Tissue optical properties combined with machine learning enables estimation of articular cartilage composition and functional integrity

Iman Kafian-Attari; Ervin Nippolainen; Dmitry Semenov; Markku Hauta-Kasari; Juha Töyräs; Isaac O Afara

doi:10.1364/BOE.402929

Tissue optical properties combined with machine learning enables estimation of articular cartilage composition and functional integrity

Biomed Opt Express. 2020 Oct 19;11(11):6480-6494. doi: 10.1364/BOE.402929. eCollection 2020 Nov 1.

Authors

Iman Kafian-Attari¹, Ervin Nippolainen¹, Dmitry Semenov², Markku Hauta-Kasari², Juha Töyräs^{1

3}, Isaac O Afara¹

Affiliations

¹ University of Eastern Finland, Department of Applied Physics, Yliopistonranta 1, Kuopio 70120, Finland.
² University of Eastern Finland, School of Computing, Lämsikatu 15, Joensuu 80110, Finland.
³ The University of Queensland, School of Information Technology, and Electrical Engineering, Brisbane, QLD 4067, Australia.

Abstract

Absorption and reduced scattering coefficients ( $μ_{a}, μ_{s}^{'}$ ) of biological tissues have shown significant potential in biomedical applications. Thus, they are effective parameters for the characterization of tissue integrity and provide vital information on the health of biological tissues. This study investigates the potential of optical properties ( $μ_{a}, μ_{s}^{'}$ ) for estimating articular cartilage composition and biomechanical properties using multivariate and machine learning techniques. The results suggest that μ_a could optimally estimate cartilage proteoglycan content in the superficial zone, in addition to its equilibrium modulus. While $μ_{s}^{'}$ could effectively estimate the proteoglycan content of the middle and deep zones in addition to the instantaneous and dynamic moduli of articular cartilage.