Detection of colon cancer using k-means and deep learning algorithms on histopathological images

In this research, a novel approach for classifying colon cancer was developed by employing two convolutional neural network (CNN) models, namely GoogLeNet and AlexNet. This approach involves training CNNs with histopathological images segmented into color clusters using an augmented k-means clustering algorithm, rather than utilizing original-raw images. This method was applied to 20 datasets with distinct structural and characteristic features, derived from larger datasets comprising both original and segmented images. The datasets were used to train and test CNN models. The results indicate that AlexNet, trained with segmented images, showed a 2% to 23% increase in accuracy performance, while GoogLeNet\\\'s accuracy performance improved by 2% to 27%. Notably, the proposed approach yielded higher accuracy with datasets containing non-homogeneous data.