🛰️ Daily AI Frontier
‹ back to 2026-07-21

Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation

Research Medical/Healthcare AI

Merged summary

TL;DR - MSSA is a training-free test-time adaptation framework for VLM-based medical image segmentation that uses reliable predictions stored in online memory instead of updating model parameters. It improves robustness under distribution shifts while preserving pretrained features.

  • Filters noisy image-text predictions to build a stable online memory of semantic priors.
  • Aligns target images with structurally relevant memory samples and their predictions.
  • Avoids instability and feature degradation associated with update-based adaptation.
  • Reports gains of up to 12.2% DSC and 11.7% mIoU across medical segmentation benchmarks.

Sources (1)

Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation

arXiv cs.CV Lingrui Li, Nan Pu, Dong Zhao, Wenjing Li, Andrew P French, Zhun Zhong, Xin Chen 2026-07-20 arXiv:2607.17693

TL;DR - MSSA is a training-free test-time adaptation framework for VLM-based medical image segmentation that uses reliable predictions stored in online memory instead of updating model parameters. It improves robustness under distribution shifts while preserving pretrained features.

  • Filters noisy image-text predictions to build a stable online memory of semantic priors.
  • Aligns target images with structurally relevant memory samples and their predictions.
  • Avoids instability and feature degradation associated with update-based adaptation.
  • Reports gains of up to 12.2% DSC and 11.7% mIoU across medical segmentation benchmarks.
item →