<![CDATA[Gastroenterology is revolutionized by advancements in artificial intelligence (AI). As the gastrointestinal (GI) tract is consulted, globally 40% of the world's and 18% of the Indian population are affected. AI is a reliable sword for diagnosing issues related to the GI tract. The learning capabilities of deep learning (DL) techniques make it widely helpful in medical investigations. The variety of data available in the medical sector generates the need for an appropriate model for every problem domain. The purpose of this research is to explore the significance of medical image pre-processing and the implementation of pre-trained DL models on endoscopic images for the diagnosis of disease. Convolutional neural network (CNN)-based architectures have robust diagnostic potential for medical images. It can assist physicians as a tool for disease analysis, screening and help in investigating further needs. The paper also provides a comparative performance framework showing CNN architectures and preprocessing techniques for endoscopic images to highlight the key points important for investigating GI tract related diseases. The endoscopic images were trained over VGG-16, ResNet-50 and DenseNet-121, DL models. The result suggests that VGG-16 and ResNet-50 gave promising results with an accuracy maximum of 87.50%.]]>
Copyrights © 2026
