Segmentation of liver tumor via nonlocal active contours

B. Chen (1, 2, 3) , Y. Chen (2, 1, 3) , G. Yang (1, 2, 3) , J. Meng (1, 2, 3) , R. Zeng (3) , L Luo (2, 1, 3)

1 CRIBS - Centre de Recherche en Information Biomédicale sino-français
2 Key Laboratory of Computer Network and Information Integration
3 LIST - Laboratory of Image Science and Technology [Nanjing]

To reduce the manual labor time and provide the accuracy of liver tumor segmentation in the treatment planning of radiofrequency ablation (RFA), a novel method for liver tumor image segmentation by nonlocal active contours is proposed in this paper. A multi Gabor feature map of the liver tumor image is computed to describe the homogeneity of patches in a nonlocal way, and the nonlocal comparisons between pairs of patches are used to calculate the active contour energy. The whole energy function is minimized via a level set method to give the final segmentation. The experimental results indicate that the proposed method leads to good liver tumor segmentation with a good robustness to initialization condition. Experiment results show the proposed method can provide segmentation close to manual results, with the mean overlap error (OE) less than 23.86%

Keywords: tumors; tumours; Active contours; Computed Tomography; error analysis; Gabor filters; Hidden Markov models; image segmentation; Liver; liver tumor segmentation; Manuals; mean overlap error; medical image processing; multi Gabor feature map; nonlocal active contours; patient treatment; radiofrequency ablation; RFA; treatment planning

Domains: Life Sciences [q-bio]; Bioengineering

B. Chen, Y. Chen, G. Yang, J. Meng, R. Zeng, et al.. Segmentation of liver tumor via nonlocal active contours. 2015 IEEE International Conference on Image Processing (ICIP), 2015, Quebec City, Canada. pp.3745--3748, ⟨10.1109/ICIP.2015.7351504⟩. ⟨hal-01320722⟩