PMID- 29188115 OWN - NLM STAT- PubMed-not-MEDLINE LR - 20201001 IS - 2156-7085 (Print) IS - 2156-7085 (Electronic) IS - 2156-7085 (Linking) VI - 8 IP - 11 DP - 2017 Nov 1 TI - Raman spectral post-processing for oral tissue discrimination - a step for an automatized diagnostic system. PG - 5218-5227 LID - 10.1364/BOE.8.005218 [doi] AB - Most oral injuries are diagnosed by histopathological analysis of a biopsy, which is an invasive procedure and does not give immediate results. On the other hand, Raman spectroscopy is a real time and minimally invasive analytical tool with potential for the diagnosis of diseases. The potential for diagnostics can be improved by data post-processing. Hence, this study aims to evaluate the performance of preprocessing steps and multivariate analysis methods for the classification of normal tissues and pathological oral lesion spectra. A total of 80 spectra acquired from normal and abnormal tissues using optical fiber Raman-based spectroscopy (OFRS) were subjected to PCA preprocessing in the z-scored data set, and the KNN (K-nearest neighbors), J48 (unpruned C4.5 decision tree), RBF (radial basis function), RF (random forest), and MLP (multilayer perceptron) classifiers at WEKA software (Waikato environment for knowledge analysis), after area normalization or maximum intensity normalization. Our results suggest the best classification was achieved by using maximum intensity normalization followed by MLP. Based on these results, software for automated analysis can be generated and validated using larger data sets. This would aid quick comprehension of spectroscopic data and easy diagnosis by medical practitioners in clinical settings. FAU - Carvalho, Luis Felipe C S AU - Carvalho LFCS AD - Univap/Instituto de Pesquisa e Desenvolvimento, Laboratorio de Espectroscopia Vibracional Biomedica, Avenida Shishima Hifumi, 2911, Sao Jose dos Campos/SP, CEP: 12244-000, Brazil. AD - luisfelipecarvalho@hotmail.com. FAU - Nogueira, Marcelo Saito AU - Nogueira MS AD - Universidade de Sao Paulo/ Sao Carlos Institute of Physics, Optics Group, Biophotonics Division, Avenida Trabalhador Sao Carlense, 400, Sao Carlos/SP, CEP: 13566-590, Brazil. AD - marcelosaitonogueira@gmail.com. FAU - Neto, Lazaro P M AU - Neto LPM AD - Univap/Instituto de Pesquisa e Desenvolvimento, Laboratorio de Espectroscopia Vibracional Biomedica, Avenida Shishima Hifumi, 2911, Sao Jose dos Campos/SP, CEP: 12244-000, Brazil. FAU - Bhattacharjee, Tanmoy T AU - Bhattacharjee TT AD - Univap/Instituto de Pesquisa e Desenvolvimento, Laboratorio de Espectroscopia Vibracional Biomedica, Avenida Shishima Hifumi, 2911, Sao Jose dos Campos/SP, CEP: 12244-000, Brazil. FAU - Martin, Airton A AU - Martin AA AD - Biomedical Engineering Innovation Center - Biomedical Vibrational Spectroscopy Group, Universidade Brasil - UnBr - Rua Carolina Fonseca, 235 - 08230-030 - Itaquera, Sao Paulo/SP/ Visiting Professor Universidade Federal do Piaui - UFPI - Campus Ministro Petronio Portella Departamento de Fisica - CCN Bairro Ininga Teresina, PI, CEP: 64049-550, Brazil. AD - amartin@pq.cnpq.br. LA - eng PT - Journal Article DEP - 20171024 PL - United States TA - Biomed Opt Express JT - Biomedical optics express JID - 101540630 EIN - Biomed Opt Express. 2018 Jan 16;9(2):649. PMID: 29553144 PMC - PMC5695965 OTO - NOTNLM OT - (120.3890) Medical optics instrumentation OT - (120.6200) Spectrometers and spectroscopic instrumentation OT - (170.1610) Clinical applications OT - (200.4560) Optical data processing OT - (300.6330) Spectroscopy, inelastic scattering including Raman EDAT- 2017/12/01 06:00 MHDA- 2017/12/01 06:01 PMCR- 2017/10/24 CRDT- 2017/12/01 06:00 PHST- 2017/01/20 00:00 [received] PHST- 2017/03/18 00:00 [revised] PHST- 2017/03/27 00:00 [accepted] PHST- 2017/12/01 06:00 [entrez] PHST- 2017/12/01 06:00 [pubmed] PHST- 2017/12/01 06:01 [medline] PHST- 2017/10/24 00:00 [pmc-release] AID - 285377 [pii] AID - 10.1364/BOE.8.005218 [doi] PST - epublish SO - Biomed Opt Express. 2017 Oct 24;8(11):5218-5227. doi: 10.1364/BOE.8.005218. eCollection 2017 Nov 1.