Single Image Test-Time Adaptation via Multi-View Co-Training

TL;DR

This paper introduces a novel single-image test-time adaptation method for volumetric medical imaging, enabling accurate tumor segmentation with only one test image, outperforming existing methods and closely matching supervised benchmarks.

Contribution

The proposed Patch-Based Multi-View Co-Training approach effectively leverages volumetric data and uncertainty-guided self-training for real-time domain adaptation in medical imaging.

Findings

Achieves near-supervised performance on breast MRI datasets.

Outperforms existing state-of-the-art test-time adaptation methods.

Provides an accessible codebase integrated with nnUNet.

Abstract

Test-time adaptation enables a trained model to adjust to a new domain during inference, making it particularly valuable in clinical settings where such on-the-fly adaptation is required. However, existing techniques depend on large target domain datasets, which are often impractical and unavailable in medical scenarios that demand per-patient, real-time inference. Moreover, current methods commonly focus on two-dimensional images, failing to leverage the volumetric richness of medical imaging data. Bridging this gap, we propose a Patch-Based Multi-View Co-Training method for Single Image Test-Time adaptation. Our method enforces feature and prediction consistency through uncertainty-guided self-training, enabling effective volumetric segmentation in the target domain with only a single test-time image. Validated on three publicly available breast magnetic resonance imaging datasets for tumor segmentation, our method achieves performance close to the upper bound supervised benchmark while also outperforming all existing state-of-the-art methods, on average by a Dice Similarity Coefficient of 3.75%. We publicly share our accessible codebase, readily integrable with the popular nnUNet framework, at https://github.com/smriti-joshi/muvi.git.