Physical foundations for trustworthy medical imaging: a review for artificial intelligence researchers

TL;DR

This review discusses how understanding the physics of medical imaging can improve the trustworthiness and robustness of AI algorithms, especially in data-limited scenarios, by integrating physics principles into AI models.

Contribution

It provides a comprehensive overview of the physical principles of medical imaging and explores how physics knowledge can be integrated into AI models for better performance.

Findings

Physics understanding enhances AI trustworthiness in medical imaging.

Physics-informed models improve robustness and feature learning.

Integration of physics constraints benefits generative and reconstruction algorithms.

Abstract

Artificial intelligence in medical imaging has seen unprecedented growth in the last years, due to rapid advances in deep learning and computing resources. Applications cover the full range of existing medical imaging modalities, with unique characteristics driven by the physics of each technique. Yet, artificial intelligence professionals entering the field, and even experienced developers, often lack a comprehensive understanding of the physical principles underlying medical image acquisition, which hinders their ability to fully leverage its potential. The integration of physics knowledge into artificial intelligence algorithms enhances their trustworthiness and robustness in medical imaging, especially in scenarios with limited data availability. In this work, we review the fundamentals of physics in medical images and their impact on the latest advances in artificial intelligence, particularly, in generative models and reconstruction algorithms. Finally, we explore the integration of physics knowledge into physics-inspired machine learning models, which leverage physics-based constraints to enhance the learning of medical imaging features.