Pneumonia Detection Using Human CT-Scan Images

Abstract

Pneumonia is a significant global health issue, causing substantial morbidity and mortality. Early and accurate diagnosis of pneumonia is crucial for effective treatment and patient management. The model is trained on a large dataset of labeled chest X-ray images, consisting of both pneumonia-positive and pneumonia-negative cases. To train the MobileNetV2 model, a transfer learning approach is adopted, where the pre-trained weights from a large-scale dataset are used as a starting point. Fine-tuning is performed by training the model on the pneumonia dataset using a combination of deep learning techniques, including data augmentation and regularization, to improve generalization and reduce overfitting. To evaluate the performance of the proposed pneumonia detection system, extensive experiments are conducted on an independent test dataset. The model's performance is assessed using various evaluation metrics, including accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). The results demonstrate the efficacy of the MobileNetV2 model in accurately detecting pneumonia from chest X-ray images, showcasing its potential for use in real-world clinical settings. In conclusion, this study presents a pneumonia detection system based on the MobileNetV2 model, offering a practical and efficient solution for automated pneumonia diagnosis. The proposed model's high accuracy and suitability for deployment on mobile devices make it a valuable tool for healthcare professionals, enabling timely and accurate diagnosis of pneumonia, thereby facilitating prompt treatment, and improving patient outcomes.”