Published Paper Details:

Early detection and accurate staging are critical to successful treatment of colon cancer, which is one of the top causes of cancer-related mortality globally. In the existing system, statistical features are used to classify cancer using supervised learning methods. However, recent advancements in deep learning have shown significant promise for improving classification accuracy. Research is being carried out to compare custom convolutional neural networks (CNNs) with pre-trained CNN models. We evaluated various deep learning models to identify the best model for classifying colon cancer. A publicly available dataset of histopathological images of colon cancer will be used to train and validate this custom CNN model. Performance metrics such as accuracy, sensitivity, specificity, and F1-score were used to assess the proposed CNN model. The results showed that the custom CNN model outperformed the pre-trained models with an accuracy of 93.6%, sensitivity of 92.7%, specificity of 94.5%, and F1-score of 0.916. Therefore, the proposed custom CNN model can be considered as a promising approach for colon cancer classification using histopathological images. By improving colon cancer diagnosis accuracy and developing an efficient computer-aided diagnosis system, this study will assist in improving colon cancer diagnosis accuracy.