Comparison of Machine Learning Methods in Stochastic Skin Optical Model Inversion

• Published in: Applied sciences Vol. 10; no. 20; p. 7097
• Main Authors: Annala, Leevi, Äyrämö, Sami, Pölönen, Ilkka
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 15.10.2020
• Subjects: Algorithms; Computer-aided medical diagnosis; convolutional neural network; Diagnosis; Discriminant analysis; Hemoglobin; Light; Machine learning; Melanoma; Methods; model inversion; Neural networks; Optical properties; physical parameter retrieval; Principal components analysis; Propagation; skin; Skin cancer; Stochastic models; Support vector machines; Finland
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app10207097

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.