Related Experiment Video
Updated: Nov 3, 2025
07:30
3D Printing Model of a Patient's Specific Lumbar Vertebra
Published on: April 14, 2023
2.2K
3D vertebrae labeling in spine CT: an accurate, memory-efficient (Ortho2D) framework.
Y Huang1, A Uneri1, C K Jones2
1Department of Biomedical Engineering, Johns Hopkins University, Baltimore MD, United States of America.
Physics in Medicine and Biology
|June 3, 2021
Summary
Accurate vertebral labeling in CT scans is crucial for diagnostics and surgery. The Ortho2D framework provides precise, memory-efficient vertebral labeling, improving accuracy and enabling higher resolution imaging.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Radiology
Background:
- Accurate computed tomography (CT) vertebral labeling is essential for quantitative diagnostics and surgical planning.
- Current methods may face limitations in accuracy and memory efficiency.
Purpose of the Study:
- To present Ortho2D, a novel framework for accurate and memory-efficient vertebral labeling in CT scans.
- To evaluate Ortho2D's performance against existing methods.
Main Methods:
- Utilized two independent faster R-convolutional neural networks for detecting and classifying vertebrae in sagittal and coronal CT slices.
- Employed 3D clustering of 2D detections for localization and classification of vertebral regions and levels.
- Incorporated a post-processing sorting method to refine classifications and reduce outliers.
Main Results:
- Achieved high accuracy: 97.1% for detection, 94.3% for region identification, and 91.0% for vertebral level identification.
- Demonstrated superior memory efficiency (approx. 50x reduction vs. 3D U-Net), enabling high-resolution CT analysis.
- Level identification accuracy increased to 95.1% on high-resolution CT, up from 80.1% on standard resolution.
Conclusions:
- Ortho2D offers comparable vertebral labeling performance to existing methods with significantly reduced memory footprint.
- The framework's memory efficiency allows for enhanced performance through high-resolution CT analysis.
- Ortho2D facilitates improved automated diagnostic analysis and surgical planning in spinal imaging.
Related Concept Videos
01:30General Structure of a Vertebra
4.7K
A typical vertebra, with the exception of the sacrum and coccyx, consists of a body, a vertebral arch, and seven different projections termed processes. The anterior portion of the vertebrae, the body, supports about half the body’s weight. The vertebral bodies progressively increase in size and thickness from the cervical region to the lumbar region of the vertebral column. The intervertebral discs present between the bodies of adjacent vertebrae firmly unites them, forming a continuous...
4.7K
01:16Vertebral Column: Regions and Curvature
5.2K
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...
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...
5.2K