Related Experiment Videos
Automatic segmentation of liver structure in CT images
1Kurt Rossmann Laboratories for Radiologic Image Research, Department of Radiology, University of Chicago, Illinois 60637.
Medical Physics
|January 1, 1993
Summary
A new method automatically segments liver structures from CT scans using image processing and morphological data. This technique accurately extracts liver boundaries, aiding surgical planning and disease detection.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Surgical Planning
Background:
- Accurate liver segmentation from CT scans is crucial for medical applications like liver transplantation and pathology detection.
- Existing methods may lack automation or precision in complex anatomical regions.
Purpose of the Study:
- To develop an automated method for liver structure extraction from abdominal CT scans.
- To improve the accuracy and efficiency of liver segmentation for clinical use.
Main Methods:
- A novel image-processing technique utilizing a priori liver morphology information.
- Sequential, slice-by-slice segmentation incorporating gray-level thresholding, Gaussian smoothing, and connectivity tracking.
- Boundary refinement using mathematical morphology and B-splines.
Main Results:
- The automated method successfully segmented liver structures from CT images.
- Computer-determined liver boundaries showed agreement with radiologist annotations.
- Calculated liver areas were within a 10% margin of error compared to manual segmentation.
Conclusions:
- The developed method provides accurate and automated liver segmentation from CT scans.
- This technique has potential applications in surgical planning and pathological state detection.
- The approach demonstrates reliable performance in defining liver boundaries.