Segmentation-Free Pretherapeutic Assessment of BRAF-Status in Pediatric Low-Grade Gliomas

Background BRAF status is crucial for treating pediatric low-grade gliomas (pLGG) and can be assessed non-invasively from segmented tumor regions on MRI using machine learning (ML). However, there are inherent limitations to manual and automated tumor segmentations. Purpose To assess the performance of automated segmentation algorithms and to develop and assess a segmentation-free ML classification pipeline that identifies BRAF status from whole-brain FLAIR MRI sequences.

In this REB-approved retrospective study, molecularly-characterized tumors and whole-brain FLAIR MR images were collected from 455 patients with pLGG treated between 1999 and 2023 at a single tertiary care children’s hospital. We trained and evaluated three medical segmentation models, TransBTS, MedNeXt, and MedicalNet. Next, we developed a model to identify BRAF status from whole-brain FLAIR MRI, without any reliance on manual or automated segmentations. We then implemented a novel pretraining regimen that embedded segmentation knowledge into the whole-brain FLAIR MRI classification model. Finally, we trained and evaluated a baseline model that used manual segmentations as inputs. All ML models were trained and evaluated under a nested-cross validation scheme, and mean performance across all test folds was compared using the corresponding t-test.

The MedNeXt segmentation model (mean Dice score: 0.555) outperformed both the convolutional neural network (CNN) based MedicalNet (0.516) and the CNN-transformer hybrid TransBTS (0.449) (p <0.05 for all comparisons). The MedNeXt style classification model achieved a one-vs-rest area under the ROC curve of 0.741 using the whole brain FLAIR sequence as an input, without any segmentation knowledge. This was improved to 0.772 through pretraining on the segmentation task, which was not significantly different from the baseline manual segmentation-based model (0.756, p-value: 0.141).

BRAF status can be assessed non-invasively using ML models based on whole-brain FLAIR sequences. Dependence on inconsistent manual or automated segmentations can be reduced by integrating tumor region information into the model through pretraining. Competing Interest Statement The authors have declared no competing interest. Funding Statement This study was funded by the Canadian Institutes of Health Research (CIHR) (Funding Reference Number: 184015). Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Research Ethics Board of of The Hospital For Sick Children (Toronto, Canada) waived ethical approval for this work. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Data Availability The datasets generated and/or analyzed during the current study are available from the corresponding author on reasonable request pending the approval of the institution(s) and trial/study investigators who contributed to the dataset. List of Abbreviations - AUC - Area Under the Receiver Operating Characteristic Curve - BRAF Fusion - KIAA1549::BRAF fusion - BRAF Mutation - BRAF p.V600E mutation - CI - Confidence Interval - CNN - Convolutional Neural Network - CNS - Central Nervous System - DL - Deep Learning - FLAIR - Fluid-Attenuated Inversion Recovery - ML - Machine Learning - MRI - Magnetic Resonance Imaging - pLGG - Pediatric Low-Grade Glioma - TL - Transfer Learning