<![CDATA[Pneumonia is one of the leading causes of death from respiratory tract infections worldwide. Early detection and identification of the causative pathogen are crucial for determining appropriate treatment. This study aims to develop a Convolutional Neural Network (CNN) model based on Multi-Task Learning (MTL) to simultaneously detect pneumonia and classify the type of pathogen through chest X-ray images. The model architecture uses a shared convolutional layer for feature extraction, which then branches into two classification paths. The model was trained using a dataset of X-ray images labeled with disease status and pathogen type, with two loss functions optimized simultaneously. Based on the training process and model architecture design, the estimated accuracy achieved is approximately 92% for pneumonia detection and 89% for pathogen type classification. These results indicate that the CNN-MTL approach is effective and efficient in simultaneously addressing two clinical tasks. The proposed model has the potential to be applied as a clinical decision support system, particularly in healthcare facilities with limited resources.]]>
Copyrights © 2025
