Image Analysing in Hepatology

An image analysis system provides diagnostic decision support for physicians' evaluation of hepatic lesions using MRI, computer tomography (CT) or ultrasound (US) images. This can be carried out on the liver in vivo or on a tissue sample of a liver biopsy.

Combining image analysis algorithms and visualization tools, image analysing provides three dimensional patient liver image data. It further gives segmentation and measurement tools for the visualization and analysis of liver lesions, hepatic vascular structures, as well as liver lobes. This volumetric analysis provides physicians with a visualization aid and offers quantification tools to support their clinical decision making and patient care management.

Optical Analysis of the Liver (in Vivo)

Optical digital analysis of multiphase Multi-Detector CT images of the liver is effective in determining the stage and distribution of liver fibrosis in chronic hepatitis C, especially in patients with homogeneous fibrosis distribution.

In Vitro Image Analysing of Liver Tissue

An automated quantification system (AQS) provides quantitative assessment of liver in liver biopsies based on a classification into six classes depending on its severity and progression.

Another approach is an automatic tissue characterization system, based on color image segmentation to analyze liver tissue images. It first utilizes the intensity to coarsely segment the tissue image and then makes use of the chromatic information to classify the segmented regions into four different tissue classes. Thus, the proposed method includes an unsupervised probabilistic relaxation segmentation process and a supervised Bayes classification process. The method has shown reliable liver tissue classification results from different test sample sets.

Contact us regarding "Image Analysing in Hepatology"
or call Tilo Stolzke at +49 451 400 83 01 directly.

We want to improve!
We welcome any recommendations for articles or other information that are viewed as high value to our users.
Contact us

Tell a
friend!