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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiaolong, Xu, Zhi-Qin John, Ren, Yan, Qiu, Tianming, Wang, Xiaowen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909881711198208
author Li, Xiaolong
Xu, Zhi-Qin John
Ren, Yan
Qiu, Tianming
Wang, Xiaowen
author_facet Li, Xiaolong
Xu, Zhi-Qin John
Ren, Yan
Qiu, Tianming
Wang, Xiaowen
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2511_00449
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements
Li, Xiaolong
Xu, Zhi-Qin John
Ren, Yan
Qiu, Tianming
Wang, Xiaowen
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
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).
title Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2511.00449