注视辅助的以人为中心的心脏超声图像分割域自适应
Gaze-Assisted Human-Centric Domain Adaptation for Cardiac Ultrasound Image Segmentation
- College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（南京航空航天大学人工智能学院）
- School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
- School of Instrument Science and Engineering, Southeast University（东南大学仪器科学与工程学院）
- Department of Biomedical Engineering, Case Western Reserve University（凯斯西储大学生物医学工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出注视辅助的以人为中心的域自适应方法GAHCDA，利用医生注视轨迹中的跨域人类认知引导心脏超声图像分割，通过注视增强对齐和注视平衡损失提升目标域分割性能，优于GAN和自训练方法。
AI中文摘要：
心脏超声图像分割的域自适应（DA）具有重要的临床意义和价值。然而，以往的域自适应方法容易受到不完整伪标签和低质量目标到源图像的影响。以人为中心的域自适应具有人类认知引导的巨大优势，能够帮助模型适应目标域并减少对标签的依赖。医生的注视轨迹包含大量跨域的人类引导信息。为了利用注视信息和人类认知来引导域自适应，我们提出了注视辅助的以人为中心的域自适应（GAHCDA），该方法能够可靠地引导心脏超声图像的域自适应。GAHCDA包含以下模块：（1）注视增强对齐（GAA）：GAA使模型能够获得人类认知通用特征，从而像人类一样在不同域的心脏超声图像中识别分割目标。（2）注视平衡损失（GBL）：GBL将注视热图与输出融合，使分割结果在结构上更接近目标域。实验结果表明，与基于GAN的方法和其他基于自训练的方法相比，我们提出的框架能够在目标域中更有效地分割心脏超声图像，展现出巨大的临床应用潜力。
英文摘要：
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.
