Comparative Analysis of Deep Learning Architectures for Multi-Disease Classification of Single-Label Chest X-rays

2026-03-11

AI Summary

This study addresses the challenges of diagnostic accuracy in chest radiography arising from radiologist shortages and inter-reader variability by systematically evaluating the single-label classification performance of seven state-of-the-art deep learning models—including both CNN and Transformer architectures—across five thoracic conditions: cardiomegaly, COVID-19, normal, pneumonia, and tuberculosis. All models were initialized with ImageNet pretraining and trained under identical conditions, including standardized image preprocessing, patient-level data splitting, and hyperparameter settings, with Grad-CAM used to verify alignment with clinically relevant regions. ConvNeXt-Tiny achieved the highest performance (92.31% accuracy, 95.70% AUROC), while MobileNetV2 delivered 90.42% accuracy with only 3.5M parameters and a 48-minute training time. Notably, AUROC exceeded 99.97% for both COVID-19 and tuberculosis. This work provides the first comprehensive, controlled comparison of diverse architectures on a balanced chest X-ray dataset, offering empirical guidance for clinical deployment.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Chest X-ray imaging remains the primary diagnostic tool for pulmonary and cardiac disorders worldwide, yet its accuracy is hampered by radiologist shortages and inter-observer variability. This study presents a systematic comparative evaluation of seven deep learning architectures for multi-class chest disease classification: ConvNeXt-Tiny, DenseNet121, DenseNet201, ResNet50, ViT-B/16, EfficientNetV2-M, and MobileNetV2. A balanced dataset of 18,080 chest X-ray images spanning five disease categories (Cardiomegaly, COVID-19, Normal, Pneumonia, and Tuberculosis) was constructed from three public repositories and partitioned at the patient level to prevent data leakage. All models were trained under identical conditions using ImageNet-pretrained weights, standardized preprocessing, and consistent hyperparameters. All seven architectures exceeded 90% test accuracy. ConvNeXt-Tiny achieved the highest performance (92.31% accuracy, 95.70% AUROC), while MobileNetV2 emerged as the most parameter-efficient model (3.5M parameters, 90.42% accuracy, 94.10% AUROC), completing training in 48 minutes. Tuberculosis and COVID-19 classification was near-perfect (AUROC >= 99.97%) across all architectures, while Normal, Cardiomegaly, and Pneumonia presented greater challenges due to overlapping radiographic features. Grad-CAM visualizations confirmed clinically consistent attention patterns across disease categories. These findings demonstrate that high-accuracy multi-disease chest X-ray classification is achievable without excessive computational resources, with important implications for AI-assisted diagnosis in both resource-rich and resource-constrained healthcare settings.

Problem

• chest X-ray
• multi-disease classification
• deep learning
• radiologist shortage
• inter-observer variability

Innovation

• deep learning architectures
• multi-disease classification
• chest X-ray
• parameter efficiency
• Grad-CAM visualization