# VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation

Source: [VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4ba>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-24T05:00:13.022Z

Authors: Zhipeng Deng, Jiale Zhou, Wenhan Jiang, Haolin Wang, Xun Lin, Yafei Ou, Yefeng Zheng

Published: 2026-05-17T12:57:29.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-sequence MRI Segmentation on BraTS SSA Target 2021](<https://www.sota2.com/research/sota/multi-sequence-mri-segmentation-on-brats-ssa-target-2021.md>): Multi-sequence MRI segmentation; BraTS SSA Target 2021; Dice Coefficient: 80.31.

- [Multi-sequence MRI segmentation on BraTS PED Target Domain 2021](<https://www.sota2.com/research/sota/multi-sequence-mri-segmentation-on-brats-ped-target-domain-2021.md>): Multi-sequence MRI segmentation; BraTS PED Target Domain 2021; Dice: 42.03.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.17433>)

[PDF](<https://arxiv.org/pdf/2605.17433.pdf>)
