Deep learning: step forward to high‐resolution in vivo shortwave infrared imaging

• Published in: Journal of biophotonics Vol. 14; no. 7; pp. e202100102 - n/a
• Main Authors: Baulin, Vladimir A., Usson, Yves, Le Guével, Xavier
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY‐VCH Verlag GmbH & Co. KGaA 01.07.2021; Wiley Subscription Services, Inc; Wiley
• Subjects: Acoustic imaging; Barriers; Bioengineering; Blood vessels; Computer Science; Deep learning; fluorescence; Image analysis; Image processing; Image resolution; Imaging; In vivo methods and tests; Infrared imaging; Infrared windows; Life Sciences; Machine Learning; microvessels; Morphology; Neural networks; Noise reduction; Redundancy; Short wave radiation; SWIR; Vascularization; deep learning; SWIR; fluorescence; microvessels
• ISSN: 1864-063X; 1864-0648
• DOI: 10.1002/jbio.202100102

Shortwave infrared window (SWIR: 1000–1700 nm) represents a major improvement compared to the NIR‐I region (700–900 nm) in terms of temporal and spatial resolutions in depths down to 4 mm. SWIR is a fast and cheap alternative to more precise methods such as X‐ray and opto‐acoustic imaging. Main obstacles in SWIR imaging are the noise and scattering from tissues and skin that reduce the precision of the method. We demonstrate that the combination of SWIR in vivo imaging in the NIR‐IIb region (1500–1700 nm) with advanced deep learning image analysis allows to overcome these obstacles and making a large step forward to high resolution imaging: it allows to precisely segment vessels from tissues and noise, provides morphological structure of the vessels network, with learned pseudo‐3D shape, their relative position, dynamic information of blood vascularization in depth in small animals and distinguish the vessels types: artieries and veins. For demonstration we use neural network IterNet that exploits structural redundancy of the blood vessels, which provides a useful analysis tool for raw SWIR images. Deep learning methods provide a fast approach to move non‐invasive infrared in vivo imaging to high resolution imaging techniques with full analyses of the vascular network.