Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

TL;DR

This survey reviews semi-supervised, multi-instance, and transfer learning methods in medical image analysis, highlighting their roles in addressing limited annotated data and exploring future research directions.

Contribution

It provides a comprehensive overview of alternative learning approaches in medical imaging, connecting different scenarios and identifying research opportunities.

Findings

Various semi-supervised methods improve annotation efficiency

Transfer learning enhances model performance with limited data

Multi-instance learning aids in complex diagnosis tasks

Abstract

Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods which can learn with less/other types of supervision, have been proposed. We review semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis/detection or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research.