Optical biopsy of human skin for the detection of neurological diseases and other non-infectious diseases
Ivan A. Bratchenko1, Lyudmila A. Bratchenko1, Yulia A. Khristoforova2, Petr A. Lebedev3, Maria A. Skuratova4, Alexandr V. Zakharov3; 1Immanuel Kant Baltic Federal University; 2Samara university; 3Samara state medical university; 4Samara City Clinical Hospital No.1 named after N.I.Pirogov.
Abstract
In this study we demonstrate application of conventional Raman spectroscopy for the analysis of skin tissues to determine the presence of non-infectious diseases. In this study, the in vivo analysis of human skin was performed for more than 100 subjects with neurological disease, and more than 200 subjects were analyzed in vivo for the detection of chronic heart failure and chronic kidney failure. Analyzed groups separation based on deep learning was implemented using a one-dimensional convolutional neural network (CNN). Application of Raman spectroscopy to investigate the forearm skin has yielded the accuracy of 0.96, sensitivity of 0.94 and specificity of 0.99 in terms of identifying the target subjects with kidney failure. When classifying subjects by the presence of nuerological diseases the accuracy reached 99%. The performed study demonstrates that for in vivo skin analysis with the application of the conventional Raman spectroscopy can provide the basis for cost-effective and accurate detection of different diseases and associated metabolic changes in the skin.
Speaker
Ivan A. Bratchenko
Scientific and Educational Center "Fundamental and Applied Photonics. Nanophotonics" of Immanuel Kant Baltic Federal University
Russia
Discussion
Ask question
