Al Driven Deep CNN Framework for colorectal Disease Diagnosis for Histopathological image datasets - (multi-class colorectal diseases diagnoses Explainable Grad (AMMTT))

The proposed deep learning model was trained and tested using histopathological image datasets of Colorectal cancer. The CNN model successfully extracted important features from the images and performed multi-class classification with high accuracy.   The experimental results show that the proposed system improves classification performance compared to traditional methods. The Grad-AMM-TT technique also generated clear attention maps that highlight the important regions in the images. These visual explanations help medical experts understand the model’s decision process.   Overall, the results demonstrate that the proposed system can support pathologists by providing faster and more reliable disease diagnosis.

1.      Alex Krizhevsky,Ilya Sutskever, and Geoffrey Hinton(2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems.   2.      Karen Simonyan and Andrew Zisserman (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition.     3.      Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun (2016). Deep Residual Learning for Image Recognition. . 4.      Ramprasaath R. Selvaraju et al. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization.   5.      World Health Organization (2023). Cancer and Colorectal Disease Global Statistics Report.     6.      National Institutes of Health (2022). Histopathological Image Analysis Using Deep Learning.