Robust estimation of skin physiological parameters from hyperspectral images using Bayesian neural networks

Teo Manojlović (Author), Tadej Tomanič (Author), Ivan Štajduhar (Author), Matija Milanič (Author)

Abstract

Significance: Machine learning models for the direct extraction of tissue parameters from hyperspectral images have been extensively researched recently, as they represent a faster alternative to the well-known iterative methods such as inverse Monte Carlo and inverse adding-doubling (IAD). Aim: We aim to develop a Bayesian neural network model for robust prediction of physiological parameters from hyperspectral images. Approach: We propose a two-component system for extracting physiological parameters from hyperspectral images. First, our system models the relationship between the measured spectra and the tissue parameters as a distribution rather than a point estimate and is thus able to generate multiple possible solutions. Second, the proposed tissue parameters are then refined using the neural network that approximates the biological tissue model. Results: The proposed model was tested on simulated and in vivo data. It outperformed current models with an overall mean absolute error of 0.0141 and can be used as a faster alternative to the IAD algorithm. Conclusions: Results suggest that Bayesian neural networks coupled with the approximation of a biological tissue model can be used to reliably and accurately extract tissue properties from hyperspectral images on the fly.

Keywords

medicinska fizika;hiperspektralno slikanje;nevronske mreže;medical physics;hyperspectral imaging;neural networks;

Data

Language:	English
Year of publishing:	2025
Typology:	1.01 - Original Scientific Article
Organization:	UL FMF - Faculty of Mathematics and Physics
UDC:	616-073
COBISS:	223069699
ISSN:	1083-3668
Views:	24
Downloads:	4
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	Slovenian
Secondary keywords:	medicinska fizika;hiperspektralno slikanje;nevronske mreže;
Type (COBISS):	Article
Pages:	str. 016004-1-016004-17
Volume:	ǂVol. ǂ30
Issue:	ǂiss. ǂ1
Chronology:	2025
DOI:	10.1117/1.JBO.30.1.016004
ID:	25739142