Nuclear F-actin Cytology in Oral Epithelial Dysplasia and Oral Squamous Cell Carcinoma

Abstract

Oral cavity cancer has a low 5-y survival rate, but outcomes improve when the disease is detected early. Cytology is a less invasive method to assess oral potentially malignant disorders relative to the gold-standard scalpel biopsy and histopathology. In this report, we aimed to determine the utility of cytological signatures, including nuclear F-actin cell phenotypes, for classifying the entire spectrum of oral epithelial dysplasia and oral squamous cell carcinoma. We enrolled subjects with oral potentially malignant disorders, subjects with previously diagnosed malignant lesions, and healthy volunteers without lesions and obtained brush cytology specimens and matched scalpel biopsies from 486 subjects. Histopathological assessment of the scalpel biopsy specimens classified lesions into 6 categories. Brush cytology specimens were analyzed by machine learning classifiers trained to identify relevant cytological features. Multimodal diagnostic models were developed using cytology results, lesion characteristics, and risk factors. Squamous cells with nuclear F-actin staining were associated with early disease (i.e., lower proportions in benign lesions than in more severe lesions), whereas small round parabasal-like cells and leukocytes were associated with late disease (i.e., higher proportions in severe dysplasia and carcinoma than in less severe lesions). Lesions with the impression of oral lichen planus were unlikely to be either dysplastic or malignant. Cytological features substantially improved upon lesion appearance and risk factors in predicting squamous cell carcinoma. Diagnostic models accurately discriminated early and late disease with AUCs (95% CI) of 0.82 (0.77 to 0.87) and 0.93 (0.88 to 0.97), respectively. The cytological features identified here have the potential to improve screening and surveillance of the entire spectrum of oral potentially malignant disorders in multiple care settings.

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 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.…”

Changes of Ex Vivo Cervical Epithelial Cells Due to Electroporation with JMY

“…Prior studies analysed the relationship between cytological details of clinically relevant disorders and the actin content of squamous cells [44][45][46]. Here we tried to make a pioneer study in molecular cytopathology, since this is the first time that we are exploring the possible relationship between cytopathologically relevant morphological…”