Sparsely Connected Convolutional Layers in CNNs for Liver Segmentation in CT
Convolutional neural networks are currently the best working solution for automatic liver segmentation. Generally, each convolutional layer processes all feature maps from the previous layer. We show that the introduction of sparsely connected convolutional layers into the U-Net architecture can benefit the quality of liver segmentation and results in the increase of the dice coeffcient by 0:32% and a reduction of the mean surface distance by 3:84 mm on the LiTS data. Evaluation on the IRCAD data set with the application of post-processing showed a 0:70% higher Dice coeffcient and a 0:26 mm lower mean surface distance.
Unable to display preview. Download preview PDF.
- 1.Christ P, Ettlinger F, Lipkova J, et al.. LiTS: liver tumor segmentation challenge; 2017. Available from: http://www.lits-challenge.com/.
- 2.Han X. Automatic liver lesion segmentation using a deep convolutional neural network method. CoRR. 2017;abs/1704.07239.Google Scholar
- 3.Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Proc MICCAI. 2015; p. 234–241.Google Scholar
- 4.Changpinyo S, Sandler M, Zhmoginov A. The power of sparsity in convolutional neural networks. CoRR. 2017;abs/1702.06257.Google Scholar
- 5.Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. Proc CVPR. 2015; p. 1–9.Google Scholar
- 6.3D-IRCADb-01; 2018. Available from: https://www.ircad.fr/research/3d-ircadb-01/.
- 7.Salehi SSM, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks. Mach Learn Med Imaging. 2017; p. 379–387.Google Scholar