Segmentation-free pretherapeutic assessment of BRAF-status in pediatric low-grade gliomas

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 limitations to manual and automated tumor segmentations. This study assessed the performance of automated segmentation algorithms and a segmentation-free ML classification pipeline. Molecularly characterized tumors and whole-brain FLAIR MR images were collected from 455 patients with pLGG treated between 1999 and 2023 at a children’s hospital. Three medical segmentation models, TransBTS, MedNeXt, and MedicalNet, were evaluated. Next, we developed a model to identify BRAF status from whole-brain FLAIR MRI, without any reliance on 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 semiautomatic whole tumor volume segmentations as inputs. Here we show that the MedNeXt segmentation model (mean Dice score: 0.555) outperformed MedicalNet (0.516) and TransBTS (0.449) (p < 0.05 for all comparisons). The MedNeXt 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 semiautomatic whole tumor volume 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. Pediatric low-grade gliomas are the most common brain tumors in children. Many of these tumors carry mutations in a gene called BRAF. Treatment choices depend on knowing the type of mutation, termed “BRAF status.” Up until now, BRAF status could only be confirmed through brain surgery or predicted from brain scans using artificial intelligence after first outlining the tumor on the scan. Tumors can be outlined manually by radiologists or automatically by a computer model, but both methods are prone to inconsistencies. In this study, we show that BRAF status can be predicted directly from brain scans using artificial intelligence without outlining, making the method more reliable and practical. This approach could help children avoid brain surgery and may extend to other cancers and age groups. Kudus et al. develop a segmentation-free deep learning pipeline to predict BRAF status in pediatric low-grade gliomas from whole-brain MRI. The model performs comparably to segmentation-based approaches, improves with pretraining, and is most accurate for identifying BRAF Fusion.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.