Renal Segmentation Algorithm Combined Low-level Features with Deep Coding Feature
Kaijian Xia, Zhaoyang Liu · 2018
In the field of medical imaging research, renal segmentation is an important task which is tedious and error-prone when performed manually. Deep learning methods have been successfully applied to feature learning in medical applications. In this paper, We focused on the high accuracy of the classification task because of its effect on the accuracy of a better segmentation, and a Renal Segmentation Algorithm Combined Low-level Features with Deep Coding Feature from medicine images is proposed. Firstly, we use the advantage of Stacked auto-encoder networks to automatically learn the high-level features that capture the structured information and semantic context in the image. Several low-level features are extracted, which can effectively capture contrast and spatial information in the renal regions, and incorporated to compensate with the learned high-level features at the output of the very last fully connected layer. The concatenated feature vector is further fed into a Least squares SVM detector with Morlwet kernel to obtain classification results. We trained the deep network on medicine data set and experimentally shows that our proposed method has high classification accuracy and can speed up the clinical task to segment the renal.