Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual Annotation

TL;DR

This paper presents a self-learning deep neural network approach for detecting and segmenting lung cysts in CT images without requiring manual annotations, improving accuracy through iterative self-supervision.

Contribution

It introduces a novel very weakly supervised method that leverages self-learning to enhance cyst segmentation without any manual labels.

Findings

Deep learning outperforms initial unsupervised segmentation.

Self-learning progressively improves segmentation accuracy.

Method reduces need for manual annotation in medical imaging.

Abstract

Image segmentation is a fundamental problem in medical image analysis. In recent years, deep neural networks achieve impressive performances on many medical image segmentation tasks by supervised learning on large manually annotated data. However, expert annotations on big medical datasets are tedious, expensive or sometimes unavailable. Weakly supervised learning could reduce the effort for annotation but still required certain amounts of expertise. Recently, deep learning shows a potential to produce more accurate predictions than the original erroneous labels. Inspired by this, we introduce a very weakly supervised learning method, for cystic lesion detection and segmentation in lung CT images, without any manual annotation. Our method works in a self-learning manner, where segmentation generated in previous steps (first by unsupervised segmentation then by neural networks) is used as ground truth for the next level of network learning. Experiments on a cystic lung lesion dataset show that the deep learning could perform better than the initial unsupervised annotation, and progressively improve itself after self-learning.