Domain Adaptation for Medical Image Segmentation Using Transformation-Invariant Self-training

Ghamsarian, Negin; Gamazo Tejero, Javier; Márquez-Neila, Pablo; Wolf, Sebastian; Zinkernagel, Martin; Schoeffmann, Klaus; Sznitman, Raphael (2023). Domain Adaptation for Medical Image Segmentation Using Transformation-Invariant Self-training. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. Lecture Notes in Computer Science: Vol. 14220 (pp. 331-341). Springer 10.1007/978-3-031-43907-0_32

	Text MICCAI23_TI_ST_1780.pdf - Accepted Version Restricted to registered users only Available under License Publisher holds Copyright. Download (5MB)
	Text 978-3-031-43907-0_32.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (2MB)

Models capable of leveraging unlabelled data are crucial in overcoming large distribution gaps between the acquired datasets across different imaging devices and configurations. In this regard, self-training techniques based on pseudo-labeling have been shown to be highly effective for semi-supervised domain adaptation. However, the unreliability of pseudo labels can hinder the capability of self-training techniques to induce abstract representation from the unlabeled target dataset, especially in the case of large distribution gaps. Since the neural network performance should be invariant to image transformations, we look to this fact to identify uncertain pseudo labels. Indeed, we argue that transformation invariant detections can provide more reasonable approximations of ground truth. Accordingly, we propose a semi-supervised learning strategy for domain adaptation termed transformation-invariant self-training (TI-ST). The proposed method assesses pixel-wise pseudo-labels’ reliability and filters out unreliable detections during self-training. We perform comprehensive evaluations for domain adaptation using three different modalities of medical images, two different network architectures, and several alternative state-of-the-art domain adaptation methods. Experimental results confirm the superiority of our proposed method in mitigating the lack of target domain annotation and boosting segmentation performance in the target domain.

Interest & Impact

Downloads

2 since deposited on 17 Nov 2023
2 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item