Challenges for machine learning in clinical translation of big data imaging studies

TL;DR

This paper discusses the main challenges hindering the clinical translation of deep learning methods applied to large-scale neuroimaging data, emphasizing data, interpretability, evaluation, and logistical issues.

Contribution

It provides a comprehensive overview of current barriers and explores potential approaches to overcome them for effective clinical application of big data deep learning.

Findings

Identifies key barriers to clinical translation.

Highlights the importance of interpretability and evaluation.

Discusses logistical challenges in data sharing and processing.

Abstract

The combination of deep learning image analysis methods and large-scale imaging datasets offers many opportunities to imaging neuroscience and epidemiology. However, despite the success of deep learning when applied to many neuroimaging tasks, there remain barriers to the clinical translation of large-scale datasets and processing tools. Here, we explore the main challenges and the approaches that have been explored to overcome them. We focus on issues relating to data availability, interpretability, evaluation and logistical challenges, and discuss the challenges we believe are still to be overcome to enable the full success of big data deep learning approaches to be experienced outside of the research field.