AI-Based Automated Chest X-Ray Analysis Using Ensemble Model for Lung Disorders Classification

View at publisher Summarise with VIRAT
Authors: Tharun E, Varun M, Velmurugan KL, N. Kirthika
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Lung diseases such as tuberculosis, pneumonia, and COVID-19 are major global health concerns that require rapid and accurate diagnosis for effective treatment. These conditions demand immediate medical attention to prevent severe complications. Traditional chest X-ray interpretation relies on manual assessment by radiologists, which is time-consuming and prone to human error. This paper presents an ensemble-based deep learning framework that automates chest X-ray analysis for multi-class lung disorder classification. The proposed system integrates YOLOv8, ResNet18, Vision Transformer (ViT), and a custom CNN into a weighted ensemble model to improve diagnostic accuracy. The models were trained on a multi-class X-ray dataset including COVID-19, tuberculosis, bacterial pneumonia, viral pneumonia, and normal cases. The weighted probability fusion method enhances diagnostic reliability by combining predictions from multiple architectures. The system operates on a Raspberry Pi with a Coral USB accelerator, enabling real-time inference with low power consumption. Experimental results demonstrate a classification accuracy between 92 % and 95 %, confirming the efficiency of the proposed framework for automated medical diagnosis.

Fields of Study & Subjects

COVID-19 diagnosis using AI Advanced Neural Network Applications Radiomics and Machine Learning in Medical Imaging

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
958–965
Publication date
21 January 2026
Language
EN