Segmentation简记-Joint shape learning and segmentation for medical images using a minimalistic deep network
创新点
1.In this paper, we propose a multi-task learning framework with the main aim of exploiting structural and spatial information along with the class information.
总结
Network Architecture
The fi rst component of the network is similar to U-Net. The second component consists of parallel convolutional blocks for multi-task learning.
the top path in second component is the classi cation branch responsible for estimating the segmentation mask while the bottom path is used for the auxiliary task and is to estimate either the contour map as a classi cation task or the distance map as a regression task. For mask and contour estimation, 3x3 convolution is applied to get 2 feature maps while for distance map, the same convolution is applied to get 1 feature map.
Capturing Structural Information
We harness the spatial information that is implicitly present in ground truth segmentation masks and we achieve the same in two ways: i) using the contours obtained from the segmentation map and ii) using the euclidean distance transforms computed from the segmentation maps.