Adaptive wavelet-VNet for single-sample test time adaptation in medical image segmentation.

Journal: Medical physics
PMID:

Abstract

BACKGROUND: In medical image segmentation, a domain gap often exists between training and testing datasets due to different scanners or imaging protocols, which leads to performance degradation in deep learning-based segmentation models. Given the high cost of manual labeling and the need for privacy protection, it is often challenging to annotate the testing (target) domain data for model fine-tuning or to collect data from different domains to train domain generalization models. Therefore, using only unlabeled target domain data for test-time adaptation (TTA) presents a more practical but challenging solution.

Authors

  • Xiaoxue Qian
    Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
  • Weiguo Lu
    Department of Radiation Oncology, The University of Texas Southwestern Medical Center, Dallas, TX, United States of America.
  • You Zhang
    Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, 75390, USA.