Chest X-ray Classification Based on Deep Neural Network

2024

Closed access Metadata (CSL-JSON)
DOI 10.1109/aic61668.2024.10730835
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This study demonstrates how artificial intelligence (AI) is transforming medical diagnosis, particularly for respiratory disorders such as COVID-19 and influenza. The project aims to enhance global healthcare systems by accurately and rapidly identifying respiratory disorders through AI-driven chest X-ray analysis. Given the significant public health implications of infections like COVID-19, the importance of this work is paramount. Convolutional Neural Networks (CNNs) are employed to analyze chest X-ray images and detect patterns indicative of viral infections. Key components of the project include convolutional blocks, the RMSprop optimizer, 2D max pooling, dropout regularization, and the categorical cross-entropy loss function. Two CNN models are developed from scratch to balance complexity and efficacy in X-ray image classification.