Gaze-Assisted Human-Centric Domain Adaptation for Cardiac Ultrasound Image Segmentation

TL;DR

This paper introduces GAHCDA, a novel method leveraging doctor gaze data to improve cardiac ultrasound image segmentation across domains, addressing limitations of previous methods by incorporating human guidance.

Contribution

It proposes a new gaze-assisted domain adaptation framework that uses human gaze information to enhance segmentation accuracy in cardiac ultrasound images.

Findings

Outperforms GAN-based and self-training methods in target domain segmentation.

Effectively incorporates human gaze data to guide domain adaptation.

Shows potential for clinical application in cardiac ultrasound analysis.

Abstract

Domain adaptation (DA) for cardiac ultrasound image segmentation is clinically significant and valuable. However, previous domain adaptation methods are prone to be affected by the incomplete pseudo-label and low-quality target to source images. Human-centric domain adaptation has great advantages of human cognitive guidance to help model adapt to target domain and reduce reliance on labels. Doctor gaze trajectories contains a large amount of cross-domain human guidance. To leverage gaze information and human cognition for guiding domain adaptation, we propose gaze-assisted human-centric domain adaptation (GAHCDA), which reliably guides the domain adaptation of cardiac ultrasound images. GAHCDA includes following modules: (1) Gaze Augment Alignment (GAA): GAA enables the model to obtain human cognition general features to recognize segmentation target in different domain of cardiac ultrasound images like humans. (2) Gaze Balance Loss (GBL): GBL fused gaze heatmap with outputs which makes the segmentation result structurally closer to the target domain. The experimental results illustrate that our proposed framework is able to segment cardiac ultrasound images more effectively in the target domain than GAN-based methods and other self-train based methods, showing great potential in clinical application.