.png){kind=icon}
Return
An optimized EfficientNetB0 framework with CLAHE-based preprocessing for accurate multi-class chest X-ray classification
.png){kind=icon}
OA
AI
DOI：10.1038/s41598-026-42492-1.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Chest radiography remains an essential diagnostic tool for thoracic diseases, yet interpreting overlapping anatomical structures is particularly challenging when multiple pathologies co-occur a common clinical scenario often oversimplified in deep learning approaches. This study presents an optimized EfficientNetB0 framework designed explicitly for multi-label classification of chest X-rays using the NIH dataset, integrating CLAHE-based contrast enhancement, strategic class balancing, and a comparative transfer learning strategy that preserves the dataset’s inherent multi-label complexity. The proposed model achieved superior diagnostic performance with a macro-average AUC of 0.906 and recall of 0.824, outperforming DenseNet121 and MobileNetV2, and demonstrated strong per-class discrimination, especially for Pneumonia (AUC = 0.950) and Cardiomegaly (AUC = 0.946). These results confirm that the framework effectively balances learning capacity and generalization in a realistic multi-label clinical setting, offering a robust, interpretable solution suitable for computer-aided diagnosis where accurate detection of co-occurring thoracic pathologies is critical.
Keywords:
Computational biology and bioinformatics
Diseases
Health care
Mathematics and computing
Medical research
Chest X-ray classification
EfficientNetB0
CLAHE preprocessing
Transfer learning
Thoracic pathology detection
Science
Humanities and Social Sciences
multidisciplinary
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.9
Papers:
28.2W
Citations:
83.5W
Organization
Cited Papers
ShareSaveHow artificial intelligence improves radiological interpretation in suspected pulmonary embolism
OAAI
OAAIShareSaveDiagnostic Case-Control versus Diagnostic Cohort Studies for Clinical Validation of Artificial Intelligence Algorithm Performance.png)
RADIOLOGY
RADIOLOGYIF15.2
PREAI
ShareSaveDevelopment and Validation of a Deep Learning-Based Automated Detection Algorithm for Major Thoracic Diseases on Chest RadiographsJAMA NETWORK OPENOAAI
JAMA NETWORK OPENIF9.7
OAAIShareSaveE-RespiNet: An LLM-ELECTRA driven triple-stream CNN with feature fusion for asthma classificationPLOS ONE
PLOS ONEIF2.6
PREAI
ShareSaveShareSaveShareSaveShareSave
View more