Contour Transformer Network for One-shot Segmentation of Anatomical Structures
This method addresses the bottleneck of requiring extensive expert-labeled data for medical image analysis, which is a significant problem for researchers and clinicians working with anatomical segmentation.
This paper introduces the Contour Transformer Network (CTN), a one-shot learning method for anatomical structure segmentation. It achieves competitive performance with state-of-the-art fully supervised methods using only one labeled image, and surpasses them with minimal human-in-the-loop editing.
Accurate segmentation of anatomical structures is vital for medical image analysis. The state-of-the-art accuracy is typically achieved by supervised learning methods, where gathering the requisite expert-labeled image annotations in a scalable manner remains a main obstacle. Therefore, annotation-efficient methods that permit to produce accurate anatomical structure segmentation are highly desirable. In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism. We formulate anatomy segmentation as a contour evolution process and model the evolution behavior by graph convolutional networks (GCNs). Training the 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. On segmentation tasks of four different anatomies, 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 methods. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved to surpass the fully supervised methods.