Author, as appears in the article.: Baulin, Vladimir A.; Usson, Yves; Le Guevel, Xavier;

Department: Química Física i Inorgànica

URV's Author/s: Baulin, Vladimir

Keywords: Tissue Thermography (imaging) Temporal and spatial Swir Structural redundancy Shortwave infrared imaging Short wave infrared Relative positions Radiofrequency radiation Radio waves Neural networks, computer Morphological structures Microvessels Infrared rays Infrared radiation Infrared devices Images Image segmentation Image analysis Histology High-resolution imaging Fluorescence Dynamic information Deep learning Blood vessels Blood Animals Animal swir microvessels fluorescence

Abstract: 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.

Thematic Areas: Química Physics and astronomy (miscellaneous) Physics and astronomy (all) Optics Odontología Medicina veterinaria Medicina iii Medicina ii Medicina i Materials science (miscellaneous) Materials science (all) Materiais Interdisciplinar General physics and astronomy General materials science General engineering General chemistry General biochemistry,genetics and molecular biology Farmacia Engineering (miscellaneous) Engineering (all) Engenharias iv Engenharias ii Educação física Ciências biológicas iii Ciências biológicas ii Ciências biológicas i Chemistry (miscellaneous) Chemistry (all) Biotecnología Biophysics Biochemistry, genetics and molecular biology (miscellaneous) Biochemistry, genetics and molecular biology (all) Biochemical research methods Astronomia / física

licence for use: https://creativecommons.org/licenses/by/3.0/es/

Author's mail: vladimir.baulin@urv.cat

Author identifier: 0000-0003-2086-4271

Record's date: 2023-02-19

Journal volume: 14

Papper version: info:eu-repo/semantics/publishedVersion

Link to the original source: https://onlinelibrary.wiley.com/doi/10.1002/jbio.202100102

Licence document URL: http://repositori.urv.cat/ca/proteccio-de-dades/

Papper original source: Journal Of Biophotonics. 14 (e202100102):

APA: Baulin, Vladimir A.; Usson, Yves; Le Guevel, Xavier; (2021). Deep learning: step forward to high-resolution in vivo shortwave infrared imaging. Journal Of Biophotonics, 14(e202100102), -. DOI: 10.1002/jbio.202100102

Article's DOI: 10.1002/jbio.202100102

Entity: Universitat Rovira i Virgili

Journal publication year: 2021

Publication Type: Journal Publications