Segmentation and classification of CT renal images using deep networks

Abstract

The study of deep learning (LeCun et al. in Nature 521(7553):436, 2015 [1]) models, in particular, the convolutional neural networks (CNN), is playing a key role for various applications in medical domain since last decade. It has successfully demonstrated interesting results with higher accuracy which motivates sophisticated diagnosis tools in the Healthcare domain. We have done a study on using CNN models such as U-net and Alexnet on renal dataset for segmentation and classification of renal images. Data preprocessing on kidney images has been carried out using U-net architecture (Ronneberger et al. in U-net: convolutional networks for biomedical image segmentation. Springer, Berlin, pp. 234–241, 2015 [2]). A detailed study on fine tuning the hyper parameters that governs the model performance and test accuracy has been carried out. We achieved a dice coefficient of 83% in creating masks for renal data using U-net. We performed experiments on AlexNet and the best accuracy achieved is 94.75%. Finally, we have visualized the convolutional layers using saliency maps.