Continual Learning in Medical Imaging: A Survey and Practical Analysis

TL;DR

This paper surveys recent advances in continual learning within medical imaging, addressing challenges like catastrophic forgetting, and provides insights and future directions to enhance practical applications in the medical domain.

Contribution

It offers a comprehensive review, taxonomy, and critical analysis of continual learning methods applied to medical imaging tasks, highlighting challenges and future research directions.

Findings

Identified key challenges in applying continual learning to medical imaging.

Provided a taxonomy categorizing recent studies and methods.

Outlined open problems and promising future research directions.

Abstract

Deep Learning has shown great success in reshaping medical imaging, yet it faces numerous challenges hindering widespread application. Issues like catastrophic forgetting and distribution shifts in the continuously evolving data stream increase the gap between research and applications. Continual Learning offers promise in addressing these hurdles by enabling the sequential acquisition of new knowledge without forgetting previous learnings in neural networks. In this survey, we comprehensively review the recent literature on continual learning in the medical domain, highlight recent trends, and point out the practical issues. Specifically, we survey the continual learning studies on classification, segmentation, detection, and other tasks in the medical domain. Furthermore, we develop a taxonomy for the reviewed studies, identify the challenges, and provide insights to overcome them. We also critically discuss the current state of continual learning in medical imaging, including identifying open problems and outlining promising future directions. We hope this survey will provide researchers with a useful overview of the developments in the field and will further increase interest in the community. To keep up with the fast-paced advancements in this field, we plan to routinely update the repository with the latest relevant papers at https://github.com/BioMedIA-MBZUAI/awesome-cl-in-medical .