3D Randomized Connection Network with Graph-based Label Inference
This work addresses brain image segmentation for medical imaging applications, but it appears incremental as it builds on existing techniques like convolutional LSTM and 3D convolution.
The paper tackled brain MR image segmentation by proposing a 3D deep learning network with randomized connections and a graph-based label inference method, achieving competitive performance compared to state-of-the-art methods on two public databases.
In this paper, a novel 3D deep learning network is proposed for brain MR image segmentation with randomized connection, which can decrease the dependency between layers and increase the network capacity. The convolutional LSTM and 3D convolution are employed as network units to capture the long-term and short-term 3D properties respectively. To assemble these two kinds of spatial-temporal information and refine the deep learning outcomes, we further introduce an efficient graph-based node selection and label inference method. Experiments have been carried out on two publicly available databases and results demonstrate that the proposed method can obtain competitive performances as compared with other state-of-the-art methods.