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
Segmenting lung fields in serial chest radiographs using both population and patient-specific shape statistics.
Yonghong Shi1, Feihu Qi, Zhong Xue
1Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China. shi-yh@cs.sjtu.edu.cn
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 new deformable model for segmenting lung fields in chest radiographs. It combines population and patient-specific shape data for more accurate and robust medical image segmentation.
Area of Science:
- Medical imaging
- Computer-aided diagnosis
- Image processing
Background:
- Accurate segmentation of lung fields in serial chest radiographs is crucial for diagnosing and monitoring respiratory diseases.
- Existing deformable models often struggle with patient-specific anatomical variations and require extensive manual input.
Purpose of the Study:
- To develop and evaluate a novel deformable model for robust lung field segmentation in serial chest radiographs.
- To integrate both population-based and patient-specific shape statistics for improved segmentation accuracy and adaptability.
Main Methods:
- A modified scale-invariant feature transform (SIFT) local descriptor was employed to characterize image features for guiding the deformable model.
- The deformable model was constrained using a combination of population-based shape statistics (initially) and patient-specific statistics (progressively).
Main Results:
- The proposed model demonstrated adaptability to diverse patient lung field shapes.
- The deformable model achieved more robust and accurate segmentation results compared to conventional methods.
Conclusions:
- The novel deformable model effectively segments lung fields in serial chest radiographs by leveraging both population and patient-specific shape statistics.
- This approach enhances segmentation accuracy and robustness, offering a valuable tool for clinical applications in respiratory imaging.
