{"paper_id":"98f71eba-565c-46d6-947a-d30250678fe6","body_text":"Abstract\nObjective\nTo develop and validate a model that can preoperatively identify the ovarian clear cell carcinoma (OCCC) subtype in epithelial ovarian cancer (EOC) using CT imaging radiomics and clinical data.\nMaterial and methods\nWe retrospectively analyzed data from 282 patients with EOC (training set = 225, testing set = 57) who underwent pre-surgery CT examinations. Patients were categorized into OCCC or other EOC subtypes based on postoperative pathology. Seven clinical characteristics (age, cancer antigen [CA]-125, CA-199, endometriosis, venous thromboembolism, hypercalcemia, stage) were collected. Primary tumors were manually delineated on portal venous-phase images, and 1218 radiomic features were extracted. The F-test-based feature selection method and logistic regression algorithm were used to build the radiomic signature, clinical model, and integrated model. To explore the effects of integrated model-assisted diagnosis, five radiologists independently interpreted images in the testing set and reevaluated cases two weeks later with knowledge of the integrated model’s output. The diagnostic performances of the predictive models, radiologists, and radiologists aided by the integrated model were evaluated.\nResults\nThe integrated model containing the radiomic signature (constructed by four wavelet radiomic features) and three clinical characteristics (CA-125, endometriosis, and hypercalcinemia), showed better diagnostic performance (AUC = 0.863 [0.762–0.964]) than the clinical model (AUC = 0.792 [0.630–0.953], p = 0.295) and the radiomic signature alone (AUC = 0.781 [0.636–0.926], p = 0.185). The diagnostic sensitivities of the radiologists were significantly improved when using the integrated model (p = 0.023–0.041), while the specificities and accuracies were maintained (p = 0.074–1.000).\nConclusion\nOur integrated model shows great potential to facilitate the early identification of the OCCC subtype in EOC, which may enhance subtype-specific therapy and clinical management.\nSimilar content being viewed by others\nAbbreviations\n- AUC:\n-\nArea under the curve\n- CT:\n-\nComputed tomography\n- CA-125:\n-\nCancer antigen-125\n- CA-199:\n-\nCancer antigen-199\n- CI:\n-\nConfidence interval\n- EOC:\n-\nEpithelial ovarian cancer\n- FIGO:\n-\nInternational federation of gynecology and obstetrics\n- HGSC:\n-\nHigh-grade serous carcinoma\n- NCCN:\n-\nNational comprehensive cancer network\n- OCCC:\n-\nOvarian clear cell carcinoma\nReferences\nSung H, Ferlay J, Siegel RL et al (2021) Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71:209–249. https://doi.org/10.3322/caac.21660\n(2020) WHO classification of tumours editorial board. WHO classification of tumours. female genital tumours, (5th edn), IARC Press, Lyon\nIida Y, Okamoto A, Hollis RL, Gourley C, Herrington CS (2021) Clear cell carcinoma of the ovary: a clinical and molecular perspective. Int J Gynecol Cancer 31:605–616. https://doi.org/10.1136/ijgc-2020-001656\nZhu C, Xu Z, Zhang T et al (2021) Updates of pathogenesis, diagnostic and therapeutic perspectives for ovarian clear cell carcinoma. J Cancer 12:2295–2316. https://doi.org/10.7150/jca.53395\nKim SI, Lim MC, Lim J et al (2016) Incidence of epithelial ovarian cancer according to histologic subtypes in Korea, 1999 to 2012. J Gynecol Oncol 27:e5. https://doi.org/10.3802/jgo.2016.27.e5\nOliver KE, Brady WE, Birrer M et al (2017) An evaluation of progression free survival and overall survival of ovarian cancer patients with clear cell carcinoma versus serous carcinoma treated with platinum therapy: an NRG oncology/gynecologic oncology group experience. Gynecol Oncol 147:243–249. https://doi.org/10.1016/j.ygyno.2017.08.004\nLee YY, Kim TJ, Kim MJ et al (2011) Prognosis of ovarian clear cell carcinoma compared to other histological subtypes: a meta-analysis. Gynecol Oncol 122:541–547. https://doi.org/10.1016/j.ygyno.2011.05.009\nTakano M, Tsuda H, Sugiyama T (2012) Clear cell carcinoma of the ovary: is there a role of histology-specific treatment? J Exp Clin Cancer Res 31:53. https://doi.org/10.1186/1756-9966-31-53\nChung YS, Park SY, Lee JY et al (2019) Outcomes of non-high grade serous carcinoma after neoadjuvant chemotherapy for advanced-stage ovarian cancer: a Korean gynecologic oncology group study (OV 1708). BMC Cancer 19:341. https://doi.org/10.1186/s12885-019-5514-7\nNational Comprehensive Cancer Network. NCCN clinical practice guidelines in oncology. ovarian cancer including fallopian tube cancer and primary peritoneal cancer. (Version 1.2023) [cited 2023 Febrary 8] Available from:https://www.nccn.org/professionals/physician_gls/pdf/ovarian.pdf\nColombo N, Sessa C, du Bois A et al (2019) ESMO-ESGO consensus conference recommendations on ovarian cancer: pathology and molecular biology, early and advanced stages, borderline tumours and recurrent disease†. Ann Oncol 30:672–705. https://doi.org/10.1093/annonc/mdz062\nOkamoto A, Glasspool RM, Mabuchi S et al (2014) Gynecologic cancer interGroup (GCIG) consensus review for clear cell carcinoma of the ovary. Int J Gynecol Cancer 24:S20-25. https://doi.org/10.1097/igc.0000000000000289\nHoang LN, Zachara S, Soma A et al (2015) Diagnosis of ovarian carcinoma histotype based on limited sampling: a prospective study comparing cytology, frozen section, and core biopsies to full pathologic examination. Int J Gynecol Pathol 34:517–527. https://doi.org/10.1097/pgp.0000000000000199\nStewart CJ, Brennan BA, Hammond IG, Leung YC, McCartney AJ, Ruba S (2008) Intraoperative assessment of clear cell carcinoma of the ovary. Int J Gynecol Pathol 27:475–482. https://doi.org/10.1097/PGP.0b013e31816b5cff\nMayerhoefer ME, Materka A, Langs G et al (2020) Introduction to radiomics. J Nucl Med 61:488–495. https://doi.org/10.2967/jnumed.118.222893\nGuiot J, Vaidyanathan A, Deprez L et al (2022) A review in radiomics: making personalized medicine a reality via routine imaging. Med Res Rev 42:426–440. https://doi.org/10.1002/med.21846\nKang SK, Reinhold C, Atri M et al (2018) ACR appropriateness criteria(®) staging and follow-up of ovarian cancer. J Am Coll Radiol 15:S198-s207. https://doi.org/10.1016/j.jacr.2018.03.015\nZhu H, Ai Y, Zhang J et al (2021) Preoperative nomogram for differentiation of histological subtypes in ovarian cancer based on computer tomography radiomics. Front Oncol 11:642892. https://doi.org/10.3389/fonc.2021.642892\nHu Y, Weng Q, Xia H et al (2021) A radiomic nomogram based on arterial phase of CT for differential diagnosis of ovarian cancer. Abdom Radiol 46:2384–2392. https://doi.org/10.1007/s00261-021-03120-w\nWang M, Perucho JAU, Hu Y et al (2022) Computed tomographic radiomics in differentiating histologic subtypes of epithelial ovarian carcinoma. JAMA Netw Open 5:e2245141. https://doi.org/10.1001/jamanetworkopen.2022.45141\nAn H, Wang Y, Wong EMF et al (2021) CT texture analysis in histological classification of epithelial ovarian carcinoma. Eur Radiol 31:5050–5058. https://doi.org/10.1007/s00330-020-07565-3\nDong S, Yu F, Liu Y et al (2022) Comparison of the clinical characteristics and prognosis between clear cell carcinomas and high-grade serous ovarian carcinomas. Ginekol Pol. https://doi.org/10.5603/GP.a2022.012310.5603/GP.a2022.0123\nPark H, Qin L, Guerra P, Bay CP, Shinagare AB (2021) Decoding incidental ovarian lesions: use of texture analysis and machine learning for characterization and detection of malignancy. Abdom Radiol 46:2376–2383. https://doi.org/10.1007/s00261-020-02668-3\nYi X, Liu Y, Zhou B et al (2021) Incorporating SULF1 polymorphisms in a pretreatment CT-based radiomic model for predicting platinum resistance in ovarian cancer treatment. Biomed Pharmacother 133:111013. https://doi.org/10.1016/j.biopha.2020.111013\nBoehm KM, Aherne EA, Ellenson L et al (2022) Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer. Nat Cancer 3:723–733. https://doi.org/10.1038/s43018-022-00388-9\nDepeursinge A, Foncubierta-Rodriguez A, Van De Ville D, Müller H (2014) Three-dimensional solid texture analysis in biomedical imaging: review and opportunities. Med Image Anal 18:176–196. https://doi.org/10.1016/j.media.2013.10.005\nXue C, Yuan J, Lo GG et al (2021) Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review. Quant Imaging Med Surg 11:4431–4460. https://doi.org/10.21037/qims-21-86\nLi X, Ye Z (2015) Clear cell carcinoma of the ovary: multi-slice computed tomography findings. World J Surg Oncol 13:133. https://doi.org/10.1186/s12957-015-0546-1\nLi M, Tan J, Zhang Y et al (2021) Assessing CT imaging features combined with CEA and CA125 levels to identify endometriosis-associated ovarian cancer. Abdom Radiol 46:2367–2375. https://doi.org/10.1007/s00261-020-02571-x\nLiu H, Xu Y, Ji J, Dong R, Qiu H, Dai X (2020) Prognosis of ovarian clear cell cancer compared with other epithelial cancer types: a population-based analysis. Oncol Lett 19:1947–1957. https://doi.org/10.3892/ol.2020.11252\nPaik ES, Kim TJ, Choi CH, Kim BG, Bae DS, Lee JW (2018) Clinical outcomes of patients with clear cell and endometrioid ovarian cancer arising from endometriosis. J Gynecol Oncol 29:e18. https://doi.org/10.3802/jgo.2018.29.e18\nMarks EI, Brown VS, Dizon DS (2020) Genomic and molecular abnormalities in gynecologic clear cell carcinoma. Am J Clin Oncol 43:139–145. https://doi.org/10.1097/coc.0000000000000641\nPozzati F, Moro F, Pasciuto T et al (2018) Imaging in gynecological disease (14): clinical and ultrasound characteristics of ovarian clear cell carcinoma. Ultrasound Obstet Gynecol 52:792–800. https://doi.org/10.1002/uog.19171\nJian J, Li Y, Pickhardt PJ et al (2021) MR image-based radiomics to differentiate type Ι and type ΙΙ epithelial ovarian cancers. Eur Radiol 31:403–410. https://doi.org/10.1007/s00330-020-07091-2\nQian L, Ren J, Liu A et al (2020) MR imaging of epithelial ovarian cancer: a combined model to predict histologic subtypes. Eur Radiol 30:5815–5825. https://doi.org/10.1007/s00330-020-06993-5\nLambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762. https://doi.org/10.1038/nrclinonc.2017.141\nWang R, Cai Y, Lee IK et al (2021) Evaluation of a convolutional neural network for ovarian tumor differentiation based on magnetic resonance imaging. Eur Radiol 31:4960–4971. https://doi.org/10.1007/s00330-020-07266-x\nZhang K, Liu X, Shen J et al (2020) Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell 181:1423-1433.e1411. https://doi.org/10.1016/j.cell.2020.04.045\nWang X, Sun Z, Xue H et al (2022) A deep learning algorithm to improve readers’ interpretation and speed of pancreatic cystic lesions on dual-phase enhanced CT. Abdom Radiol 47:2135–2147. https://doi.org/10.1007/s00261-022-03479-4\nTanaka YO, Okada S, Satoh T et al (2016) Differentiation of epithelial ovarian cancer subtypes by use of imaging and clinical data: a detailed analysis. Cancer Imaging 16:3. https://doi.org/10.1186/s40644-016-0061-9\nCollins GS, Reitsma JB, Altman DG, Moons KG (2015) Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ 350:g7594. https://doi.org/10.1136/bmj.g7594\nAcknowledgements\nThis work was supported by grants from Natural Science Foundation of China (grant No. 81901829), National High Level Hospital Clinical Research Funding (grant No. 2022-PUMCH-A-004) and Natural Science Foundation of China (grant No. 82271886)\nFunding\nThis work was supported by grants from Natural Science Foundation of China (grant No. 81901829), National High Level Hospital Clinical Research Funding (grant No. 2022-PUMCH-A-004) and Natural Science Foundation of China (grant No. 82271886).\nAuthor information\nAuthors and Affiliations\nContributions\nAll authors contributed to the study conception and design. YLH, ZYJ, and HDX contributed to the conception and design of the study. XYL, JZ and CW contributed to the acquisition of clinical data. JR, LM and XLL contributed to data analysis and interpretation. JR and LM contributed to statistical analyses. JR, YL, and YLH participated in manuscript preparation, edition and revision. All authors have read and approved the final manuscript.\nCorresponding authors\nEthics declarations\nConflict of interest\nCo-authors Li Mao and Xiu-Li Li are employees of AI Lab, Deepwise Healthcare, China. The other authors have no conflicts of interest to disclose. The authors not employed by AI Lab, Deepwise Healthcare were in control of this study.\nEthical approval\nThis retrospective study was approved by the Institutional Review Board of the Peking Union Medical College Hospital (I-22PJ945), and the consents from patients were waived.\nAdditional information\nPublisher's Note\nSpringer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.\nRights and permissions\nSpringer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.\nAbout this article\nCite this article\nRen, J., Mao, L., Zhao, J. et al. Seeing beyond the tumor: computed tomography image-based radiomic analysis helps identify ovarian clear cell carcinoma subtype in epithelial ovarian cancer. Radiol med 128, 900–911 (2023). https://doi.org/10.1007/s11547-023-01666-x\nReceived:\nAccepted:\nPublished:\nVersion of record:\nIssue date:\nDOI: https://doi.org/10.1007/s11547-023-01666-x","source_license":"CC0","license_restricted":false}