HD-TTA: Hypothesis-Driven Test-Time Adaptation for Safer Brain Tumor Segmentation

TL;DR

This paper introduces a hypothesis-driven test-time adaptation framework for brain tumor segmentation that enhances safety by intelligently selecting the most reliable prediction outcome, reducing errors in critical medical applications.

Contribution

It proposes a novel dynamic decision process for test-time adaptation that generates and selects between competing hypotheses to improve safety in medical image segmentation.

Findings

Improves safety metrics such as Hausdorff Distance and Precision.

Reduces segmentation errors in cross-domain brain tumor segmentation.

Maintains comparable Dice scores to baseline models.

Abstract

Standard Test-Time Adaptation (TTA) methods typically treat inference as a blind optimization task, applying generic objectives to all or filtered test samples. In safety-critical medical segmentation, this lack of selectivity often causes the tumor mask to spill into healthy brain tissue or degrades predictions that were already correct. We propose Hypothesis-Driven TTA, a novel framework that reformulates adaptation as a dynamic decision process. Rather than forcing a single optimization trajectory, our method generates intuitive competing geometric hypotheses: compaction (is the prediction noisy? trim artifacts) versus inflation (is the valid tumor under-segmented? safely inflate to recover). It then employs a representation-guided selector to autonomously identify the safest outcome based on intrinsic texture consistency. Additionally, a pre-screening Gatekeeper prevents negative transfer by skipping adaptation on confident cases. We validate this proof-of-concept on a cross-domain binary brain tumor segmentation task, applying a source model trained on adult BraTS gliomas to unseen pediatric and more challenging meningioma target domains. HD-TTA improves safety-oriented outcomes (Hausdorff Distance (HD95) and Precision) over several state-of-the-art representative baselines in the challenging safety regime, reducing the HD95 by approximately 6.4 mm and improving Precision by over 4%, while maintaining comparable Dice scores. These results demonstrate that resolving the safety-adaptation trade-off via explicit hypothesis selection is a viable, robust path for safe clinical model deployment. Code will be made publicly available upon acceptance.