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 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.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11737236 | PMC |
| http://dx.doi.org/10.1117/1.JBO.30.1.016004 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Mapping nutrient pollution in inland water bodies using multi-platform hyperspectral imagery and deep regression network.
J Hazard Mater
January 2025
Shanghai Municipal Institute of Surveying and Mapping, Shanghai, 200063, China.
Inland waters face multiple threats from human activities and natural factors, leading to frequent water quality issues, particularly the significant challenge of eutrophication. Hyperspectral remote sensing provides rich spectral information, enabling timely and accurate assessment of water quality status and trends. To address the challenge of inaccurate water quality mapping, we propose a novel deep learning framework for multi-parameter estimation from hyperspectral imagery.
View Article and Find Full Text PDFHigh-throughput precision assessment of pea-derived protein products using near infrared hyperspectral imaging.
Spectrochim Acta A Mol Biomol Spectrosc
January 2025
Department of Bioresource Engineering, McGill University, Macdonald Campus, 21111 Lakeshore Road, Ste-Anne-de-Bellevue, QC H9X 3V9, Canada.
This study aims to develop rapid and non-invasive methods based on near-infrared hyperspectral imaging and chemometrics for quantitative prediction of chemical compositions of pea-derived products. Hyperspectral imaging was used to acquire images from pea processing streams, namely pea flour, pea protein concentrate, and pea protein isolate. The PLS algorithm was used to develop quantitative prediction models based on the relationship between the hyperspectral image data and the chemical compositions of the pea products, including moisture, protein, ash, insoluble fiber, and total starch.
View Article and Find Full Text PDFOptical Based Methods for Water Monitoring in Biological Tissue.
J Biophotonics
January 2025
Center for Photonic Science and Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia.
Skin homeostasis is strongly dependent on its hydration levels, making skin water content measurement vital across various fields, including medicine, cosmetology, and sports science. Noninvasive diagnostic techniques are particularly relevant for clinical applications due to their minimal risk of side effects. A range of optical methods have been developed for this purpose, each with unique physical principles, advantages, and limitations.
View Article and Find Full Text PDFExploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing.
Sci Rep
January 2025
Fischell Department of Bioengineering, University of Maryland, College Park, USA.
The development of optical sensors for label-free quantification of cell parameters has numerous uses in the biomedical arena. However, using current optical probes requires the laborious collection of sufficiently large datasets that can be used to calibrate optical probe signals to true metabolite concentrations. Further, most practitioners find it difficult to confidently adapt black box chemometric models that are difficult to troubleshoot in high-stakes applications such as biopharmaceutical manufacturing.
View Article and Find Full Text PDFRobust estimation of skin physiological parameters from hyperspectral images using Bayesian neural networks.
J Biomed Opt
January 2025
University of Ljubljana, Faculty of Mathematics and Physics, Ljubljana, Slovenia.
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.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!