Test-Time Adaptation with Shape Moments for Image Segmentation

TL;DR

This paper introduces a test-time adaptation method for image segmentation that leverages shape priors and entropy minimization, enabling effective adaptation with minimal target data without additional training.

Contribution

It proposes a novel shape-guided entropy minimization approach for single-subject test-time adaptation in segmentation tasks, outperforming existing methods without requiring target domain training.

Findings

Outperforms existing test-time adaptation methods in MRI and cross-site prostate segmentation.

Surpasses state-of-the-art domain adaptation methods despite no additional target training.

Highlights the importance of shape priors in segmentation adaptation.

Abstract

Supervised learning is well-known to fail at generalization under distribution shifts. In typical clinical settings, the source data is inaccessible and the target distribution is represented with a handful of samples: adaptation can only happen at test time on a few or even a single subject(s). We investigate test-time single-subject adaptation for segmentation, and propose a Shape-guided Entropy Minimization objective for tackling this task. During inference for a single testing subject, our loss is minimized with respect to the batch normalization's scale and bias parameters. We show the potential of integrating various shape priors to guide adaptation to plausible solutions, and validate our method in two challenging scenarios: MRI-to-CT adaptation of cardiac segmentation and cross-site adaptation of prostate segmentation. Our approach exhibits substantially better performances than the existing test-time adaptation methods. Even more surprisingly, it fares better than state-of-the-art domain adaptation methods, although it forgoes training on additional target data during adaptation. Our results question the usefulness of training on target data in segmentation adaptation, and points to the substantial effect of shape priors on test-time inference. Our framework can be readily used for integrating various priors and for adapting any segmentation network, and our code is available.