Key points are not available for this paper at this time.
Oral cancer poses a global health concern, affecting the mouth, throat, face, and oral glands. Histopathology images play a crucial role in diagnosing and predicting anomalies, yet human error remains a challenge in physical examinations. Deep learning algorithms offer advancements, aiding medical professionals by enhancing the accuracy of oral cancer identification from histopathology pictures. This study modifies three Convolutional Neural Network (CNN) architectures, including two based on DENSENET-121, to discern photos containing both oral cancer and healthy cells. The experiment focuses on two classes: normal and malignant cells, with a global incidence rate of 7 for malignancy, a prevalent form of head and neck cancer. Traditional oral squamous cell carcinoma (OSCC) diagnosis relies on time-consuming histological analysis, prone to human interpretation variations. Utilizing artificial intelligence techniques improves diagnostic accuracy, expediting precise diagnoses. This research aims to employ hybrid methodologies, leveraging fused characteristics to optimize early OSCC detection, addressing a critical need in global healthcare.
Paramasivam et al. (Wed,) studied this question.