Saved in:
Bibliographic Details
Main Authors: Kumar, Lokendra, Aggarwal, Shubham
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19844
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918410512760832
author Kumar, Lokendra
Aggarwal, Shubham
author_facet Kumar, Lokendra
Aggarwal, Shubham
contents We present the first study of Hyper-Connections (HC) for volumetric multi-modal brain tumor segmentation, integrating them as a drop-in replacement for fixed residual connections across five architectures: nnU-Net, SwinUNETR, VT-UNet, U-Net, and U-Netpp. Dynamic HC consistently improves all 3D models on the BraTS 2021 dataset, yielding up to +1.03 percent mean Dice gain with negligible parameter overhead. Gains are most pronounced in the Enhancing Tumor sub-region, reflecting improved fine-grained boundary delineation. Modality ablation further reveals that HC-equipped models develop sharper sensitivity toward clinically dominant sequences, specifically T1ce for Tumor Core and Enhancing Tumor, and FLAIR for Whole Tumor, a behavior absent in fixed-connection baselines and consistent across all architectures. In 2D settings, improvements are smaller and configuration-sensitive, suggesting that volumetric spatial context amplifies the benefit of adaptive aggregation. These results establish HC as a simple, efficient, and broadly applicable mechanism for multi-modal feature fusion in medical image segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19844
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hyper-Connections for Adaptive Multi-Modal MRI Brain Tumor Segmentation
Kumar, Lokendra
Aggarwal, Shubham
Computer Vision and Pattern Recognition
We present the first study of Hyper-Connections (HC) for volumetric multi-modal brain tumor segmentation, integrating them as a drop-in replacement for fixed residual connections across five architectures: nnU-Net, SwinUNETR, VT-UNet, U-Net, and U-Netpp. Dynamic HC consistently improves all 3D models on the BraTS 2021 dataset, yielding up to +1.03 percent mean Dice gain with negligible parameter overhead. Gains are most pronounced in the Enhancing Tumor sub-region, reflecting improved fine-grained boundary delineation. Modality ablation further reveals that HC-equipped models develop sharper sensitivity toward clinically dominant sequences, specifically T1ce for Tumor Core and Enhancing Tumor, and FLAIR for Whole Tumor, a behavior absent in fixed-connection baselines and consistent across all architectures. In 2D settings, improvements are smaller and configuration-sensitive, suggesting that volumetric spatial context amplifies the benefit of adaptive aggregation. These results establish HC as a simple, efficient, and broadly applicable mechanism for multi-modal feature fusion in medical image segmentation.
title Hyper-Connections for Adaptive Multi-Modal MRI Brain Tumor Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.19844