SpineNet Online Demo

Back pain is the most common cause of long-term disability world-wide, affecting around half of all people over their lifetime. As people live longer, this problem will only get worse.

To combat this, we've developed SpineNet, a computer vision-based system to automatically perform a wide range of radiological gradings in spinal magnetic resonance imaging. It is robust and has been validated across several different datasets, showing performance comparable to clinical radiologists.

You can try a demo version of the software on your own lumbar spine MR scans on this website. We're constantly working on ways to improve it so if you would like to try your own grading system or provide feedback, please contact us.

Try the Software

This is the second version of the spinenet software with better vertebra detection, labelling and additional radiological gradings. To access the original version, click here

Latest News

• November 2020:The Online Demo for version 2 of Spinenet is now live! We have updated the existing method of detecting and labelling vertebrae as well as adding new radiological gradings for foraminal stenosis.
• October 2020: Our paper "A Convolutional Approach to Vertebrae Detection and Labelling In Whole Spine MRI" has been presented at MICCAI 2020. Here we show a new method for finding vertebrae in variable field of view scans and demonstrate this on whole spine & lumbar scans. We also show how this can be used to detect scoliosis in clinical MR scans. Read More

Features

The demo version of SpineNet on this website takes lumbar spinal MRIs as input detects and labels vertebral bodies and outputs the following radiological gradings on a per-vertebral disk level:

1. Pfirrman Grading (5 Classes)
2. Disc Narrowing (4 Classes)
3. Central Canal Stenosis (4 Classes)
4. Upper & Lower Endplate Defects (Binary)
5. Upper & Lower Marrow Changes (Binary)
6. Left/Right Foraminal Stenosis (Binary)
7. Spondylolisthesis (Binary)
8. Disc Herniation (Binary)

We also have versions of the software for detecting and labelling vertebrae in whole spine MRIs and are constantly working on new tasks. Please get in touch if you'd like to try a different task or use the whole spine version.

Contact

For queries, feedback, or to add your own grading system, please email rhydian@robots.ox.ac.uk or amirj@robots.ox.ac.uk.

Acknowledgements

This software is developed as a collaboration between computer vision researchers and spinal clinicians. We'd particularly like to thank Professor Jeremy Fairbank, Professor Jill Urban, Professor Ian McCall and Dr. Sarim Ather for contributing their expertise in spinal anatomy and pathology to this project.

We are also grateful to Cancer Research UK, EPSRC Program Grant Seebibyte & Genodisc for funding and data acquisition.

Related Publications

If you use this software in your own research please consider citing the following papers:

1. A. Jamaludin, M. Lootus, T. Kadir, A. Zisserman, J. Urban, M. C. Battié, J. Fairbank, and I. McCall. Issls prize in bioengineering science 2017: Automation of reading of radiological features from magnetic resonance images (mris) of the lumbar spine without human intervention is comparable with an expert radiologist. European Spine Journal, 26(5):1374–1383, May 2017. link
2. R. Windsor, A. Jamaludin, T. Kadir, A. Zisserman. A Convolutional Approach to Vertebrae Detection and Labelling in Whole Spine MRI. MICCAI 2020. link
3. A. Jamaludin, T. Kadir and A. Zisserman. SpineNet: Automated classification and evidence visualization in spinal MRIs. Medical Image Analysis, 41 (Supplement C): 63-73, 2017. link

The following studies have also employed Spinenet:

1. B. L. Roller, R. D. Boutin, T. J. O'Gara, Z. O. Knio, A. Jamaludin, J. C. Tan, and L. Lenchik, "Accurate prediction of lumbar microdecompression level with an automated MRI grading system" in Skeletal Radiology, 2020.
2. Y. Ishimoto, A. Jamaludin, C. Cooper, K. Walker-Bone, H. Yamada, H. Hashizume, H. Oka, S. Tanaka, N. Yoshimura, M. Yoshida, J. Urban, T. Kadir, and J. Fairbank, "Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study" in BMC Musculoskeletal Disorders, 2020.

1. A. Jamaludin, T. Kadir, A. Zisserman, B. L. Roller, D. McKean, J. Urban, and J. Fairbank, "Determining Severity of Central Canal Stenosis by Comparing Pairs of Scans" in The International Society for the Study of the Lumbar Spine (ISSLS) , 2020. Special Poster
2. B. L. Roller, P. Zhang, Z. O. Knio, T. J. O'Gara, L. Lenchik, J. C. Tan, T. Kadir, A. Jamaludin, and R. D. Boutin, "Radiologist versus the Machine: Can a Machine Learning Algorithm Adequately Identify the Surgical Level in Patients Undergoing Lumbar Decompression" in Radiological Society of North America (RSNA) Scientific Assembly and Annual Meeting, 2019.
3. A. Jamaludin, T. Kadir, A. Zisserman, C. Pereira, F. M. K. Williams, J. Urban, and J. Fairbank, "Disc Degeneration More Than an Aging Process" in BritSpine, 2020.
4. A. Jamaludin, T. Kadir, A. Zisserman, C. Pereira, F. M. K. Williams, J. Urban, and J. Fairbank, "Disc Degeneration More Than an Aging Process" in ORS PSRS 5th International Spine Research Symposium, 2019.
5. A. Jamaludin, T. Kadir, A. Zisserman, C. Pereira, F. M. K. Williams, J. Urban, and J. Fairbank, "Disc Degeneration More Than an Aging Process" in EUROSPINE, 2019. Oral
6. B. Roller, Z. Knio, T. O'Gara, J. Tan, R. Boutin, T. Kadir, A. Jamaludin, and L. Lenchik, "Machine Learning Algorithm for Automated Lumbar MRI Scoring Correlates With Pain and Disability Index in Patients Undergoing Lumbar Decompression" in the Annual Meeting of the International Skeletal Society (ISS), 2019.
7. J. Matta, T. Kadir, A. Jamaludin, J. Niinimaki, Mikko Saukkonen, and Jaro Karppinen, "Independent validation of a machine learning based spinal MRI grading system on the Finnish population cohort" in The International Society for the Study of the Lumbar Spine (ISSLS) Meeting, 2019.
8. B. L. Roller, Z. Knio, T. J. O'Gara, J. Tan, L. Lenchik, R. D Boutin, T. Kadir, and A. Jamaludin, "Correlation of automated lumbar MRI grading with microdecompression surgical level" in The International Society for the Study of the Lumbar Spine (ISSLS) Meeting, 2019. Special Poster
9. A. Jamaludin, T. Kadir, A. Zisserman, C. Pereira, F. Williams, J. Urban, and J. Fairbank, "Disc Degeneration More Than an Aging Process" in The International Society for the Study of the Lumbar Spine (ISSLS) Meeting, 2019. Special Poster
10. Y. Ishimoto, A. Jamaludin, C. Cooper, K. Walker-Bone, H. Yamada, H. Hashizume, H. Oka, S. Tanaka, N. Yoshimura, M. Yoshida, J. Urban, T. Kadir, and J. Fairbank, "Automation of MRI gradings to aid longitudinal studies of lumbar spinal stenosis in the Wakayama Spine Study" in The International Society for the Study of the Lumbar Spine (ISSLS) Meeting, 2019. Oral
11. T. Kadir, A. Zisserman, J. Fairbank, A. Jamaludin, and J. Urban, "SpineNet: Automated Vertebra and Disc Gradings Using Deep Learning" in Radiological Society of North America (RSNA) Scientific Assembly and Annual Meeting, 2018.
12. A. Jamaludin, T. Kadir, A. Zisserman, J. Urban, J. Fairbank, and Frances MK Williams, "Adapting a deep learning model to a different grading system in a new dataset" in The International Society for the Study of the Lumbar Spine (ISSLS) Meeting, 2018. Special Poster