Research

We have developed deep learning methods for segmenting brain tumors, brain structures, and kidneys. To segment brain tumors in MRI data, we have developed a deep learning model by fully convolutional neural networks (FCNNs) and Conditional Random Fields (CRFs) in a unified framework to obtain segmentation results with appearance and spatial consistency [12]. To obtain accurate fine-grained segmentation of brain structures in MRI data efficiently, we have developed an end-to-end Feature-Fused Context-Encoding Network [11]. To robustly segment kidneys in ultrasound images, we have developed subsequent boundary distance regression and pixel classification networks to segment the kidneys automatically [13].

Transfer learning network, and subsequent boundary distance regression and pixel classification networks for fully automatic kidney segmentation in US images. The boundary detection network (Bnet) is trained using a distance loss function and the end-to-end subsequent segmentation network is trained by combining the distance loss function and a softmax loss function.