Learning to Segment Anatomical Structures Accurately from One Exemplar

TL;DR

This paper introduces a one-shot segmentation method for anatomical structures using a Contour Transformer Network that learns from a single labeled image and unlabeled data, incorporating human feedback for improved accuracy.

Contribution

The novel Contour Transformer Network enables accurate anatomical segmentation from one exemplar, integrating a human-in-the-loop mechanism and shape-aware loss functions.

Findings

Outperforms non-learning-based methods

Competitive with state-of-the-art fully supervised models

Improves with minimal human feedback

Abstract

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.