Automatic 3D liver location and segmentation via convolutional neural network and graph cut

• Published in: International journal for computer assisted radiology and surgery Vol. 12; no. 2; pp. 171 - 182
• Main Authors: Lu, Fang, Wu, Fa, Hu, Peijun, Peng, Zhiyi, Kong, Dexing
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.02.2017; Springer Nature B.V
• Subjects: Abdomen; Algorithms; Artificial neural networks; Computed tomography; Computer Imaging; Computer Science; Databases, Factual; Datasets; Health Informatics; Humans; Imaging; Imaging, Three-Dimensional - methods; Liver; Liver - diagnostic imaging; Machine learning; Medicine; Medicine & Public Health; Neural Networks (Computer); Organ Size; Original Article; Pattern Recognition and Graphics; Radiation therapy; Radiology; Statistical analysis; Surgery; Tomography, X-Ray Computed - methods; Vision; Volume measurement; 3D convolution neural network; CT images; Liver segmentation; Graph cut
• ISSN: 1861-6410; 1861-6429; 1861-6429
• DOI: 10.1007/s11548-016-1467-3

Purpose Segmentation of the liver from abdominal computed tomography (CT) images is an essential step in some computer-assisted clinical interventions, such as surgery planning for living donor liver transplant, radiotherapy and volume measurement. In this work, we develop a deep learning algorithm with graph cut refinement to automatically segment the liver in CT scans. Methods The proposed method consists of two main steps: (i) simultaneously liver detection and probabilistic segmentation using 3D convolutional neural network; (ii) accuracy refinement of the initial segmentation with graph cut and the previously learned probability map. Results The proposed approach was validated on forty CT volumes taken from two public databases MICCAI-Sliver07 and 3Dircadb1. For the MICCAI-Sliver07 test dataset, the calculated mean ratios of volumetric overlap error (VOE), relative volume difference (RVD), average symmetric surface distance (ASD), root-mean-square symmetric surface distance (RMSD) and maximum symmetric surface distance (MSD) are 5.9, 2.7 %, 0.91, 1.88 and 18.94 mm, respectively. For the 3Dircadb1 dataset, the calculated mean ratios of VOE, RVD, ASD, RMSD and MSD are 9.36, 0.97 %, 1.89, 4.15 and 33.14 mm, respectively. Conclusions The proposed method is fully automatic without any user interaction. Quantitative results reveal that the proposed approach is efficient and accurate for hepatic volume estimation in a clinical setup. The high correlation between the automatic and manual references shows that the proposed method can be good enough to replace the time-consuming and nonreproducible manual segmentation method.