Deep learning in biomedical optics

TL;DR

This review discusses how deep learning techniques are applied across various biomedical optical imaging modalities, highlighting recent advances, challenges, and future opportunities for clinical translation.

Contribution

It provides a comprehensive overview of deep learning applications in biomedical optics, organized by imaging domain, and discusses potential for enabling new medical imaging capabilities.

Findings

Deep learning enhances image quality and analysis in biomedical optics.

Challenges include data availability and translation to clinical practice.

Opportunities involve new imaging capabilities and improved diagnostics.

Abstract

This article reviews deep learning applications in biomedical optics with a particular emphasis on image formation. The review is organized by imaging domains within biomedical optics and includes microscopy, fluorescence lifetime imaging, in vivo microscopy, widefield endoscopy, optical coherence tomography, photoacoustic imaging, diffuse tomography, and functional optical brain imaging. For each of these domains, we summarize how deep learning has been applied and highlight methods by which deep learning can enable new capabilities for optics in medicine. Challenges and opportunities to improve translation and adoption of deep learning in biomedical optics are also summarized.