Pleural Effusion Detection Using Machine Learning and Deep Learning Based on Computer Vision

Document Type

Conference Proceeding

Publication Date

2022

Abstract

Pleural effusion is one of the serious chest diseases that affect human life depending on the causes, such as malignant tumors, liver, kidney or chest failure, and the risks increase with the delay in diagnosis and treatment. In recent years, artificial intelligence (AI) has achieved a significant development in the medical field. As part of artificial intelligence, deep learning (DL), machine learning (ML), and computer vision (CV) have become very important in the diagnosis and treatment of diseases, as they help in terms of early and accurate diseases diagnosis and suggesting the best treatments. Furthermore, with the widespread use of medical images in diagnosing diseases, the need for computer vision, machine learning, and deep learning to analyze and understand those images, and to help clinicians make quick and accurate diagnoses has increased. In this paper, machine learning model i.e., artificial neural network (ANN), and deep learning models i.e., AlexNet, GoogleNet, SqueezeNet, and DarkNet19, are used to detect the presence or absence of pleural effusion in Chest X-ray14 dataset images. We have used 80% of the dataset for training the models, and the remaining 20% for testing.

Share

COinS