Enhancement of Diagnostic Accuracy of Colon Diseases Using Multi-Class Classification Technique and Endoscopic Images

Colon diseases are a significant health concern worldwide, with conditions such as polyps, esophagitis, and ulcerative diseases posing substantial risks to patients. Early and accurate diagnosis is crucial for effective treatment and prevention of complications. In recent years, deep learning techniques have shown promising results in the field of medical image analysis, offering the potential to enhance the diagnostic process. In this research, a transfer learning-based Inception V3model is proposed for the multi-classification of colon disease using endoscopic images. This study focuses on the classification of four major classes: Normal, Polyps, Esophagitis, and Ulcerative diseases. The dataset used for this research comprises a diverse collection of endoscopic images obtained from online platforms. The training process involves the optimization of hyperparameters such as optimizers namely Adam and Adadelta, with batch size 32 and 100 epochs to enhance the robustness of the model. The proposed classification system has obtained the highest value of validation accuracy as 93.65% on the Adam optimizer. The proposed system holds great promise for assisting clinicians in the early diagnosis and classification of colon diseases, thereby facilitating timely intervention.