Implementation of data fusion to increase the efficiency of classification of precancerous skin states using in vivo bimodal spectroscopic technique

Implementation of data fusion to increase the efficiency of classification of precancerous skin states using in vivo bimodal spectroscopic technique

This study presents the results of the classification of diffuse reflectance (DR) spectra and multiexcitation autofluorescence (AF) spectra that were collected in vivo from precancerous and benign skin lesions at three different source detector separation (SDS) values. Spectra processing pipeline co...

Full description

Bibliographic Details
Published in:Journal of biophotonics Vol. 16, № 7. P. e202300035 (1-14)
Other Authors: Kupriyanov, Valentin, Blondel, Walter, Daul, Christian, Amouroux, Marine, Kistenev, Yury V.
Format: Article
Language:English
Subjects:
автофлуоресценция
диффузное отражение
машинное обучение
рак кожи
статьи в журналах
Online Access:http://vital.lib.tsu.ru/vital/access/manager/Repository/koha:001017034
LEADER 02330nab a2200349 c 4500
001 koha001017034
005 20240112180137.0
007 cr |
008 240111|2023 gw s a eng d
024 7 |a 10.1002/jbio.202300035  |2 doi 
035 |a koha001017034 
040 |a RU-ToGU  |b rus  |c RU-ToGU 
245 1 0 |a Implementation of data fusion to increase the efficiency of classification of precancerous skin states using in vivo bimodal spectroscopic technique  |c V. Kupriyanov, W. Blondel, C. Daul [et al.] 
336 |a Текст 
337 |a электронный 
504 |a Библиогр.: 47 назв. 
520 3 |a This study presents the results of the classification of diffuse reflectance (DR) spectra and multiexcitation autofluorescence (AF) spectra that were collected in vivo from precancerous and benign skin lesions at three different source detector separation (SDS) values. Spectra processing pipeline consisted of dimensionality reduction, which was performed using principal component analysis (PCA), followed by classification step using such methods as support vector machine (SVM), multilayered perceptron (MLP), linear discriminant analysis (LDA), and random forest (RF). In order to increase the efficiency of lesion classification, several data fusion methods were applied to the classification results: majority voting, stacking, and manual optimization of weights. The results of the study showed that in most of cases the use of data fusion methods increased the average multiclass classification accuracy from 2% up to 4%. The highest accuracy of multiclass classification was obtained using the manual optimization of weights and reached 94.41%. 
653 |a автофлуоресценция 
653 |a диффузное отражение 
653 |a машинное обучение 
653 |a рак кожи 
655 4 |a статьи в журналах 
700 1 |a Kupriyanov, Valentin 
700 1 |a Blondel, Walter 
700 1 |a Daul, Christian 
700 1 |a Amouroux, Marine 
700 1 |a Kistenev, Yury V. 
773 0 |t Journal of biophotonics  |d 2023  |g Vol. 16, № 7. P. e202300035 (1-14)  |x 1864-063X 
852 4 |a RU-ToGU 
856 4 |u http://vital.lib.tsu.ru/vital/access/manager/Repository/koha:001017034 
908 |a статья 
999 |c 1017034  |d 1017034 

Similar Items