Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges

前言：
该篇文章较为全面但稍偏简单的介绍医学图像分割的常见数据集、各种神经网络，以及常见的训练技巧等问题。
一、重点摘录

1. 2.5D approaches are inspired by the fact that 2.5D has the richer spatial information of neighboing pixels wiht less computational costs than 3D.
2. The 3D network is trained to predict the label of a central voxel according to the content fo surrounding 3D patches.
3. To address the deimensionality issue and reduce the processing time, Dou et al. in [23] proposed to utilize a set of 3D kernels that shared the weights spatially, which helped to reduce the number of parameters.
4. The authors in [66] applied a hierarchical coarse-to-fine strategy that significantly improved the segmentation results of small organs.
5. Focal FCN
   Zhou et al. [93] proposed to apply the focal loss on the FCN to reduce the number of false positives occurred due to the unbalanced ration of backgroun