Fully automatic anatomical, pathological, and functional segmentation from CT scans for hepatic surgery
read more
Citations
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes
Statistical shape models for 3D medical image segmentation: a review.
Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets
The Liver Tumor Segmentation Benchmark (LiTS)
Analysis of vasculature for liver surgical planning
References
Numerical recipes in C
Snakes : Active Contour Models
A survey of image registration techniques
Automatic detection of brain contours in MRI data sets
Related Papers (5)
Automatic liver segmentation technique for three-dimensional visualization of CT data.
Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets
Frequently Asked Questions (9)
Q2. What is the method for determining the distribution of a liver?
The fitting of distribution onto the gray level histogram is performed by the Levenberg and Marquardt’s method21, which minimizes a least square criterion and which is currently used for other organs in many articles22,23,24,25.
Q3. What is the first step in the correction of drawbacks?
The correction of these drawbacks consists in reducing the skeleton by smoothing lines, rejecting barbules and fusing neighboring junction points.
Q4. What is the reason why the authors chose to modify their method?
The authors chose to modify their method by considering that the distributions of the same three tissue classes follow a normal law, these distributions being then used to consider thresholds allowing segmentation for each structure.
Q5. What is the morphological constraint for the merging system?
The authors chose to define a new merging system that uses anatomical knowledge translated into topological,geometrical and morphological constraints.
Q6. How do the authors simplify the vascular network?
The authors first simplify the vascular network by computing its skeleton, as in Zahlten et al.12,13, but with theMalandain and Bertrand method27,28 that provides a skeleton geometrically and topologically much more precise than the region-growing method.
Q7. What is the upper limit value of the obtuse angle?
The upper limit value of the obtuse angle obtained has been determined in order to removed connections between portal branches and hepatic vein branches.
Q8. How many units of air, fat tissue, water and bones are known?
The intensity in Hounsfield units of air, fat tissue, water and bones are known and are respectively -1000 HU, -120 HU to -80 HU, 0 HU, and 500 HU to 3000 HU.
Q9. How many slices of hepatic tissue have been obtained?
This study has been performed on a set of 35 CT-scans with slices from 2 mm to 3 mm of thickness, acquired after contrast agent injection at portal phase, from an helical Siemens Somatom 4 plus CT-scan.