Related Experiment Video
Updated: Aug 28, 2026
Live-3D-Cell Immunocytochemistry Assays of Pediatric Diffuse Midline Glioma
Published on: November 11, 2021
Improved Deep Learning Segmentation of Pediatric Diffuse Midline Gliomas After Treatment
John Zielke1, Francesca Romana Mussa1, Anna Zapaishchykova1
1From the Artificial Intelligence in Medicine (AIM) Program (J.K., F.R.M., A.Z., D.T., R. M.-Y., Z.Y., S.V., H.J.W.L.A., B.H.K.), Mass General Brigham, Radiation Oncology (J.K., F.R.M., A.Z., D.T., R.M.-Y., Z.Y., R.R., D.A.H.-K., H.J.W.L.A., T.Y.P., B.H.K.), Dana-Farber Cancer Institute and Brigham and Women's Hospital, Neurosurgery (O.A.), Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States; Radiology and Nuclear Medicine (J.K., F.R.M., A.Z., D.T., R.M.-Y., H.J.W.L.A.), CARIM & GROW, Maastricht University, Maastricht, the Netherlands; Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging (A.H.A., A.M.R.), Neurology, Neurosurgery and Pediatrics (S.M.), University of California San Francisco, San Francisco, California, USA; Department of Radiology (V.R., R.R., C.A., S.V., T.Y.P.), Boston Children's Hospital, Department of Radiology (A.G.S., A.H.), Brigham and Women's Hospital, Boston, MA, United States and Sheikh Zayed Institute for Pediatric Surgical Innovation (M.G.L.), Children's National Hospital, Departments of Pediatrics and Radiology (M.G.L.), George Washington University School of Medicine and Health Sciences, Washington, District of Columbia, USA.
Purpose:
To develop and validate a pediatric diffuse midline glioma (DMG) auto-segmentation tool optimized for longitudinal treatment response assessment across the disease course.
Materials And Methods:
In this multi-institutional retrospective study, we included patients aged 1-30 years with DMG from an institutional pediatric cancer center, BraTS-PEDs 2024, and PNOC007, a prospective trial of radiation followed by peptide vaccine plus poly-ICLC, and we trained nnU-Net-based DMGtracker using expert segmentations from 140 institutional pre- and post-treatment studies and all 261 BraTS-PEDs 2024 pre-treatment studies, using four-sequence multiparametric MRI (T1, T1 post-contrast, T2, and FLAIR). We externally validated the model on 88 annotated PNOC007 studies (n = 49 patients) and compared it with the BraTS-PEDs 2024 winning model using median Dice similarity coefficient (DSC) and relative volumetric difference (RVD) for whole-tumor and contrast-enhancing tumor segmentation using the Wilcoxon signed-rank test.
Results:
Training and internal testing used 153 scans (59 post-treatment) from 74 patients. Incorporating post-treatment data improved internal whole-tumor DSC for our trained model (0.94 [IQR 0.82-0.96] vs 0.93 [0.81-0.96]; p<0.001). On external validation, DMGtracker outperformed the BraTS-PEDs 2024 winning model for whole-tumor segmentation, with higher DSC (0.90 [0.72-0.95] vs 0.81 [0.66-0.90]) and lower RVD (9.6% [3.7%-31.6%] vs 16.8% [7.3%-39.2%]). This advantage was greatest in post-treatment scans (n = 50 scans, DSC 0.90 [0.73-0.94] vs 0.80 [0.58-0.88]; RVD 9.7% [3.8%-26.2%] vs 19.8% [12.6%-39.8%]; p<0.001 for both). In post-treatment scans, DMGtracker achieved clinically acceptable whole-tumor segmentation (DSC > 0.80) in 64.0% of cases, compared with 52.0% for the BraTS-PEDs winner.
Conclusion:
Training DMG segmentation models with post-treatment scans substantially improves performance in longitudinal clinical trial imaging, enabling more accurate volumetric tracking and response assessment.