Classification of Gastrointestinal Disease Images Through Residual Learning Algorithm and Comparative Analysis of Deep Learning Architectures

This research aims to develop an advanced system for detecting gastrointestinal diseases from medical images using deep learning techniques, specifically the ResNet50 architecture. Gastrointestinal conditions are often diagnosed through the examination of endoscopic images, a process that can be prone to human error and time-consuming. To address this, the study proposes a fully automated system that leverages ResNet50, a convolutional neural network (CNN) known for its deep residual learning capabilities. The system is compared with other well-established CNN architectures, including VGG16 and MobileNetv2, to assess performance in terms of accuracy, precision, recall, and computational efficiency. Experimental results demonstrate that ResNet50 significantly outperforms VGG16 and MobileNetv2 in accurately identifying various gastrointestinal diseases. This research highlights the potential of deep learning in enhancing diagnostic processes, offering a more reliable and efficient tool for clinical use. The findings suggest that ResNet50 could potentially revolutionize the early detection of gastrointestinal diseases, improving patient outcomes and reducing diagnostic time in medical practices.