Worldwide, oral cancer is the sixth most common type of cancer. India is in 2nd position, with the highest number of oral cancer patients. To the population of oral cancer patients, India contributes to almost one-third of the total count. Among several types of oral cancer, the most common and dominant one is oral squamous cell carcinoma (OSCC). The major reason for oral cancer is tobacco consumption, excessive alcohol consumption, unhygienic mouth condition, betel quid eating, viral infection (namely human papillomavirus), etc. The early detection of oral cancer type OSCC, in its preliminary stage, gives more chances for better treatment and proper therapy. In this paper, author proposes a convolutional neural network model, for the automatic and early detection of OSCC, and for experimental purposes, histopathological oral cancer images are considered. The proposed model is compared and analyzed with state-of-the-art deep learning models like VGG16, VGG19, Alexnet, ResNet50, ResNet101, Mobile Net and Inception Net. The proposed model achieved a cross-validation accuracy of 97.82%, which indicates the suitability of the proposed approach for the automatic classification of oral cancer data.

Deep learning approaches for medical image analysis are widely applied for the recognition and classification of different kinds of cancer. In this study, histopathological images of oral cells are analyzed for the programmed recognition of Oral squamous cell carcinoma (OSCC) using the proposed framework. The suggested model applies transfer learning and ensemble learning in two phases. In the 1st phase, a few Convolutional neural network (CNN) models are considered through transfer learning applications for OSCC detection. In the 2nd phase, the ensemble model is constructed considering the best two pre-trained CNN from the 1st phase. The proposed classifier is compared with leading-edge models like Alexnet, Resnet50, Resnet101, Inception net, Xception net, and InceptionresnetV2. Results are analyzed to demonstrate the effectiveness of the suggested framework. A three-phase comparative analysis is considered. Firstly, various metrics including accuracy, recall, F-score, and precision are evaluated. Secondly, a graphical analysis using a loss and accuracy graph is performed. Lastly, the accuracy of the proposed classifier is compared with that of other models from existing literature. Following the three-stage performance evaluation, the proposed ensemble classifier exhibits enhanced performance with an accuracy of 97.88%.

In high-dimensional data analysis, Feature Selection (FS) is one of the most fundamental issues in machine learning and requires the attention of researchers. These datasets are characterized by huge space due to a high number of features, out of which only a few are significant for analysis. Thus, significant feature extraction is crucial. There are various techniques available for feature selection; among them, the filter techniques are significant in this community, as they can be used with any type of learning algorithm and drastically lower the running time of optimization algorithms and improve the performance of the model. Furthermore, the application of a filter approach depends on the characteristics of the dataset as well as on the machine learning model. Thus, to avoid these issues in this research, a combination of feature reduction (CFR) is considered designing a pipeline of filter approaches for high-dimensional microarray data classification. Considering four filter approaches, sixteen combinations of pipelines are generated. The feature subset is reduced in different levels, and ultimately, the significant feature set is evaluated. The pipelined filter techniques are Correlation-Based Feature Selection (CBFS), Chi-Square Test (CST), Information Gain (InG), and Relief Feature Selection (RFS), and the classification techniques are Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), and k-Nearest Neighbor (k-NN). The performance of CFR depends highly on the datasets as well as on the classifiers. Thereafter, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method is used for ranking all reduction combinations and evaluating the superior filter combination among all.