Learning to Segment Anatomical Structures Accurately from One Exemplar
This addresses the bottleneck of scalable expert-labeled annotations in medical image analysis, offering a practical solution for clinicians to support personalized diagnosis with minimal labeling effort.
The paper tackles the problem of segmenting anatomical structures in medical images with limited labeled data by proposing a Contour Transformer Network that requires only one labeled exemplar and leverages unlabeled data, achieving competitive performance with state-of-the-art fully supervised methods and further improving with human-in-the-loop feedback.
Accurate segmentation of critical anatomical structures is at the core of medical image analysis. The main bottleneck lies in gathering the requisite expert-labeled image annotations in a scalable manner. Methods that permit to produce accurate anatomical structure segmentation without using a large amount of fully annotated training images are highly desirable. In this work, we propose a novel contribution of Contour Transformer Network (CTN), a one-shot anatomy segmentor including a naturally built-in human-in-the-loop mechanism. Segmentation is formulated by learning a contour evolution behavior process based on graph convolutional networks (GCNs). Training of our CTN model requires only one labeled image exemplar and leverages additional unlabeled data through newly introduced loss functions that measure the global shape and appearance consistency of contours. We demonstrate that our one-shot learning method significantly outperforms non-learning-based methods and performs competitively to the state-of-the-art fully supervised deep learning approaches. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved and tailored towards the observer desired outcomes. This can facilitate the clinician designed imaging-based biomarker assessments (to support personalized quantitative clinical diagnosis) and outperforms fully supervised baselines.