OneSeg: Self-learning and One-shot Learning based Single-slice Annotation for 3D Medical Image Segmentation

TL;DR

This paper introduces OneSeg, a framework that reduces annotation effort in 3D medical image segmentation by using self-learning and one-shot annotation of a single slice, achieving high accuracy with minimal labeled data.

Contribution

The paper presents a novel self-learning and one-shot learning framework that significantly decreases annotation effort for 3D medical images while maintaining competitive segmentation performance.

Findings

Achieves comparable accuracy with less than 1% annotated data

Effectively propagates annotations using a reconstruction network

Generalizes well on out-of-distribution datasets

Abstract

As deep learning methods continue to improve medical image segmentation performance, data annotation is still a big bottleneck due to the labor-intensive and time-consuming burden on medical experts, especially for 3D images. To significantly reduce annotation efforts while attaining competitive segmentation accuracy, we propose a self-learning and one-shot learning based framework for 3D medical image segmentation by annotating only one slice of each 3D image. Our approach takes two steps: (1) self-learning of a reconstruction network to learn semantic correspondence among 2D slices within 3D images, and (2) representative selection of single slices for one-shot manual annotation and propagating the annotated data with the well-trained reconstruction network. Extensive experiments verify that our new framework achieves comparable performance with less than 1% annotated data compared with fully supervised methods and generalizes well on several out-of-distribution testing sets.