Deep Learning Automated Differential Diagnosis of Pharyngitis using Smartphone Camera

In this article, we aimed to diagnose whether patients have bacterial pharyngitis ornonbacterial pharyngitis. To achieve this, a dataset from ۵۷۹ patients was collected, and at leastfour general practitioners diagnosed each sample. Data augmentation methods were employedto increase the sample size, and various preprocessing techniques were applied to enhance thequality of images. In this study, we utilized a Convolutional Neural Network (CNN) and twotransformers for binary classification. The results demonstrate the capability of deep learningmodels to classify pharyngitis into bacterial and nonbacterial categories based on images takenby smartphone cameras with high accuracy.

کلیدواژه ها:

Bacterial ، Nonbacterial ، Pharyngitis ، Deep Learning ، CNNs ، Vision Transformer ، Swin Transformer