Stratified squamous epithelial biopsy image classifier using machine learning and neighborhood feature selection.

• The main objective of this work is to design and develop a classifier for oral squamous cell carcinoma (OSCC) originating in stratified squamous epithelial tissue of oral cavity. The classifier is named as Stratified Squamous Epithelium Biopsy Image Classifier (SSE-BIC). This algorithm automatize the detection and or classification process which is still a tedious work being done manually via visual inspection by experts. • A total 676 images have been used to design, train and test the classifier. As many as 305 features have been computed from H&E-stained microscopic images of oral mucosa which include colour features, textural features, gradient features, shape features and tamura features to design the SSE-BIC. We used, unsupervised data mining technique to extract cellular regions from the images as a part of shape feature extraction process. • The accuracy observed as an exhaustive simulation is found to be 95.56% using H&E-stained microscopic colour images which has very complicated structure as compared to cytology images. Squamous cell carcinoma (SCC) of oral cavity is the most common among oral cancer patients. In this paper, we have developed machine learning based automatic oral squamous cell carcinoma (OSCC) classifier named as Stratified Squamous Epithelial Biopsy Image Classifier (SSE-BIC) to categorize H&E-stained microscopic images of squamous epithelial layer in four different classes: normal, well-differentiated, moderately-differentiated and poorly-differentiated. Five classifiers are used to perform the classification by maximum voting method. Total 305 features are extracted from the images of oral mucosa which include color features, textural features, gradient features, geometrical features and tamura features. Unsupervised data mining is used for segmenting the cellular area to compute geometrical features of the cells retaining color details of the images. Feature selection has been performed by neighborhood component feature selection (NCFS) technique. Total 676 images have been used to design, train and test the classifier. A detailed performance analysis is presented with individual feature sets and hybrid feature sets with feature selection applied using individual classifiers as well as proposed classifier. The proposed classifier achieves overall accuracy of 95.56%. This can account for first level of automatic screening of the biopsy images. [ABSTRACT FROM AUTHOR]