Multi-Model Convolutional Neural Network Ensemble with Attention for Pneumonia Detection

Satyam Jai; Siddharth Sahoo; Harsh Gupta; Madhumitha Kulandaivel

doi:10.71097/IJSAT.v16.i4.9455

Multi-Model Convolutional Neural Network Ensemble with Attention for Pneumonia Detection

Author(s)	Mr. Satyam Jai, Mr. Siddharth Sahoo, Mr. Harsh Gupta, Dr. Madhumitha Kulandaivel
Country	India
Abstract	Pneumonia has emerged as a persistent global health burden, especially in high-risk groups such as children and the elderly where timely and reliable diagnosis is essential. In current clinical environments, efficient chest X-ray examination, interpretation and diagnosis relies primarily upon expert radiologists, indicating clear challenges in rural or resource-poor settings. We present a deep learning framework for automatic pneumonia detection using chest X-rays. We propose a novel method to fine-tune and blend two powerful convolutional neural networks (CNNs), VGG16 and ResNe50, through a weighted ensemble approach. Consideration of user needs and application transparency were augmented to enhance user confidence through the use of attention mechanisms and Grad-CAM explainability. Performance evaluations implemented upon a unified database of 11,733 X-ray images attained a sensitivity of , accuracy of 98.44 and an F1-score of 0.99 , surpassing three existing models. The proposed framework has demonstrated scalability, interpretability and adaptability for a feasible clinical deployment in low-resourced areas.
Keywords	Pneumonia Detection, Convolutional Neural Networks, Ensemble Learning, Attention Mechanisms, Explainable AI, Medical Imaging
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-11-17
DOI	https://doi.org/10.71097/IJSAT.v16.i4.9455
Short DOI	https://doi.org/hbb8g3

View / Download PDF File

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Multi-Model Convolutional Neural Network Ensemble with Attention for Pneumonia Detection

Share this