Risk Prediction for Oral Potentially Malignant Disorders Using Fuzzy Analysis of Cytomorphological and Autofluorescence Alterations in Habitual Smokers

Abstract

Alterations in cellular morphology and autofluorescence intensities showed positive correlation with OPMD. The present study will benefit to investigate early prediction of OPMD among susceptible individuals.

Role of Artificial Intelligence in the Early Diagnosis of Oral Cancer. A Scoping Review

“…A total of 384 publications were found to be duplicates and were discarded, thus leaving 1167 articles of which 1110 were excluded after evaluation of the title and abstract. In the second step, and after full-text reading of the 62 selected articles, a total of 36 were included in the review [ 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 ], with a description of the relevant findings ( Figure 1 ).…”

“…Only five of the selected articles were published before 2015 [ 33 , 38 , 44 , 58 , 59 ]. The field work of 12 studies was carried out in India [ 29 , 30 , 34 , 39 , 44 , 49 , 51 , 52 , 54 , 55 , 56 , 57 ], while five studies were carried out in Malaysia [ 37 , 42 , 47 , 48 , 61 ] and in China [ 28 , 35 , 43 , 59 , 60 ], four in the United States [ 36 , 38 , 45 , 46 ], two in The Netherlands [ 33 , 58 ] and Poland [ 40 , 41 ], and one in Taiwan [ 32 ], Saudi Arabia [ 50 ], Morocco [ 31 ], Germany [ 27 ], Greece [ 53 ] and Sweden [ 62 ].…”

“…The study subjects and aims were classified as follows: (1) identification of the most appropriate biopsy site [ 28 ]; (2) selection of patients through clinical screening and the referral of suspicious cases to a specialist in oral medicine or oral cancer [ 30 , 37 , 52 , 57 , 61 ]; (3) screening in smokers [ 34 , 49 ]; (4) oral cancer screening through smart telecytology [ 54 ]; (5) the diagnosis of OPMDs such as solar cheilosis [ 53 ], oral lichen planus [ 41 , 46 ], leukoplakia [ 29 , 40 , 58 ], with a prediction of their course [ 43 ]; (6) aids to differential diagnosis by classifying the lesions as benign or precancerous [ 50 ]; normal mucosa or oral cancer [ 27 , 32 , 35 , 36 , 39 , 42 , 62 ]; or as different benign, premalignant and malignant lesions [ 31 , 33 , 39 , 46 , 59 ]; (7) classification of oral cancer [ 56 ]; and (8) development of oral cancer risk predictive models [ 42 , 47 , 48 , 51 , 55 , 60 ].…”

“…The most frequent evaluative metrics were: concordance [ 30 ]; precision [ 31 ], sensitivity, specificity [ 29 , 40 , 41 , 43 , 44 , 53 , 58 , 60 ]; concordance, sensitivity, specificity [ 37 ]; accuracy [ 47 , 56 ]; accuracy—area under the curve (AUC) [ 45 , 46 , 55 ], accuracy, sensitivity, specificity [ 28 , 34 , 36 , 38 , 39 , 42 , 49 , 52 , 54 ]; receiver operating characteristics curve (ROC-AUC) [ 33 ]; accuracy, sensitivity (recall), specificity, F-measure, ROC-AUC, precision [ 51 ]; precision, recall and F1-score [ 61 ]; sensitivity, specificity and ROC-AUC [ 45 , 57 ]; sensitivity, specificity and IOU (intersection over union evaluating accuracy of the ROI (region of interest)) [ 32 ]; accuracy, sensitivity, specificity and ROC-AUC [ 27 , 35 , 48 , 50 ]; accuracy, precision, recall and F-score [ 62 ]; sensitivity, specificity and positive predictive value [ 59 ]. The definitions of the terms employed are provided in Table 1 .…”

“…Cytological diagnosis was used in nine articles, based on exfoliative liquid [ 29 , 49 ], scraped [ 34 ] and brush biopsies ( Table 5 ) [ 43 , 45 , 46 , 52 , 62 ]. Banerjee et al [ 29 ], using linear SVM, classified oral leukoplakia and OSCC cells with a sensitivity and specificity of 100% when only using the cellular descriptors, vs. a sensitivity of 89.9% using the nuclear descriptors.…”