Related Experiment Video
Updated: May 22, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.6K
A CNN Autoencoder for Learning Latent Disc Geometry from Segmented Lumbar Spine MRI
Mattia Perrone1, D'Mar Moore1, Daisuke Ukeba1
1Rush University Medical Center, Chicago, IL, 60612, USA.
Medrxiv : the Preprint Server for Health Sciences
|March 17, 2025
Summary
A novel convolutional neural network (CNN) autoencoder effectively extracts latent geometric features from lumbar MRI, improving disc narrowing prediction and understanding of disc pathology.
Area of Science:
- Biomedical Imaging
- Machine Learning in Healthcare
- Spine Biomechanics
Background:
- Low back pain is a leading cause of disability globally.
- Lumbar intervertebral disc pathology is a frequent pain driver.
- Disc geometry provides insights into mechanical behavior and pathology.
Purpose of the Study:
- Develop a convolutional neural network (CNN) autoencoder for latent feature extraction from segmented lumbar disc MRI.
- Interpret these latent features to identify disc pathology.
- Complement standard geometric measures for enhanced diagnostic capabilities.
Main Methods:
- Utilized 195 sagittal T1-weighted lumbar spine MRIs from a public dataset.
- Implemented a pipeline involving MRI segmentation, CNN autoencoder training, and latent feature extraction.
- Measured standard geometric features and predicted disc narrowing using both latent and standard features.
Main Results:
- Achieved high segmentation accuracy (IoU 0.82, DSC 0.90).
- CNN autoencoder converged with a 4x1 bottleneck size, yielding high IoU (0.9984).
- Combined latent and geometric features improved disc narrowing prediction accuracy.
Conclusions:
- A CNN autoencoder effectively extracts interpretable latent features from lumbar disc MRI.
- These latent features enhance the prediction of disc narrowing.
- Future research will incorporate voxel intensity for compositional analysis.
