Portal de Periódicos da CAPES

A Multiorgan Segmentation Model for CT Volumes via Full Convolution-Deconvolution Network

2017; Hindawi Publishing Corporation; Volume: 2017; Linguagem: Inglês

10.1155/2017/6941306

2314-6141

Yangzi Yang, Huiyan Jiang, Qingjiao Sun,

AI in cancer detection

We propose a model with two-stage process for abdominal segmentation on CT volumes. First, in order to capture the details of organs, a full convolution-deconvolution network (FCN-DecNet) is constructed with multiple new unpooling, deconvolutional, and fusion layers. Then, we optimize the coarse segmentation results of FCN-DecNet by multiscale weights probabilistic atlas (MS-PA), which uses spatial and intensity characteristic of atlases. Our coarse-fine model takes advantage of intersubject variability, spatial location, and gray information of CT volumes to minimize the error of segmentation. Finally, using our model, we extract liver, spleen, and kidney with Dice index of 90.1 ± 1%, 89.0 ± 1.6%, and 89.0 ± 1.3%, respectively.