Non-parametric Iterative Model Constraint Graph min-cut for Automatic Kidney Segmentation

Abstract

We present a new non-parametric model constraint graph min-cut algorithm for automatic kidney segmentation in CT images. The segmentation is formulated as a maximum a-posteriori estimation of a model-driven Markov random field. A non-parametric hybrid shape and intensity model is treated as a latent variable in the energy functional. The latent model and labeling map that minimize the energy functional are then simultaneously computed with an expectation maximization approach. The main advantages of our method are that it does not assume a fixed parametric prior model, which is subjective to inter-patient variability and registration errors, and that it combines both the model and the image information into a unified graph min-cut based segmentation framework. We evaluated our method on 20 kidneys from 10 CT datasets with and without contrast agent for which ground-truth segmentations were generated by averaging three manual segmentations. Our method yields an average volumetric overlap error of 10.95%, and average symmetric surface distance of 0.79mm. These results indicate that our method is accurate and robust for kidney segmentation.

Anatomical Structures Segmentation by Spherical 3D Ray Casting and Gradient Domain Editing

“…3 shows a representative example. These results are comparable to previously reported methods [11,12,13,14] without their underlying assumptions and with a significant improvement in the running time.…”

A shape prior-based MRF model for 3D masseter muscle segmentation

“…Voxels inside the contour incur 0 penalty to belong to the foreground. Freiman et al 4 also creates a probability map by registering binary image segmentations where as our probability map is created from the unsigned distance map of the template shape's contour in 3D. The smootness term V S pq (z p , z q ) is similar to that of Freedman and Zhang.…”

“…[2][3][4][5][6][7][8][9][10][11] It is, however, very difficult to incorporate prior shape knowledge into graph-cut based approaches. The approaches of Slabaugh and Unal 6 and Zhu-Jacquot, 8 tried to spatially constrain the graph-cut segmentation by incorporating parametric shape information.…”

Effective Kidney Segmentation Using Gradient Based Approach in Abdominal CT Images

“…However, kidney image segmentation is a challenging task. The main factors are unclear borders between the kidneys, the liver and the spleen, image acquisition artifacts, image noise, and various pathologies, such as tumours and nephrolithiasis [5].…”