Related Experiment Video
Updated: Jun 16, 2025
Whole-body PET/MRI of Pediatric Patients: The Details That Matter
Published on: December 19, 2017
nnU-Net-based Segmentation of Tumor Subcompartments in Pediatric Medulloblastoma Using Multiparametric MRI: A
Rohan Bareja1, Marwa Ismail1, Douglas Martin1
1From the Department of Radiology, University of Wisconsin-Madison, Madison, Wis (R.B., M.I., I.Y.); University Hospitals, Cleveland, Ohio (D.M., A.N.); Departments of Biomedical Engineering (M.L., S.G., S.I.) and Neurosciences (P.D.), Case Western Reserve University, Cleveland, Ohio; Department of Radiology, Children's Hospital Los Angeles, Los Angeles, Calif (B.T.); Division of Hematology, Oncology & Bone Marrow Transplant, Nationwide Children's Hospital, Columbus, Ohio (R.S.); Department of Pediatrics, Keck School of Medicine of University of Southern California, Children's Hospital Los Angeles, Los Angeles, Calif (A.M.); Department of Pathology, Children's Hospital Los Angeles, Los Angeles, Calif (A.J.); Division of Oncology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio (P.d.B.); William S. Middleton Memorial Veterans Affairs (VA) Healthcare, Madison, Wis (P.T.); and Department of Radiology and Biomedical Engineering, University of Wisconsin-Madison, 750 Highland Ave, Madison, WI 53726 (P.T.).
None:
Purpose To evaluate nnU-Net-based segmentation models for automated delineation of medulloblastoma 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 to 18 years, with medulloblastomas, from three different sites (28 from hospital A, 18 from hospital B, and 32 from hospital C), who had data available from three clinical MRI protocols (gadolinium-enhanced T1-weighted, T2-weighted, and fluid-attenuated inversion recovery). 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 plus 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: (a) the transfer learning nnU-Net model was pretrained on an adult glioma cohort (n = 484) and fine-tuned on medulloblastoma studies using Models Genesis and (b) the direct deep learning nnU-Net model was trained directly on the medulloblastoma datasets, across fivefold cross-validation. Model robustness was evaluated on the three datasets when using different combinations of training and test sets, with data from two sites at a time used for training and data from the third site used for testing. Results Analysis on the three test sites yielded Dice scores of 0.81, 0.86, and 0.86 and 0.80, 0.86, and 0.85 for tumor habitat; 0.68, 0.84, and 0.77 and 0.67, 0.83, and 0.76 for enhancing tumor; 0.56, 0.71, and 0.69 and 0.56, 0.71, and 0.70 for edema; and 0.32, 0.48, and 0.43 and 0.29, 0.44, and 0.41 for cystic core plus nonenhancing tumor for the transfer learning and direct nnU-Net models, respectively. The models were largely robust to site-specific variations. Conclusion nnU-Net segmentation models hold promise for accurate, robust automated delineation of medulloblastoma tumor subcompartments, potentially leading to more effective radiation therapy planning in pediatric medulloblastoma. Keywords: Pediatrics, MR Imaging, Segmentation, Transfer Learning, Medulloblastoma, nnU-Net, MRI Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Rudie and Correia de Verdier in this issue.
