Figure - available from: BMC Medical Imaging
This content is subject to copyright. Terms and conditions apply.
Source publication
Purpose
Development and assessment the deep learning weakly supervised algorithm for the classification and detection pneumonia via X-ray.
Methods
This retrospective study analyzed two publicly available dataset that contain X-ray images of pneumonia cases and normal cases. The first dataset from Guangzhou Women and Children’s Medical Center. It c...
Citations
... Studies (11,(16)(17)(18) highlighted the limitations imposed by the scarcity of datasets. A weakly supervised method was used in (19) to identify pneumonia cases, and lightweight DenseNet-121 was utilized in (20) to extract features. With limited datasets, Xception and DenseNet121 achieved the highest accuracy for pneumonia diagnosis (13,21) . ...
Objectives: To create a deep learning system for pneumonia detection that is both effective and gradually optimized. Methods: A customized CNN is used with an incremental approach for pneumonia classification and detection. Starting with a baseline model, hypertuning parameters such as four convolution layers with filters of 16, 32, 64, and 128 sizes, a dropout layer with values of 0.3, 0.5, and 0.7, four batch normalization layers, and an Adam optimizer are added. A total images of 5,863 for training, 624 for testing, and 16 for validation from the Paul Mooney dataset were used to test the suggested model. Findings: The study recorded a test accuracy of 94% for the customized CNN followed by ResNet50 at 79.9%, VGG16 at 90.14%, VGG19 at 82.21%, InceptionV3 at 74.51%, and EfficientNetB1 at 83.17%. Recall of 98.20%, accuracy of 85.55%, AUC of 93.52%, and F1_score of 92.45% obtained were all fairly excellent for the customized CNN. 15 epochs, a learning rate of 0.0001, callbacks with a patience of 3, and an early stopping feature were applied to the training model. Novelty: Five convolution blocks, two separable convolution layers, one batch normalization layer, one maxpooling layer, and a fully connected layer with an Adam optimizer were all included in the customized CNN that was developed to identify and categorize pneumonia. With Explainable AI's GradCAM technology, pneumonia-infected areas on chest X-rays were highlighted and the sickness was seen. Keywords: Customized CNN, VGG16, VGG19, ResNet50, Explainable AI
Pneumonia is a form of acute respiratory infection that affects the lungs. The lungs are made up of small sacs called alveoli, which is normally fill with air in a healthy person, but filled with pus and fluid in an individual with pneumonia thereby reduces oxygen intake and making breathing difficult Pneumonia is a fatal and leading cause of morbidity and mortality worldwide, especially among children five years and below; and the elderly 65 years and above especially those with weakened immune systems. Pneumonia can be caused by bacteria, virus, and fungi, and the severity ranges from mild to severe depending on the causative agent and the duration of the infection. Early diagnosis, particularly knowing the severity level of Pneumonia gains a paramount importance for saving lives. Medical diagnosis using artificial intelligence (AI) systems, is currently an active research area in medicine widely used in biomedical systems. Deep learning, a subset of Artificial intelligence provides a powerful tool that assist medical experts to analyze, model, and make sense of complex clinical image data across a broad range of medical applications. This paper proposes a deep learning technique of classifying X-ray images of pneumonia patients into their severity classes.
