mlsanityData to 7 Oct 2026

Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements

arXiv 2511.00449 ↗First posted 1 Nov 2025eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate segmentation of pediatric brain tumors in multi-parametric magnetic resonance imaging (mpMRI) is critical for diagnosis, treatment planning, and monitoring, yet faces unique challenges due to limited data, high anatomical variability, and heterogeneous imaging across institutions. In this work, we present an advanced nnU-Net framework tailored for BraTS 2025 Task-6 (PED), the largest public dataset of pre-treatment pediatric high-grade gliomas. Our contributions include: (1) a widened residual encoder with squeeze-and-excitation (SE) attention; (2) 3D depthwise separable convolutions; (3) a specificity-driven regularization term; and (4) small-scale Gaussian weight initialization. We further refine predictions with two postprocessing steps. Our models achieved first place on the Task-6 validation leaderboard, attaining lesion-wise Dice scores of 0.759 (CC), 0.967 (ED), 0.826 (ET), 0.910 (NET), 0.928 (TC) and 0.928 (WT).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 14 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

12 of 14 references.

References · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 360
  6. 2021MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluationcited by 88
  7. 2020Phase diagram for two-layer ReLU neural networks at infinite-width limitcited by 65
  8. 2023The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)cited by 49
  9. 2025Primus: Enforcing Attention Usage for 3D Medical Image Segmentationcited by 22
  10. 2023Loss Spike in Training Neural Networkscited by 15
  11. 2024The Brain Tumor Segmentation in Pediatrics (BraTS-PEDs) Challenge: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)cited by 13
  12. 2025Scalable Complexity Control Facilitates Reasoning Ability of LLMscited by 1

Built on by

Not cited yet.