Intelligent Deep Learning Enabled Oral Squamous Cell Carcinoma Detection and Classification Using Biomedical Images. (30th June 2022)

• Record Type: Journal Article
• Authors: Alanazi, Adwan A.; Khayyat, Manal M.; Khayyat, Mashael M.; Elamin Elnaim, Bushra M.; Abdel-Khalek, Sayed
• Other Names: Javed Abdul Rehman Academic Editor.
• Is Part Of: Computational intelligence and neuroscience. Volume 2022(2022)
• Publication Date: 2022-06-30
• Subjects: Neurosciences -- Data processing -- Periodicals; Computational intelligence -- Periodicals; Computational neuroscience -- Periodicals; 612.80285
• DOI: 10.1155/2022/7643967
• Languages: English
• ISSNs: 1687-5265

Abstract

Abstract : Oral cancer is one of the lethal diseases among the available malignant tumors globally, and it has become a challenging health issue in developing and low-to-middle income countries. The prognosis of oral cancer remains poor because over 50% of patients are recognized at advanced stages. Earlier detection and screening models for oral cancer are mainly based on experts' knowledge, and it necessitates an automated tool for oral cancer detection. The recent developments of computational intelligence (CI) and computer vision-based approaches help to accomplish enhanced performance in medical-image-related tasks. This article develops an intelligent deep learning enabled oral squamous cell carcinoma detection and classification (IDL-OSCDC) technique using biomedical images. The presented IDL-OSCDC model involves the recognition and classification of oral cancer on biomedical images. The proposed IDL-OSCDC model employs Gabor filtering (GF) as a preprocessing step to eliminate noise content. In addition, the NasNet model is exploited for the generation of high-level deep features from the input images. Moreover, an enhanced grasshopper optimization algorithm (EGOA)-based deep belief network (DBN) model is employed for oral cancer detection and classification. The hyperparameter tuning of the DBN model is performed using the EGOA algorithm which in turn boosts the classification outcomes. The experimentation outcomes of the IDL-OSCDC model using a benchmark biomedical imaging dataset highlighted its promising performance over the other methods with maximum accu y, prec n, reca l, and F score of 95%, 96.15%, 93.75%, and 94.67% correspondingly.