Related Experiment Video
Updated: Jul 16, 2026
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Constructing a probabilistic model for automated liver region segmentation using non-contrast X-ray torso CT images
Xiangrong Zhou1, Teruhiko Kitagawa, Takeshi Hara
1Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University, Gifu 501-1194, Japan. zxr@fjt.info.gifu-u.ac.jp
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|March 16, 2007
Summary
This study introduces a novel probabilistic model for fully-automated liver segmentation in CT scans. The model accurately identifies liver regions using spatial and density probabilities, proving its clinical utility.
Area of Science:
- Medical Imaging
- Radiology
- Computer-Aided Diagnosis
Background:
- Accurate liver segmentation is crucial for medical diagnosis and treatment planning.
- Manual segmentation is time-consuming and prone to inter-observer variability.
- Automated methods are needed to improve efficiency and consistency in liver segmentation.
Purpose of the Study:
- To develop and validate a fully-automated probabilistic model for liver segmentation in non-contrast CT images.
- To assess the model's performance against manually segmented gold standards.
Main Methods:
- A probabilistic model integrating spatial location and density (CT number) probabilities was developed.
- Spatial probability was derived from manually segmented liver regions in a training dataset.
- Density probability was estimated using a Gaussian function.
Main Results:
- The model was trained on 132 CT cases and validated using a leave-one-out cross-validation method.
- Performance evaluation demonstrated the model's ability to accurately segment liver regions.
- Comparison with gold standards confirmed the validity and usefulness of the proposed method.
Conclusions:
- The proposed probabilistic model offers a robust solution for fully-automated liver segmentation in CT imaging.
- This automated approach has the potential to streamline radiological workflows and improve diagnostic accuracy.
- The model's reliance on both spatial and density information enhances its reliability for liver segmentation.
