Related Experiment Video
Updated: Jun 7, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Image-based deep learning in diagnosing mycoplasma pneumonia on pediatric chest X-rays
Xing-Hao Lan1, Yun-Xu Zhang2, Wei-Hua Yuan3
1Radiology department, Children's Hospital of Soochow University, Suzhou, 215025, China.
Background:
Correctly diagnosing and accurately distinguishing mycoplasma pneumonia in children has consistently posed a challenge in clinical practice, as it can directly impact the prognosis of affected children. To address this issue, we analyzed chest X-rays (CXR) using various deep learning models to diagnose pediatric mycoplasma pneumonia.
Methods:
We collected 578 cases of children with mycoplasma infection and 191 cases of children with virus infection, with available CXR sets. Three deep convolutional neural networks (ResNet50, DenseNet121, and EfficientNetv2-S) were used to distinguish mycoplasma pneumonia from viral pneumonia based on CXR. Accuracy, area under the curve (AUC), sensitivity, and specificity were used to evaluate the performance of the model. Visualization was also achieved through the use of Class Activation Mapping (CAM), providing more transparent and interpretable classification results.
Results:
Of the three models evaluated, ResNet50 outperformed the others. Pretrained with the ZhangLabData dataset, the ResNet50 model achieved 80.00% accuracy in the validation set. The model also showed robustness in two test sets, with accuracy of 82.65 and 83.27%, and AUC values of 0.822 and 0.758. In the test results using ImageNet pre-training weights, the accuracy of the ResNet50 model in the validation set was 80.00%; the accuracy in the two test sets was 81.63 and 62.91%; and the corresponding AUC values were 0.851 and 0.776. The sensitivity values were 0.884 and 0.595, and the specificity values were 0.655 and 0.814.
Conclusions:
This study demonstrates that deep convolutional networks utilizing transfer learning are effective in detecting mycoplasma pneumonia based on chest X-rays (CXR). This suggests that, in the near future, such computer-aided detection approaches can be employed for the early screening of pneumonia pathogens. This has significant clinical implications for the rapid diagnosis and appropriate medical intervention of pneumonia, potentially enhancing the prognosis for affected children.
Insights
Deep learning models effectively diagnosed pediatric mycoplasma pneumonia using chest X-rays (CXR). The ResNet50 model showed high accuracy, aiding in early pathogen screening and improving patient prognosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Pediatric Pulmonology
Background:
- Diagnosing pediatric mycoplasma pneumonia is clinically challenging and impacts patient outcomes.
- Chest X-rays (CXR) are crucial for pneumonia diagnosis.
- Developing accurate diagnostic tools for pediatric pneumonia is essential.
Purpose of the Study:
- To evaluate deep learning models for diagnosing pediatric mycoplasma pneumonia using CXR.
- To compare the performance of different convolutional neural networks (CNNs) for this task.
- To assess the potential of AI in distinguishing mycoplasma pneumonia from viral pneumonia.
Main Methods:
- Collected CXR data from 578 children with mycoplasma infection and 191 with viral infection.
- Applied three deep convolutional neural networks (ResNet50, DenseNet121, EfficientNetv2-S) for classification.
- Evaluated model performance using accuracy, AUC, sensitivity, and specificity, with Class Activation Mapping (CAM) for interpretability.
Main Results:
- ResNet50 demonstrated superior performance among the evaluated models.
- ResNet50 achieved up to 83.27% accuracy and 0.822 AUC on test sets when pre-trained with ZhangLabData.
- Performance varied with different pre-training datasets (ZhangLabData vs. ImageNet), highlighting the impact of training data.
Conclusions:
- Deep convolutional networks with transfer learning effectively detect mycoplasma pneumonia from CXR.
- AI-driven computer-aided detection shows promise for early screening of pneumonia pathogens.
- This technology has significant clinical implications for rapid diagnosis and improved pediatric pneumonia prognosis.
