Quantitative dimensions of histopathological attributes and status of GSTM1–GSTT1 in oral submucous fibrosis

Epithelial Distribution of E-Cadherin, p63, and Mitotic Figures in ApoTome Images to Determine the Oncogenic Potentiality of Oral Submucous Fibrosis

The exact process of the malignant conversion of oral submucous fibrosis (OSF) to oral cancer is not fully understood. This study aimed to detect and analyze E-cadherin expression, p63 expression, and number of mitotic figures, all correlated to cancer development, in ApoTome images of oral tissues to determine the oncogenic potentiality of OSF. ApoTome images of the study groups (6 normal, 16 OSF with dysplasia, and 10 OSF without dysplasia) were recorded. Cytoplasmic and membranous E-cadherin expression, breakages of the cell membrane, and p63 expression were detected in MATLAB 2016b. The number of mitotic figures detected by MATLAB was correlated with the number of chromosomes detected by ImageJ. A Mann–Whitney U test was done to determine a significant difference between the study groups for cytoplasmic and membranous E-cadherin distribution points. Statistical significant differences were found for cytoplasmic E-cadherin distribution between normal and OSF (with dysplasia) (p = 0.0278). There was an increase in mitotic figures, p63 expression, and cytoplasmic E-cadherin expression and a decrease in membranous E-cadherin expression from normal to diseased condition. Hence, automated detection and quantification of E-cadherin, p63, and mitotic figures in ApoTome images of oral biopsies can help in determining the oncogenic potentiality of OSF.

Susceptibility to oral squamous cell carcinoma: correlation with variants of CYP1A1-MspI, GSTT1, GSTM1, ALDH2, EC-SOD and Lifestyle factors

In order to investigate the association between polymorphisms in genes encoding metabolizing enzymes (CYP1A1-MspI, EC-SOD (extracellular superoxide dismutase), GSTT1, GSTM1, ALDH2), cigarette and alcohol consumption, and the risk of oral squamous cell carcinoma, we conducted a prospective case-control study comprised of 750 individuals with oral squamous cell carcinoma (OSCC) and 750 healthy individuals. Data about smoking and drinking habits were collected along with other demographic and clinical information. Peripheral blood samples were collected for DNA extraction, and polymerase chain reaction (PCR) and PCR-RFLP (restriction fragment length polymorphism) were used to determine genotypes of CYP1A1, EC-SOD, GSTT1, GSTM1, ALDH2. The results showed that smoking and alcohol consumption were significantly more common among patients than controls (p <0.05). There were significant differences in the genotype distribution for each locus between groups, with the CYP1A1 (m2/ m2), EC-SOD (C/G), GSTT1 [-], GSTM1 [-] and ALDH2 (non G/G) genotypes being more common among patients (p <0.05). Furthermore, the majority of patients had at least two or more variant genotypes, while controls had one or no variant genotype (p <0.05). Finally, multiple variant genotypes combined with smoking, drinking, or both smoking and drinking significantly increased the risk of OSCC, with greater increase for heavier smoking/drinking. In brief, genetic polymorphism of CYP1A1, EC-SOD, GSTT1, GSTM1, and ALDH2 and smoking and drinking history are closely associated with susceptibility to OSCC.

Automated oral cancer identification using histopathological images: a hybrid feature extraction paradigm

Oral cancer (OC) is the sixth most common cancer in the world. In India it is the most common malignant neoplasm. Histopathological images have widely been used in the differential diagnosis of normal, oral precancerous (oral sub-mucous fibrosis (OSF)) and cancer lesions. However, this technique is limited by subjective interpretations and less accurate diagnosis. The objective of this work is to improve the classification accuracy based on textural features in the development of a computer assisted screening of OSF. The approach introduced here is to grade the histopathological tissue sections into normal, OSF without Dysplasia (OSFWD) and OSF with Dysplasia (OSFD), which would help the oral onco-pathologists to screen the subjects rapidly. The biopsy sections are stained with H&E. The optical density of the pixels in the light microscopic images is recorded and represented as matrix quantized as integers from 0 to 255 for each fundamental color (Red, Green, Blue), resulting in a M×N×3 matrix of integers. Depending on either normal or OSF condition, the image has various granular structures which are self similar patterns at different scales termed "texture". We have extracted these textural changes using Higher Order Spectra (HOS), Local Binary Pattern (LBP), and Laws Texture Energy (LTE) from the histopathological images (normal, OSFWD and OSFD). These feature vectors were fed to five different classifiers: Decision Tree (DT), Sugeno Fuzzy, Gaussian Mixture Model (GMM), K-Nearest Neighbor (K-NN), Radial Basis Probabilistic Neural Network (RBPNN) to select the best classifier. Our results show that combination of texture and HOS features coupled with Fuzzy classifier resulted in 95.7% accuracy, sensitivity and specificity of 94.5% and 98.8% respectively. Finally, we have proposed a novel integrated index called Oral Malignancy Index (OMI) using the HOS, LBP, LTE features, to diagnose benign or malignant tissues using just one number. We hope that this OMI can help the clinicians in making a faster and more objective detection of benign/malignant oral lesions.