Reproducibility of the Methods in Medical Imaging with Deep Learning

TL;DR

This study assesses the reproducibility of deep learning methods in medical imaging submissions to MIDL, highlighting the need for improved repository quality and proposing guidelines to enhance reproducibility in future research.

Contribution

The paper evaluates reproducibility practices in MIDL submissions and introduces tailored guidelines to improve repository quality and research reproducibility.

Findings

Only 22% of submissions had repeatable repositories.

Repository quality has not improved significantly over years.

Publishing repositories and using public datasets are increasingly common.

Abstract

Concerns about the reproducibility of deep learning research are more prominent than ever, with no clear solution in sight. The relevance of machine learning research can only be improved if we also employ empirical rigor that incorporates reproducibility guidelines, especially so in the medical imaging field. The Medical Imaging with Deep Learning (MIDL) conference has made advancements in this direction by advocating open access, and recently also recommending authors to make their code public - both aspects being adopted by the majority of the conference submissions. This helps the reproducibility of the methods, however, there is currently little or no support for further evaluation of these supplementary material, making them vulnerable to poor quality, which affects the impact of the entire submission. We have evaluated all accepted full paper submissions to MIDL between 2018 and 2022 using established, but slightly adjusted guidelines on reproducibility and the quality of the public repositories. The evaluations show that publishing repositories and using public datasets are becoming more popular, which helps traceability, but the quality of the repositories has not improved over the years, leaving room for improvement in every aspect of designing repositories. Merely 22% of all submissions contain a repository that were deemed repeatable using our evaluations. From the commonly encountered issues during the evaluations, we propose a set of guidelines for machine learning-related research for medical imaging applications, adjusted specifically for future submissions to MIDL.