Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual Annotation
This work addresses the challenge of reducing expert annotation effort in medical image analysis, though it is incremental as it builds on existing weakly supervised and self-learning concepts.
The paper tackles the problem of detecting and segmenting cysts in lung CT images without manual annotation by introducing a self-learning method that uses unsupervised segmentation as initial ground truth and iteratively refines it with neural networks, achieving progressive improvement over the initial unsupervised annotation.
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.