Application of classification algorithms to diuse reflectance spectroscopy measurements for ex vivo characterization of biological tissues
EstadísticasView Usage Statistics
Full recordShow full item record
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.
Entropy, 2020, 22(7), 736
37th Annual Congress of the Spanish Society of Biomedical Engineering (CASEIB), Santander, 2019
Diffuse reflectance spectroscopy
Biological tissue identification in real clinical scenarios is a relevant and unsolved medical problem, particularly in the operating room. Although it could be thought that healthy tissue identification is an immediate task, in practice there are several clinical situations that greatly impede this process. For instance, it could be challenging in open surgery in complex areas, such as the neck, where different structures are quite close together, with bleeding and other artifacts affecting visual inspection. Solving this issue requires, on one hand, a high contrast noninvasive technique and, on the other hand, powerful classification algorithms. Regarding the technique, optical diffuse reflectance spectroscopy has demonstrated such capabilities in the discrimination of tumoral and healthy biological tissues. The complex signals obtained, in the form of spectra, need to be adequately computed in order to extract relevant information for discrimination. As usual, accurate discrimination relies on massive measurements, some of which serve as training sets for the classification algorithms. In this work, diffuse reflectance spectroscopy is proposed, implemented, and tested as a potential technique for healthy tissue discrimination. A specific setup is built and spectral measurements on several ex vivo porcine tissues are obtained. The massive data obtained are then analyzed for classification purposes. First of all, considerations about normalization, detrending and noise are taken into account. Dimensionality reduction and tendencies extraction are also considered. Featured spectral characteristics, principal component or linear discrimination analysis are applied, as long as classification approaches based on k-nearest neighbors (k-NN), quadratic discrimination analysis (QDA) or Naïve Bayes (NB). Relevant parameters about classification accuracy are obtained and compared, including ANOVA tests. The results show promising values of specificity and sensitivity of the technique for some classification algorithms, even over 95%, which could be relevant for clinical applications in the operating room.