Physical foundations for trustworthy medical imaging: A survey for artificial intelligence researchers.
Authors
Affiliations (4)
Affiliations (4)
- AI Technology for Life, Department of Information and Computing Sciences, Department of Biology, Utrecht University, Utrecht, Netherlands; Advanced Computing and e-Science Group, Institute of Physics of Cantabria (IFCA), CSIC - UC, Santander, Spain; Department of Radiology, The Netherlands Cancer Institute, Amsterdam, Netherlands. Electronic address: [email protected].
- Department of Radiology, León University Health Care Complex, León, Spain; Department of Morphology and Cell Biology and Group of Peripheral Nervous System and Sensory Organs, University of Oviedo, Oviedo, Spain.
- AI Technology for Life, Department of Information and Computing Sciences, Department of Biology, Utrecht University, Utrecht, Netherlands; Department of Radiology, The Netherlands Cancer Institute, Amsterdam, Netherlands.
- Advanced Computing and e-Science Group, Institute of Physics of Cantabria (IFCA), CSIC - UC, Santander, Spain.
Abstract
Artificial intelligence in medical imaging has grown rapidly in the past decade, driven by advances in deep learning and widespread access to computing resources. Applications cover diverse imaging modalities, including those based on electromagnetic radiation (e.g., X-rays), subatomic particles (e.g., nuclear imaging), and acoustic waves (ultrasound). Each modality features and limitations are defined by its underlying physics. However, many artificial intelligence practitioners lack a solid understanding of the physical principles involved in medical image acquisition. This gap hinders leveraging the full potential of deep learning, as incorporating physics knowledge into artificial intelligence systems promotes trustworthiness, especially in limited data scenarios. This work reviews the fundamental physical concepts behind medical imaging and examines their influence on recent developments in artificial intelligence, particularly, generative models and reconstruction algorithms. Finally, we describe physics-informed machine learning approaches to improve feature learning in medical imaging.