Automatic Liver Segmentation of Contrast Enhanced CT Images Based on Histogram Processing.
ABSTRACT Pixel values of contrast enhanced computed tomography (CE-CT) images are randomly changed. Also, the middle liver part has
a problem to segregate the liver structure because of similar gray-level values of neighboring organs in the abdomen. In this
paper, an automatic liver segmentation method using histogram processing is proposed for overcoming randomness of CE-CT images
and removing other abdominal organs. Forty CE-CT slices of ten patients were selected to evaluate the proposed method. As
the evaluation measure, the normalized average area and area error rate were used. From the results of experiments, liver
segmentation using histogram process has similar performance as the manual method by medical doctor.
- SourceAvailable from: Marius Danciu
[Show abstract] [Hide abstract]
- "Different classes of automatic CT liver segmentation methods are reported. The simplest category involves threshold  or multi-threshold  segmentation applied on the intensity only. The segmentation accuracy achieved by this strategy is rather low, as the intensities inside the liver are neither always homogeneous, neither perfectly discriminative between the liver and other organs. "
ABSTRACT: Medical volume segmentation in various imaging modalities using real 3D approaches (in contrast to sliceby-slice segmentation) represents an actual trend. The increase in the acquisition resolution leads to large amount of data, requiring solutions to reduce the dimensionality of the segmentation problem. In this context, the real-time interaction with the large medical data volume represents another milestone. This paper addresses the twofold problem of the 3D segmentation applied to large data sets and also describes an intuitive neuro-fuzzy trained interaction method. We present a new hybrid semisupervised 3D segmentation, for liver volumes obtained from computer tomography scans. This is a challenging medical volume segmentation task, due to the acquisition and inter-patient variability of the liver parenchyma. The proposed solution combines a learning-based segmentation stage (employing 3D discrete cosine transform and a probabilistic support vector machine classifier) with a post-processing stage (automatic and manual segmentation refinement). Optionally, an optimization of the segmentation can be achieved by level sets, using as initialization the segmentation provided by the learning-based solution. The supervised segmentation is applied on elementary cubes in which the CT volume is decomposed by tilling, thus ensuring a significant reduction of the data to be classified by the support vector machine into liver/not liver. On real volumes, the proposed approach provides good segmentation accuracy, with a significant reduction in the computational complexity.Radioengineering 04/2013; 22(1):100-113. · 0.65 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: Computed Tomography (CT) images are widely used for diagnosis of liver diseases and volume measurement for liver surgery and transplantation. Segmentation of liver and lesion is regarded as a major primary step in computer-aided diagnosis of liver diseases. Lesion alone cannot be segmented automatically from the abdominal CT image since there are tissues external to the liver with similar intensity to the lesions. Therefore, it is necessary to segment the liver first so that lesion can then be segmented accurately from it. In this paper, an approach for automatic and effective segmentation of liver and lesion from CT images needed for computer-aided diagnosis of liver is proposed. The method uses confidence connected region growing facilitated by preprocessing and postprocessing functions for automatic segmentation of liver and Alternative Fuzzy C-Means clustering for lesion segmentation. The algorithm is quantitatively evaluated by comparing automatic segmentation results to the manual segmentation results based on volume measurement error, figure of merit, spatial overlap, false positive error, false negative error, and visual overlap. KeywordsLiver segmentation–Lesion segmentation–Volume measurement-confidence connected region growing–Alternative FCMSignal Image and Video Processing 01/2011; 7(1):1-10. DOI:10.1007/s11760-011-0223-y · 1.43 Impact Factor