Saved in:
Bibliographic Details
Main Authors: Deng, Zhipeng, Zhou, Jiale, Jiang, Wenhan, Wang, Haolin, Lin, Xun, Ou, Yafei, Zheng, Yefeng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17433
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911691926667264
author Deng, Zhipeng
Zhou, Jiale
Jiang, Wenhan
Wang, Haolin
Lin, Xun
Ou, Yafei
Zheng, Yefeng
author_facet Deng, Zhipeng
Zhou, Jiale
Jiang, Wenhan
Wang, Haolin
Lin, Xun
Ou, Yafei
Zheng, Yefeng
contents Deploying multi-sequence magnetic resonance imaging (MRI) segmentation models to new clinical environments is challenging due to variations in scanners and acquisition protocols. Although existing TTA methods handle basic per-modality shifts, they often fail under a fundamental dual-shift problem, as their adaptation signals fail to capture modality-interaction shifts that disrupt inter-sequence consistency. To address this, we propose Variance-gated Inter-Sequence Test-time Adaptation (VISTA), a source-free framework that tackles modality-interaction shifts. First, we design an Inter-Sequence Intervention Generator (ISIG) that generates a set of consistency probes by swapping low-frequency spectra and entropy-localized patches across sequences, preserving anatomical semantics while challenging inter-sequence dependencies. Second, we introduce Cross-View Disagreement-Aware Pseudo Labeling (CDPL), which establishes a voxel-wise reliability metric using cross-view disagreement variance to dynamically gate self-training and enforce interventional consistency, encouraging the network to rely on robust anatomical semantics. Extensive experiments adapting from standard adult MRI (BraTS-GLI-Pre) to African low-field (BraTS-SSA) and pediatric (BraTS-PED) cohorts show improved performance over competing methods under clinical shifts, achieving absolute Dice improvements of +1.89% (SSA) and +2.82% (PED) over the source model. The code is available at https://github.com/dzp2095/VISTA.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17433
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation
Deng, Zhipeng
Zhou, Jiale
Jiang, Wenhan
Wang, Haolin
Lin, Xun
Ou, Yafei
Zheng, Yefeng
Computer Vision and Pattern Recognition
Deploying multi-sequence magnetic resonance imaging (MRI) segmentation models to new clinical environments is challenging due to variations in scanners and acquisition protocols. Although existing TTA methods handle basic per-modality shifts, they often fail under a fundamental dual-shift problem, as their adaptation signals fail to capture modality-interaction shifts that disrupt inter-sequence consistency. To address this, we propose Variance-gated Inter-Sequence Test-time Adaptation (VISTA), a source-free framework that tackles modality-interaction shifts. First, we design an Inter-Sequence Intervention Generator (ISIG) that generates a set of consistency probes by swapping low-frequency spectra and entropy-localized patches across sequences, preserving anatomical semantics while challenging inter-sequence dependencies. Second, we introduce Cross-View Disagreement-Aware Pseudo Labeling (CDPL), which establishes a voxel-wise reliability metric using cross-view disagreement variance to dynamically gate self-training and enforce interventional consistency, encouraging the network to rely on robust anatomical semantics. Extensive experiments adapting from standard adult MRI (BraTS-GLI-Pre) to African low-field (BraTS-SSA) and pediatric (BraTS-PED) cohorts show improved performance over competing methods under clinical shifts, achieving absolute Dice improvements of +1.89% (SSA) and +2.82% (PED) over the source model. The code is available at https://github.com/dzp2095/VISTA.
title VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.17433