Nn-Unet-based Segmentation of Tumor Subcompartments in Pediatric Medulloblastoma Using Multiparametric MRI: A Multi-institutional Study.

Abstract

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate nn-Unet-based segmentation models for automated delineation of medulloblastoma (MB) tumors on multi-institutional MRI scans. Materials and Methods This retrospective study included 78 pediatric patients (52 male, 26 female), with ages ranging from 2-18 years, with MB tumors from three different sites (28 from Hospital A, 18 from Hospital B, 32 from Hospital C), who had data from three clinical MRI protocols (gadolinium-enhanced T1-weighted, T2-weighted, FLAIR) available. The scans were retrospectively collected from the year 2000 until May 2019. Reference standard annotations of the tumor habitat, including enhancing tumor, edema, and cystic core + nonenhancing tumor subcompartments, were performed by two experienced neuroradiologists. Preprocessing included registration to age-appropriate atlases, skull stripping, bias correction, and intensity matching. The two models were trained as follows: (1) transfer learning nn-Unet model was pretrained on an adult glioma cohort (n = 484) and fine-tuned on MB studies using Models Genesis, and (2) direct deep learning nn-Unet model was trained directly on the MB datasets, across five-fold cross-validation. Model robustness was evaluated on the three datasets when using different combinations of training and test sets, with data from 2 sites at a time used for training and data from the third site used for testing. Results Analysis on the 3 test sites yielded Dice scores of 0.81, 0.86, 0.86 and 0.80, 0.86, 0.85 for tumor habitat; 0.68, 0.84, 0.77 and 0.67, 0.83, 0.76 for enhancing tumor; 0.56, 0.71, 0.69 and 0.56, 0.71, 0.70 for edema; and 0.32, 0.48, 0.43 and 0.29, 0.44, 0.41 for cystic core + nonenhancing tumor for the transfer learning-and direct-nn-Unet models, respectively. The models were largely robust to site-specific variations. Conclusion nn-Unet segmentation models hold promise for accurate, robust automated delineation of MB tumor subcompartments, potentially leading to more effective radiation therapy planning in pediatric MB. ©RSNA, 2024.