CNN BASED CHEST X-RAY CLASSIFICATION

CNN BASED CHEST X-RAY CLASSIFICATION

1 BHAGYA S G , 2 ROOPA R

1 Assistant Professor, AI and ML Department,BIET, Davangere

2Assistant Professor, Department of MCA, BIET, Davangere

ABSTRACT

India faces acute shortage of radiologists. As per NCBI, USA India has one radiologist per 1,00,000 people. In past two years we have seen unprecedented COVID-19 pandemic which has posed a huge burden on our health care infrastructure and health care professionals. The rural parts are hit worst struggling to provide lifesaving health care access causing millions of Indians to lose their lives. In this regard our project focuses on developing a web based application which may reduce the burden on health care professionals and help in timely diagnosis of chest x-ray findings without delays and withprecision. This will help to treat patients with utmost care, can avoid unnecessary surgeriesand save lives.

In the recent years Artificial Intelligence(AI) empowered systems have proven to be dominant in all domains. Artificial Intelligence has attracted most of the researchers of therecent past. Artificial Intelligence which encompasses all the industries has been proven tobe vital in Health care by helping healthcare professionals in taking decisions and also in diagnosis and detection of several critical ailments like cancers and others.

In this project we have leveraged the transfer learning as benchmark to obtain the models for our task of classification. We have executed the experiment through the various standard models available retaining the similar experimental conditions and did the comparative analysis to evaluate them and to pick the best one among them. The results achieved show that Densenet-169 provided the best results with 95.56 percentage validation accuracy which has been used for making predictions in the web application.