Classification of Histopathological Images of Colorectal Cancer with Deep Learning Models: A Comparative Study

Colorectal cancer is the third most common cancer in men and women worldwide. In addition, the incidence of cancer has been increasing over the years. Therefore, early diagnosis and treatment save lives. The advancement of artificial intelligence-based systems daily makes important contributions to the health field as in every field. This study aims to classify histopathological images of colorectal cancer. Accordingly, Inception-ResNet-v2, Inception-v4 and improved Inception-v4 models were trained and tested on the colorectal cancer dataset. When the models are compared, the improved Inception-v4 model with an accuracy of 0.9327 outperforms the other two models.