Related Experiment Video
Updated: Jun 10, 2025
09:36
Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin
Published on: March 14, 2018
9.3K
A method framework of semi-automatic knee bone segmentation and reconstruction from computed tomography (CT) images
Ahsan Humayun1,2,3, Mustafain Rehman1,2,3, Bin Liu1,2,3
1International School of Information Science & Engineering (DUT-RUISE), Dalian University of Technology, Dalian, China.
Quantitative Imaging in Medicine and Surgery
|October 21, 2024
Summary
This study introduces a new semi-automatic method for precise knee bone segmentation from CT scans using fuzzy C-means and active contours. The technique significantly improves accuracy for computer-aided diagnosis and treatment planning in knee diseases.
Area of Science:
- Medical Imaging
- Computational Anatomy
- Biomedical Engineering
Background:
- Accurate knee bone segmentation is vital for computer-aided diagnosis (CAD) and treatment planning.
- Current segmentation methods face challenges due to knee joint complexity, anatomical variations, and image quality.
- Improved techniques are needed for precise extraction of knee bone boundaries.
Purpose of the Study:
- To present a novel semi-automatic segmentation method for extracting knee bones from computed tomography (CT) images.
- To enhance the accuracy and efficiency of knee bone segmentation for clinical applications.
- To develop a robust method for generating 3D models of knee bones.
Main Methods:
- The method integrates the fuzzy C-means (FCM) algorithm with an adaptive region-based active contour model (ACM).
- FCM assigns voxel membership degrees to differentiate bone from soft tissues.
- The ACM refines segmentation boundaries using FCM outputs, followed by 3D model reconstruction using the marching cubes algorithm.
Main Results:
- High Dice scores were achieved: femur (98.95%), tibia (98.10%), and patella (97.14%).
- Low root mean square distance (RSD) values indicate precise segmentation: tibia/femur (0.5±0.14 mm), patella (0.6±0.13 mm).
- The method demonstrated superior accuracy and geometrical precision in segmenting knee bones.
Conclusions:
- The proposed method significantly advances CAD systems for knee pathologies.
- It offers precise and accurate segmentation of knee bones, crucial for anatomical analysis and surgical planning.
- The technique provides valuable insights for developing patient-specific prostheses and improving treatment outcomes.
