<![CDATA[The utilization of technology to build models that can classify pneumonia medical images automatically is needed for early diagnosis. This study aims to implement a Convolutional Neural Network (CNN) model with ResNet50V2 architecture that has been proven to have high accuracy in medical image classification. The model adopts a deep and efficient residual architecture, which facilitates deeper training of the model without suffering from vanishing gradient problem. This study went through four main stages: pneumonia and normal X-ray image data collection, data pre-processing (including set division, transformation, and augmentation), modeling using CNN with hyperparameter tuning, and model evaluation. Evaluation was performed using accuracy, F1-score, and Confusion Matrix metrics. The CNN model with ResNet50V2 as the backbone achieved 97% accuracy, showing excellent performance in differentiating between pneumonia and normal despite a small amount of misclassification. Although this model showed impressive results, challenges such as potential misclassification in cases with unclear or ambiguous images remain. Compared to previous approaches, this model offers advantages in accuracy and processing efficiency thanks to the use of a deeper and more sophisticated ResNet50V2. These advantages are expected to improve the precision of automated diagnosis in future medical applications.]]>
Copyrights © 2025
