Related Experiment Video
Updated: Feb 16, 2026
07:05
Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
Published on: February 15, 2022
3.0K
Fully automated segmentation of a hip joint using the patient-specific optimal thresholding and watershed algorithm
Jung Jin Kim1, Jimin Nam1, In Gwun Jang1
1The Cho Chun Shik Graduate School of Green Transportation, 373-1, Guseong-dong, Yuseong-gu, Daejeon 305-701, Korea Advanced Institute of Science and Technology, Republic of Korea.
Computer Methods and Programs in Biomedicine
|December 19, 2017
Summary
This study introduces a novel automated hip joint segmentation method combining thresholding and watershed algorithms. It achieves high accuracy and speed, crucial for large-scale quantitative assessments.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Computational Anatomy
Background:
- Automated segmentation is vital for quantitative assessments in large populations.
- Hip joint segmentation is challenging due to anatomical variations and thin bone structures.
Purpose of the Study:
- To develop a fully automated hip joint segmentation method.
- To overcome limitations of existing segmentation techniques for hip joints.
Main Methods:
- Combines thresholding technique with watershed algorithm.
- Utilizes golden section method and load path algorithm for optimal thresholding.
- Merges regional and boundary information for proximal femur extraction.
Main Results:
- Achieved high accuracy (Dice: 97.24%, ASD: 0.36 mm) compared to manual segmentation.
- Demonstrated fast processing time (1.25 s/slice).
- Results show structural behavior close to manual segmentation (mean relative error: 4.99%).
Conclusions:
- The method provides accurate and fast hip joint segmentation without manual intervention.
- It matches the speed of simplified Kang-based methods and accuracy of snake-based methods.
