Development of a Machine-Learning Algorithm to Identify Cauda Equina Compression on Magnetic Resonance Imaging Scans
This study pilots a deep learning approach for predicting cauda equina compression presence, promising improved healthcare quality and timely CES management. As referrals rise, this tool can act as a fast triage system which can lead to prompt management of CES in environments where resources for radiological interpretation of MRI scans are limited.
Authors
- Li Guo
- Joshua MacArthur (ORCID: https://orcid.org/0000-0003-3838-7370)
- Ella Snowdon (ORCID: https://orcid.org/0009-0006-0402-6904)
- Hamza Ahmed (ORCID: https://orcid.org/0000-0002-3306-5586)
- K. Joshi George (ORCID: https://orcid.org/0000-0002-1149-2536)
- Sayan Biswas (ORCID: https://orcid.org/0000-0002-7744-5732)
- Ved Sarkar
- Callum Tetlow
- Xutao Deng (ORCID: https://orcid.org/0000-0002-7372-3758)
Institutions
- Manchester Metropolitan University (GB)
- Berkeley College (US)
- Edge Hill University (GB)
- Salford Royal NHS Foundation Trust (GB)
- Northwick Park Hospital (GB)
- Salford Royal Hospital (GB)
- Alliance Data (United States) (US)
- University of California, Berkeley (US)
Publication Details
- Journal
- World Neurosurgery
- Published
- 2025-02-20
- DOI
- https://doi.org/10.1016/j.wneu.2025.123669
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00