Frequency-Aware Ensemble Learning for BraTS 2025 Pediatric Brain Tumor Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Yuxiao, Zhuang, Qingyao, Xu, Zhi-Qin John, Wang, Xiaowen, Ren, Yan, Qiu, Tianming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915543121920000
author Yi, Yuxiao
Zhuang, Qingyao
Xu, Zhi-Qin John
Wang, Xiaowen
Ren, Yan
Qiu, Tianming
author_facet Yi, Yuxiao
Zhuang, Qingyao
Xu, Zhi-Qin John
Wang, Xiaowen
Ren, Yan
Qiu, Tianming
contents Pediatric brain tumor segmentation presents unique challenges due to the rarity and heterogeneity of these malignancies, yet remains critical for clinical diagnosis and treatment planning. We propose an ensemble approach integrating nnU-Net, Swin UNETR, and HFF-Net for the BraTS-PED 2025 challenge. Our method incorporates three key extensions: adjustable initialization scales for optimal nnU-Net complexity control, transfer learning from BraTS 2021 pre-trained models to enhance Swin UNETR's generalization on pediatric dataset, and frequency domain decomposition for HFF-Net to separate low-frequency tissue contours from high-frequency texture details. Our final ensemble framework combines nnU-Net ($γ=0.7$), fine-tuned Swin UNETR, and HFF-Net, achieving Dice scores of 62.7% (CC), 83.2% (ED), 72.9% (ET), 85.7% (NET), 91.8% (TC), and 92.6% (WT) on the unseen test dataset, respectively. Our proposed method achieves first place (rank 1st) in the BraTS 2025 Pediatric Brain Tumor Segmentation Challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19353
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Frequency-Aware Ensemble Learning for BraTS 2025 Pediatric Brain Tumor Segmentation
Yi, Yuxiao
Zhuang, Qingyao
Xu, Zhi-Qin John
Wang, Xiaowen
Ren, Yan
Qiu, Tianming
Image and Video Processing
Computer Vision and Pattern Recognition
Pediatric brain tumor segmentation presents unique challenges due to the rarity and heterogeneity of these malignancies, yet remains critical for clinical diagnosis and treatment planning. We propose an ensemble approach integrating nnU-Net, Swin UNETR, and HFF-Net for the BraTS-PED 2025 challenge. Our method incorporates three key extensions: adjustable initialization scales for optimal nnU-Net complexity control, transfer learning from BraTS 2021 pre-trained models to enhance Swin UNETR's generalization on pediatric dataset, and frequency domain decomposition for HFF-Net to separate low-frequency tissue contours from high-frequency texture details. Our final ensemble framework combines nnU-Net ($γ=0.7$), fine-tuned Swin UNETR, and HFF-Net, achieving Dice scores of 62.7% (CC), 83.2% (ED), 72.9% (ET), 85.7% (NET), 91.8% (TC), and 92.6% (WT) on the unseen test dataset, respectively. Our proposed method achieves first place (rank 1st) in the BraTS 2025 Pediatric Brain Tumor Segmentation Challenge.
title Frequency-Aware Ensemble Learning for BraTS 2025 Pediatric Brain Tumor Segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.19353