Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Nov;32(11):3815-3824.
doi: 10.1007/s00586-023-07706-4. Epub 2023 Apr 24.

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT

Affiliations

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT

James Thomas Patrick Decourcy Hallinan et al. Eur Spine J. 2023 Nov.

Abstract

Purpose: To develop a deep learning (DL) model for epidural spinal cord compression (ESCC) on CT, which will aid earlier ESCC diagnosis for less experienced clinicians.

Methods: We retrospectively collected CT and MRI data from adult patients with suspected ESCC at a tertiary referral institute from 2007 till 2020. A total of 183 patients were used for training/validation of the DL model. A separate test set of 40 patients was used for DL model evaluation and comprised 60 staging CT and matched MRI scans performed with an interval of up to 2 months. DL model performance was compared to eight readers: one musculoskeletal radiologist, two body radiologists, one spine surgeon, and four trainee spine surgeons. Diagnostic performance was evaluated using inter-rater agreement, sensitivity, specificity and AUC.

Results: Overall, 3115 axial CT slices were assessed. The DL model showed high kappa of 0.872 for normal, low and high-grade ESCC (trichotomous), which was superior compared to a body radiologist (R4, κ = 0.667) and all four trainee spine surgeons (κ range = 0.625-0.838)(all p < 0.001). In addition, for dichotomous normal versus any grade of ESCC detection, the DL model showed high kappa (κ = 0.879), sensitivity (91.82), specificity (92.01) and AUC (0.919), with the latter AUC superior to all readers (AUC range = 0.732-0.859, all p < 0.001).

Conclusion: A deep learning model for the objective assessment of ESCC on CT had comparable or superior performance to radiologists and spine surgeons. Earlier diagnosis of ESCC on CT could reduce treatment delays, which are associated with poor outcomes, increased costs, and reduced survival.

Keywords: Artificial intelligence; CT; Deep learning; Epidural spinal cord compression; MRI; Metastatic epidural spinal cord compression.

PubMed Disclaimer

References

    1. Van den Brande R, Cornips EM, Peeters M, Ost P, Billiet C, Van de Kelft E (2022) Epidemiology of spinal metastases, metastatic epidural spinal cord compression and pathologic vertebral compression fractures in patients with solid tumors: a systematic review. J Bone Oncol 35:100446. https://doi.org/10.1016/j.jbo.2022.100446 - DOI - PubMed - PMC
    1. Kuah T, Vellayappan BA, Makmur A, Nair S, Song J, Tan JH, Kumar N, Quek ST, Hallinan JTPD (2022) State-of-the-art imaging techniques in metastatic spinal cord compression. Cancers (Basel) 14:3289. https://doi.org/10.3390/cancers14133289 - DOI - PubMed
    1. Pezaro C, Omlin A, Perez-Lopez R, Mukherji D, Attard G, Bianchini D, Lorente D, Parker C, Dearnaley D, de Bono JS, Sohaib A, Tunariu N (2015) Progressive computed tomography (CT) appearances preceding malignant spinal cord compression (MSCC) in men with castration-resistant prostate cancer. Clin Radiol 70:359–365. https://doi.org/10.1016/j.crad.2014.05.104 - DOI - PubMed
    1. (2008) Metastatic spinal cord compression: diagnosis and management of patients at risk of or with metastatic spinal cord compression. National Collaborating Centre for Cancer, Cardiff
    1. Hallinan JTPD, Ge S, Zhu L, Zhang W, Lim YT, Thian YL, Jagmohan P, Kuah T, Lim DSW, Low XZ, Teo EC, Barr Kumarakulasinghe N, Yap QV, Chan YH, Tan JH, Kumar N, Vellayappan BA, Ooi BC, Quek ST, Makmur A (2022) Diagnostic accuracy of CT for metastatic epidural spinal cord compression. Cancers (Basel) 14:4231. https://doi.org/10.3390/cancers14174231 - DOI - PubMed

Publication types

LinkOut - more resources