Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice

TL;DR

This paper outlines key challenges and considerations for developing and deploying machine learning models in clinical radiology, emphasizing practical issues like data quality, model robustness, and clinical validation.

Contribution

It compiles and contextualizes existing techniques addressing challenges in medical imaging ML models, making them more accessible for stakeholders.

Findings

Identifies critical considerations for ML in radiology.

Provides techniques to address data and model challenges.

Highlights importance of clinical validation and fairness.

Abstract

The use of machine learning to develop intelligent software tools for interpretation of radiology images has gained widespread attention in recent years. The development, deployment, and eventual adoption of these models in clinical practice, however, remains fraught with challenges. In this paper, we propose a list of key considerations that machine learning researchers must recognize and address to make their models accurate, robust, and usable in practice. Namely, we discuss: insufficient training data, decentralized datasets, high cost of annotations, ambiguous ground truth, imbalance in class representation, asymmetric misclassification costs, relevant performance metrics, generalization of models to unseen datasets, model decay, adversarial attacks, explainability, fairness and bias, and clinical validation. We describe each consideration and identify techniques to address it. Although these techniques have been discussed in prior research literature, by freshly examining them in the context of medical imaging and compiling them in the form of a laundry list, we hope to make them more accessible to researchers, software developers, radiologists, and other stakeholders.