Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptation

About

Test-time adaptation (TTA) refers to adapting a trained model to a new domain during testing. Existing TTA techniques rely on having multiple test images from the same domain, yet this may be impractical in real-world applications such as medical imaging, where data acquisition is expensive and imaging conditions vary frequently. Here, we approach such a task, of adapting a medical image segmentation model with only a single unlabeled test image. Most TTA approaches, which directly minimize the entropy of predictions, fail to improve performance significantly in this setting, in which we also observe the choice of batch normalization (BN) layer statistics to be a highly important yet unstable factor due to only having a single test domain example. To overcome this, we propose to instead integrate over predictions made with various estimates of target domain statistics between the training and test statistics, weighted based on their entropy statistics. Our method, validated on 24 source/target domain splits across 3 medical image datasets surpasses the leading method by 2.9% Dice coefficient on average.

Haoyu Dong, Nicholas Konz, Hanxue Gu, Maciej A. Mazurowski• 2024

Related benchmarks

TaskDatasetResultRank
Tumor SegmentationISPY1 Dataset (test)
DSC66.06
14
Tumor SegmentationTCGA-BRCA (target)
DSC0.6228
13
Cardiac Image SegmentationM&MS Domain D 1.0 (test)
ASSD (LV)3.27
11
Prostate MRI SegmentationProstate MRI Dataset Domain D
Dice Coefficient83.24
11
Cardiac Image SegmentationM&MS Domain D (target)
LV Dice84.05
11
Cardiac Image SegmentationM&MS Domain B 1.0 (test)
ASSD (LV)4.1
11
Cardiac Image SegmentationM&MS Domain C 1.0 (test)
ASSD (LV)4.69
11
Cardiac Image SegmentationM&MS Average 1.0 (test)
ASSD4.39
11
Prostate MRI SegmentationProstate MRI Dataset (Domain F)
Dice Coefficient0.7334
11
Cardiac Image SegmentationM&MS Domain B (target)
LV Dice81.34
11
Showing 10 of 14 rows

Other info

Follow for update