Noninvasive detection of bladder cancer using mid-infrared spectra classification. (15th December 2017)

• Record Type: Journal Article
• Authors: Bensaid, Siouar; Kachenoura, Amar; Costet, Nathalie; Bensalah, Karim; Tariel, Hugues; Senhadji, Lotfi
• Is Part Of: Expert systems with applications. Volume 89(2017)
• Page Start: 333
• Page End: 342
• Publication Date: 2017-12-15
• Subjects: Bladder cancer -- Variable selection -- Infrared spectroscopy -- Automatic detection -- Chalcogenide glass fibers -- PLSDA -- SVM; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.07.052
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: New system is used to acquire mid-infrared spectra from urine samples. New PLSDA-based classifiers are designed for automatic bladder cancer detection. The best classifier allows for automatic detection of bladder cancer with an accuracy of 82.35%. A minimally invasive medical device with a high potential for screening and follow-up is envisioned. Abstract: In this paper, we focus on the detection of Bladder Cancer (BC) via mid infrared spectroscopy. Two main contributions, material and methods, are presented. In terms of material, a new minimally invasive technology, combining fiber evanescent wave spectroscopy and newly patented biosensors, is used for the first time to acquire mid-infrared spectra from voided urine/bladder wash. This new machine promises practicality, cheapness and high-quality of spectrum acquisition. As for classical systems, the data acquired using the new system was highly correlated, resulting in a poor classification performance using classical methods. Therefore, the second contribution consists in developing statistical methods that alleviate the problem. Three new statistical methods based on Partial Least Square Discriminant Analysis algorithm (PLSDA) are proposed. PLSDA is a supervised classifier well-known for its ability to process correlated data. The key point is the choice of the most discriminant latent variables in the training step. In this work, we propose three new decision rules in order to select the most relevant latent variables. These decision rules give rise to three algorithms, namely bayesian, joint and best model PLSDA. A comparative study between the proposed methods and standard ones, namely SVM, K-MEANS and classical PLSDA, confirms clearly the efficiency of the former. The best performance in terms of accuracy is achieved by joint and best model PLSDA (82.35%). Besides, by embedding the proposed statistical methods in the new machine, we are able to provide a new medical device that is very promising in terms of automatic bladder cancer detection.