Deep Learning Automated Differential Diagnosis of Pharyngitis using Smartphone Camera, By Habib Rostami

Research

Title	Deep Learning Automated Differential Diagnosis of Pharyngitis using Smartphone Camera
Type	Presentation
Keywords	Bacterial , Nonbacterial , Pharyngitis , Convolutional Neural Network, Vision Transformer
Researchers	negar shojaei (First researcher) , ali behrozi (Second researcher) , Habib Rostami (Third researcher) , Amir Sanati (Fourth researcher) , Majid Alimohammadi (Fifth researcher) , jahanbakhsh Keyvani (Not in first six researchers)

Abstract

In this article, we aimed to diagnose whether patients have bacterial pharyngitis or nonbacterial pharyngitis. To achieve this, a dataset from 579 patients was collected, and at least four general practitioners diagnosed each sample. Data augmentation methods were employed to increase the sample size, and various preprocessing techniques were applied to enhance the quality of images. In this study, we utilized a Convolutional Neural Network (CNN) and two transformers for binary classification. The results show that deep learning classifiy the pharyngitis into bacterial and nonbacterial, based on images taken by smartphone cameras, precisely.