An Automated Approach for Identification of Oral Squamous Cell Carcinoma based on 2D-ICNN
Singaraju Ramya, R. I. Minu, KT Magesh · 2023
Oral cancer (OC) is a malignant neoplasm that poses a significant threat to human health, resulting in a considerable fatality rate. India accounts for almost one-third of the global population of OC patients. Among the various types of OC, OSCC is the most common and dominant. Histopathological images are widely considered as the benchmark for diagnosing OSCC. However, this method is known to be time-consuming and requires a high level of expertise due to the heterogeneity of the tumor. To aid accurate diagnosis, artificial Intelligence (AI) techniques have been employed. Deep Learning (DL) algorithms, such as the Two-Dimensional Improved Convolutional Neural Network (2D-ICNN) using GLCM have shown promise in predicting different medical image-based cancers, including breast cancer, OC, and lung cancer. This research work proposes a new approach for classifying OC by utilizing the 2D-ICNN technique. Our method focuses on extracting the best features from biopsy images of OSCC to train the model. By employing GLCM, achieve efficient feature extraction. The findings of our simulations indicate that the suggested model attains an especially elevated level of classification accuracy, amounting to 98.29%. The timely identification of OC, particularly in its early stages, is of paramount importance in facilitating optimal treatment and suitable therapy. The integration of DL algorithms, such as our proposed model, holds promise for improving the diagnosis and management of OC.