Related Experiment Video
Updated: May 15, 2026
06:45
Automated Joint Space Detection Improves Bone Segmentation Accuracy
Published on: November 28, 2025
Automatic location of vertebrae on DXA images using random forest regression.
M G Roberts1, Timothy F Cootes, J E Adams
1Imaging Science Research Group, University of Manchester, UK. martin.roberts@manchester.ac.uk
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|January 5, 2013
Summary
We developed an automated method to segment vertebrae in DXA scans, aiding osteoporosis diagnosis and fracture grading. This technique accurately identifies vertebral fractures for improved clinical trial assessments.
Area of Science:
- Medical Imaging
- Radiology
- Computer Vision
Background:
- Vertebral fractures are key indicators of osteoporosis.
- Accurate segmentation of vertebrae in DXA images is crucial for diagnosis and clinical trials.
- Current methods may require manual initialization, limiting efficiency.
Purpose of the Study:
- To develop a fully automatic method for segmenting vertebrae in DXA images.
- To improve the accuracy and efficiency of vertebral fracture assessment.
- To support osteoporosis diagnosis and fracture grading in clinical settings.
Main Methods:
- Training detectors for upper and lower vertebral endplates using random forest regressor voting on Haar-like features.
- Utilizing a grid of points across the image for regressor application and vote smoothing to identify endplate candidates.
- Resolving ambiguity using geometric constraints and initializing active appearance model search for detailed segmentation.
Main Results:
- The method was applied to a dataset of 320 DXA images.
- Achieved accuracy comparable to manual initialization in 91% of cases.
- Identified potential edge confusion in severely osteoporotic cases with multiple severe fractures.
Conclusions:
- The developed fully automatic method offers a robust approach for vertebrae segmentation in DXA images.
- This technique has significant clinical relevance for osteoporosis diagnosis and fracture grading.
- Further refinement may be needed for complex cases with severe osteoporotic changes.
Related Concept Videos
01:18Classification of Bones
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
01:16Vertebral Column: Regions and Curvature
The vertebral column or spine is a flexible column that supports the head, neck, and body and allows for their movements. It also protects the spinal cord.
Regions of the Vertebral Column
In an adult, the spine is subdivided into five regions: the cervical, the thoracic, the lumbar, the sacral, and the coccygeal region. The spine initially develops as a series of 33 vertebrae; after 20 years of age, the nine bones in the sacral region, five sacral, and four coccygeal bones fuse to form the...
Regions of the Vertebral Column
In an adult, the spine is subdivided into five regions: the cervical, the thoracic, the lumbar, the sacral, and the coccygeal region. The spine initially develops as a series of 33 vertebrae; after 20 years of age, the nine bones in the sacral region, five sacral, and four coccygeal bones fuse to form the...