A1 Journal article (refereed)
Comparison of Machine Learning Methods in Stochastic Skin Optical Model Inversion (2020)

Annala, L., Äyrämö, S., & Pölönen, I. (2020). Comparison of Machine Learning Methods in Stochastic Skin Optical Model Inversion. Applied Sciences, 10(20), Article 7097. https://doi.org/10.3390/app10207097

JYU authors or editors

Publication details

All authors or editors: Annala, Leevi; Äyrämö, Sami; Pölönen, Ilkka

Journal or series: Applied Sciences

eISSN: 2076-3417

Publication year: 2020

Publication date: 13/10/2020

Volume: 10

Issue number: 20

Article number: 7097

Publisher: MDPI AG

Publication country: Switzerland

Publication language: English

DOI: https://doi.org/10.3390/app10207097

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/72408


In this study, we compare six different machine learning methods in the inversion of a stochastic model for light propagation in layered media, and use the inverse models to estimate four parameters of the skin from the simulated data: melanin concentration, hemoglobin volume fraction, and thicknesses of epidermis and dermis. The aim of this study is to determine the best methods for stochastic model inversion in order to improve current methods in skin related cancer diagnostics and in the future develop a non-invasive way to measure the physical parameters of the skin based partially on the results of the study. Of the compared methods, which are convolutional neural network, multi-layer perceptron, lasso, stochastic gradient descent, and linear support vector machine regressors, we find the convolutional neural network to be the most accurate in the inversion task.

Keywords: spectral imaging; imaging; machine learning; neural networks (information technology); skin cancer; diagnostics

Free keywords: skin; physical parameter retrieval; convolutional neural network; model inversion

Contributing organizations

Related projects

Ministry reporting: Yes

Reporting Year: 2020

JUFO rating: 1

Last updated on 2022-17-06 at 11:57