Branch: master
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
50 lines (26 sloc) 1.79 KB


medical image segmentation: a survey medical image segmentation

Three architectures achieve good performance:

encoder-decoder network

structure: input-conv-deconv-segmentation

Implementation: ultrasound-nerve-segmentation

propose skip-connect from encoder to decoder.

1. propose dice-coeff loss which is specially designed for medical image segmentation. 2. illustrate the idea of 3D convolution on a images volume.

Other useful paper:

have a similar skip-connect structure

, symmetric upsampling. not as powerful as u-net.

<DHSnet: Deep Hierarchical Saliency Network for Saliency Object Detection> similar to medical image (predict single probability map)

forward network

structure: input-conv-upsampling-refinement

Implementation: medical-image-segmentation

<Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs> achieves best performance on PASCAL VOC segmentation challenge

similar to medical image (predict single probability map)

<DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation> learning to predict coutour map and segmentation map.

multitask network cascades

SDS first propose the task:

Implementation: rpn_drn_new

defeat segmentation-only encoder-decoder network on COCO segmentation challenge


Dilated convolution helps reduce computation