High-Performance Lung Disease Identification and Explanation Using a ReciproCAM-Enhanced Lightweight Convolutional Neural Network
Open Access
- 9 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 84954-84965
Abstract
Lung diseases significantly contribute to global morbidity and mortality, underscoring the importance of accurate and efficient diagnostic tools. This study introduces a lightweight two-dimensional convolutional neural network (LW-2DCNN) integrated with ReciproCAM, an explainable artificial intelligence (XAI) technique, specifically designed to classify multiple pulmonary conditions from chest computed tomography (CT) scans. Our model effectively addresses limitations of existing diagnostic methods by enhancing computational efficiency, diagnostic accuracy, and interpretability. Utilizing a curated dataset comprising 10,000 CT images from a Korean population, the LW-2DCNN achieved exceptional accuracy of 99.80% across five diagnostic categories: normal, lung cancer, pneumothorax, pneumonia, and interstitial lung disease (ILD). Comparative analyses demonstrated superior performance relative to established benchmark models, including EfficientNetB0, ResNet50, InceptionV3, DenseNet121, NASNetMobile, MobileNetV2, and Xception. The integrated ReciproCAM technique significantly enhanced clinical interpretability by highlighting the precise anatomical regions influencing the model’s diagnostic decisions. Ablation studies validated the optimal choice of the Adam optimizer and demonstrated the model’s computational feasibility, predicting and explaining 1000 images in approximately 150 seconds on a CPU-only device. This indicates strong potential for deployment in resource-constrained clinical settings.Keywords
Funding Information
- Institute of Information & Communications Technology Planning & Evaluation (IITP)-Innovative Human Resource Development for Local Intellectualization Program grant funded by Korean Government (IITP-2025-RS-2024-00436773)
This publication has 43 references indexed in Scilit:
- XCovNet: An optimized xception convolutional neural network for classification of COVID-19 from point-of-care lung ultrasound imagesMultimedia Tools and Applications, 2023
- Lightweight deep CNN-based models for early detection of COVID-19 patients from chest X-ray imagesExpert Systems with Applications, 2023
- Applications of deep learning in disease diagnosis of chest radiographs: A survey on materials and methodsBiomedical Engineering Advances, 2023
- Advances in Deep Learning for Tuberculosis Screening using Chest X-rays: The Last 5 Years ReviewJournal of Medical Systems, 2022
- Deep learning models-based CT-scan image classification for automated screening of COVID-19Biomedical Signal Processing and Control, 2022
- A lightweight CNN-based network on COVID-19 detection using X-ray and CT imagesComputers in Biology and Medicine, 2022
- A lightweight deep learning architecture for the automatic detection of pneumonia using chest X-ray imagesMultimedia Tools and Applications, 2021
- A deep learning approach using effective preprocessing techniques to detect COVID-19 from chest CT-scan and X-ray imagesComputers in Biology and Medicine, 2021
- Towards an effective and efficient deep learning model for COVID-19 patterns detection in X-ray imagesResearch on Biomedical Engineering, 2021
- Two-stage classification of tuberculosis culture diagnosis using convolutional neural network with transfer learningThe Journal of Supercomputing, 2020