. 2018; https://doi.org/10.1016/j.radonc.2018.07.014.\u003c/li\u003e\n\u003cli\u003eFarr KP, West K, Yeghiaian-Alvandi R, Farlow D, Stensmyr R, Chicco A, et al. Functional perfusion image guided radiation treatment planning for locally advanced lung cancer. \u003cem\u003ePhysics and Imaging in Radiation Oncology\u003c/em\u003e. 2019;11: 76\u0026ndash;81. https://doi.org/10.1016/j.phro.2019.08.007.\u003c/li\u003e\n\u003cli\u003eFaught AM, Yamamoto T, Castillo R, Castillo E, Zhang J, Miften M, et al. Evaluating Which Dose-Function Metrics Are Most Critical for Functional-Guided Radiation Therapy. \u003cem\u003eInternational Journal of Radiation Oncology, Biology, Physics\u003c/em\u003e. 2017;99(1): 202\u0026ndash;209. https://doi.org/10.1016/j.ijrobp.2017.03.051.\u003c/li\u003e\n\u003cli\u003eVinogradskiy Y, Castillo R, Castillo E, Tucker SL, Liao Z, Guerrero T, et al. Use of 4-Dimensional Computed Tomography-Based Ventilation Imaging to Correlate Lung Dose and Function With Clinical Outcomes. \u003cem\u003eInternational journal of radiation oncology, biology, physics\u003c/em\u003e. 2013;86(2). https://doi.org/10.1016/j.ijrobp.2013.01.004.\u003c/li\u003e\n\u003cli\u003eSeppenwoolde Y, De Jaeger K, Boersma LJ, Belderbos JSA, Lebesque JV. Regional differences in lung radiosensitivity after radiotherapy for non-small-cell lung cancer. \u003cem\u003eInternational Journal of Radiation Oncology, Biology, Physics\u003c/em\u003e. 2004;60(3): 748\u0026ndash;758. https://doi.org/10.1016/j.ijrobp.2004.04.037.\u003c/li\u003e\n\u003cli\u003eO\u0026rsquo;Reilly S, Jain V, Huang Q, Cheng C, Teo B-KK, Yin L, et al. Dose to Highly Functional Ventilation Zones Improves Prediction of Radiation Pneumonitis for Proton and Photon Lung Cancer Radiation Therapy. \u003cem\u003eInternational Journal of Radiation Oncology, Biology, Physics\u003c/em\u003e. 2020;107(1): 79\u0026ndash;87. https://doi.org/10.1016/j.ijrobp.2020.01.014.\u003c/li\u003e\n\u003cli\u003eBousabarah K, Temming S, Hoevels M, Borggrefe J, Baus WW, Ruess D, et al. Radiomic analysis of planning computed tomograms for predicting radiation-induced lung injury and outcome in lung cancer patients treated with robotic stereotactic body radiation therapy. \u003cem\u003eStrahlentherapie und Onkologie\u003c/em\u003e. 2019;195(9): 830\u0026ndash;842. https://doi.org/10.1007/s00066-019-01452-7.\u003c/li\u003e\n\u003cli\u003eKrafft SP, Rao A, Stingo F, Briere TM, Court LE, Liao Z, et al. The utility of quantitative CT radiomics features for improved prediction of radiation pneumonitis. \u003cem\u003eMedical Physics\u003c/em\u003e. 2018;45(11): 5317\u0026ndash;5324. https://doi.org/10.1002/mp.13150.\u003c/li\u003e\n\u003cli\u003eMoran A, Daly ME, Yip SSF, Yamamoto T. Radiomics-based Assessment of Radiation-induced Lung Injury After Stereotactic Body Radiotherapy. \u003cem\u003eClinical Lung Cancer\u003c/em\u003e. 2017;18(6): e425\u0026ndash;e431. https://doi.org/10.1016/j.cllc.2017.05.014.\u003c/li\u003e\n\u003cli\u003eCunliffe A, Armato SG, Castillo R, Pham N, Guerrero T, Al-Hallaq HA. Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. \u003cem\u003eInternational Journal of Radiation Oncology, Biology, Physics\u003c/em\u003e. 2015;91(5): 1048\u0026ndash;1056. https://doi.org/10.1016/j.ijrobp.2014.11.030.\u003c/li\u003e\n\u003cli\u003eAnthony GJ, Cunliffe A, Castillo R, Pham N, Guerrero T, Armato SG, et al. Incorporation of pre-therapy 18F-FDG uptake data with CT texture features into a radiomics model for radiation pneumonitis diagnosis. \u003cem\u003eMedical Physics\u003c/em\u003e. 2017;44(7): 3686\u0026ndash;3694. https://doi.org/10.1002/mp.12282.\u003c/li\u003e\n\u003cli\u003eShaverdian N, Thor M, Shepherd AF, Offin MD, Jackson A, Wu AJ, et al. Radiation pneumonitis in lung cancer patients treated with chemoradiation plus durvalumab. \u003cem\u003eCancer Medicine\u003c/em\u003e. 2020;9(13): 4622\u0026ndash;4631. https://doi.org/10.1002/cam4.3113.\u003c/li\u003e\n\u003cli\u003eInoue H, Ono A, Kawabata T, Mamesaya N, Kawamura T, Kobayashi H, et al. Clinical and radiation dose-volume factors related to pneumonitis after treatment with radiation and durvalumab in locally advanced non-small cell lung cancer. \u003cem\u003eInvestigational New Drugs\u003c/em\u003e. 2020; https://doi.org/10.1007/s10637-020-00917-2.\u003c/li\u003e\n\u003cli\u003eHorn K, Tomas H, Vesselle H, Kinahan P, Miyaoka R, Rengan R, et al. Concordance of quantitative FDG PET/CT imaging biomarkers for classifying early response to chemoradiotherapy in patients with locally advanced non-small cell lung cancer. \u003cem\u003eJournal of Nuclear Medicine\u003c/em\u003e. 2020;61(supplement 1): 1333\u0026ndash;1333. \u003c/li\u003e\n\u003cli\u003eSasidharan BK, Bowen SR, Rengan R, Patel SA, Thomas HMT, Miyaoka RS, et al. Early PET/CT Response Assessment for Selective FDG PET-Guided Dose Escalation in Locally Advanced NSCLC Patients Enrolled on the FLARE-RT Protocol. \u003cem\u003eInternational Journal of Radiation Oncology \u0026bull; Biology \u0026bull; Physics\u003c/em\u003e. 2018;102(3): e703\u0026ndash;e704. https://doi.org/10.1016/j.ijrobp.2018.07.1891.\u003c/li\u003e\n\u003cli\u003eSaini J, Traneus E, Maes D, Regmi R, Bowen SR, Bloch C, et al. Advanced Proton Beam Dosimetry Part I: review and performance evaluation of dose calculation algorithms. \u003cem\u003eTranslational Lung Cancer Research\u003c/em\u003e. 2018;7(2): 171\u0026ndash;179. https://doi.org/10.21037/tlcr.2018.04.05.\u003c/li\u003e\n\u003cli\u003eMaes D, Saini J, Zeng J, Rengan R, Wong T, Bowen SR. Advanced proton beam dosimetry part II: Monte Carlo vs. pencil beam-based planning for lung cancer. \u003cem\u003eTranslational Lung Cancer Research\u003c/em\u003e. 2018;7(2): 114\u0026ndash;121. https://doi.org/10.21037/tlcr.2018.04.04.\u003c/li\u003e\n\u003cli\u003eFedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin J-C, Pujol S, et al. 3D Slicer as an Image Computing Platform for the Quantitative Imaging Network. \u003cem\u003eMagnetic resonance imaging\u003c/em\u003e. 2012;30(9): 1323\u0026ndash;1341. https://doi.org/10.1016/j.mri.2012.05.001.\u003c/li\u003e\n\u003cli\u003evan Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational Radiomics System to Decode the Radiographic Phenotype. \u003cem\u003eCancer Research\u003c/em\u003e. 2017;77(21): e104\u0026ndash;e107. https://doi.org/10.1158/0008-5472.CAN-17-0339.\u003c/li\u003e\n\u003cli\u003eTibshirani R. Regression Shrinkage and Selection via the Lasso. \u003cem\u003eJournal of the Royal Statistical Society. Series B (Methodological)\u003c/em\u003e. 1996;58(1): 267\u0026ndash;288. \u003c/li\u003e\n\u003cli\u003eHarrell FE, Lee KL, Mark DB. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. \u003cem\u003eStatistics in Medicine\u003c/em\u003e. 1996;15(4): 361\u0026ndash;387. https://doi.org/10.1002/(SICI)1097-0258(19960229)15:4\u0026lt;361::AID-SIM168\u0026gt;3.0.CO;2-4.\u003c/li\u003e\n\u003cli\u003eSteyerberg EW, Harrell FE, Borsboom GJ, Eijkemans MJ, Vergouwe Y, Habbema JD. Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. \u003cem\u003eJournal of Clinical Epidemiology\u003c/em\u003e. 2001;54(8): 774\u0026ndash;781. https://doi.org/10.1016/s0895-4356(01)00341-9.\u003c/li\u003e\n\u003cli\u003eTraverso A, Kazmierski M, Zhovannik I, Welch M, Wee L, Jaffray D, et al. Machine learning helps identifying volume-confounding effects in radiomics. \u003cem\u003ePhysica Medica\u003c/em\u003e. 2020;71: 24\u0026ndash;30. https://doi.org/10.1016/j.ejmp.2020.02.010.\u003c/li\u003e\n\u003cli\u003eZhou Z, Song X, Wu A, Liu H, Wu H, Wu Q, et al. Pulmonary emphysema is a risk factor for radiation pneumonitis in NSCLC patients with squamous cell carcinoma after thoracic radiation therapy. \u003cem\u003eScientific Reports\u003c/em\u003e. 2017;7(1): 2748. https://doi.org/10.1038/s41598-017-02739-4.\u003c/li\u003e\n\u003cli\u003e\u003cem\u003ePhysiology and consequences of lung hyperinflation in COPD | European Respiratory Society\u003c/em\u003e. https://err.ersjournals.com/content/15/100/61 [Accessed 15th February 2022].\u003c/li\u003e\n\u003cli\u003eBiselli P, Grossman PR, Kirkness JP, Patil SP, Smith PL, Schwartz AR, et al. The effect of increased lung volume in chronic obstructive pulmonary disease on upper airway obstruction during sleep. \u003cem\u003eJournal of Applied Physiology\u003c/em\u003e. 2015;119(3): 266\u0026ndash;271. https://doi.org/10.1152/japplphysiol.00455.2014.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"functional lung imaging, radiomics, SPECT, pneumonitis, radiation therapy, immunotherapy, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-1680696/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1680696/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground:\u003c/strong\u003e Patients undergoing chemoradiation and immune checkpoint inhibitor (ICI) therapy for locally advanced non-small cell lung cancer (LA-NSCLC) experience pulmonary toxicity at higher rates than historical reports. We investigated the role of novel functional lung radiomics, relative to functional lung dosimetry and clinical characteristics, for pneumonitis risk stratification in LA-NSCLC.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eThirty-nine patients with LA-NSCLC were prospectively enrolled on the FLARE-RT trial (NCT02773238). All received concurrent chemoradiation using functional lung avoidance planning, while 21/39 received consolidation durvalumab ICI. Within tumour-subtracted lung regions, 110 radiomics features (shape, intensity, texture) were extracted on pre-treatment [\u003csup\u003e99m\u003c/sup\u003eTc]MAA SPECT/CT perfusion (PERF) images using fixed-bin-width discretization. The performance of functional lung radiomics for pneumonitis (CTCAEv4 grade 2 or higher) risk stratification was benchmarked against previously reported lung dosimetric parameters and clinical risk factors. Multivariate least absolute shrinkage and selection operator (LASSO) Cox models of time-varying pneumonitis risk were constructed, and prediction performance was evaluated using optimism-adjusted concordance index (c-index) with 95% confidence interval reporting throughout.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: Pneumonitis occurred in 16/39 (41%) patients. Among clinical characteristics and anatomic/functional lung dosimetry variables, only the presence of baseline chronic obstructive pulmonary disease (COPD) was significantly associated with the development of pneumonitis (HR 4.59 [1.69-12.49]) and served as the primary prediction benchmark model (c-index 0.69 [0.59-0.80]). Discrimination of time-varying pneumonitis risk was numerically higher when combining COPD with perfused lung radiomics size (c-index 0.77 [0.65-0.88]) or shape feature classes (c-index 0.79 [0.66-0.91]) but did not reach statistical significance compared to benchmark models (p\u0026gt;0.26). COPD was associated with perfused lung radiomics size features, including patients with larger lung volumes (AUC 0.75 [0.59-0.91]). Perfused lung radiomic texture features were correlated with lung volume (adj R\u003csup\u003e2\u003c/sup\u003e=0.84-1.00), representing surrogates rather than independent predictors of pneumonitis risk.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eConclusions\u003c/strong\u003e: In patients undergoing chemoradiation with functional lung avoidance therapy and optional consolidative immune checkpoint inhibitor (ICI) therapy for LA-NSCLC, the strongest predictor of pneumonitis was the presence of baseline chronic obstructive pulmonary disease. Our results support functional lung radiomics as surrogates of COPD. Further study of clinical, dosimetric, and radiomic feature combinations for radiation and immune-mediated pneumonitis in larger patient populations is warranted. \u0026nbsp;\u003c/p\u003e","manuscriptTitle":"Radiation and immune checkpoint inhibitor-mediated pneumonitis risk stratification in patients with locally advanced non-small cell lung cancer: role of functional lung radiomics?","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-05-27 14:00:47","doi":"10.21203/rs.3.rs-1680696/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2470d029-0f76-4ab5-a226-cf6f1b3695e7","owner":[],"postedDate":"May 27th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2022-05-30T07:29:09+00:00","versionOfRecord":[],"versionCreatedAt":"2022-05-27 14:00:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-1680696","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1680696","identity":"rs-1680696","version":["v1"]},"buildId":"cBFmMYwuxLRRLfASyISRj","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}