Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification

TL;DR

This paper introduces the S4MI pipeline, leveraging self-supervised and semi-supervised learning to improve medical image segmentation and classification, reducing annotation needs and outperforming traditional supervised methods.

Contribution

The study presents a novel S4MI pipeline that effectively utilizes auxiliary tasks in self- and semi-supervised learning for medical imaging, with comprehensive benchmarking across multiple datasets.

Findings

Self-supervised learning outperforms supervised methods in classification.

Semi-supervised learning achieves better segmentation with 50% fewer labels.

Open-source code facilitates broader adoption and further research.

Abstract

Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from clinical specialists. Addressing this issue, we introduce the S4MI (Self-Supervision and Semi-Supervision for Medical Imaging) pipeline, a novel approach that leverages advancements in self-supervised and semi-supervised learning. These techniques engage in auxiliary tasks that do not require labeling, thus simplifying the scaling of machine supervision compared to fully-supervised methods. Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks. Notably, we observed that self supervised learning significantly surpassed the performance of supervised methods in the classification of all evaluated datasets. Remarkably, the semi-supervised approach demonstrated superior outcomes in segmentation, outperforming fully-supervised methods while using 50% fewer labels across all datasets. In line with our commitment to contributing to the scientific community, we have made the S4MI code openly accessible, allowing for broader application and further development of these methods.