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
. 2025 Jun 28;17(13):2180.
doi: 10.3390/cancers17132180.

Exploring the Potential of a Deep Learning Model for Early CT Detection of High-Grade Metastatic Epidural Spinal Cord Compression and Its Impact on Treatment Delays

James Thomas Patrick Decourcy Hallinan  1   2 , Junran Wu  3 , Changshuo Liu  3 , Hien Anh Tran  4 , Noah Tian Run Lim  4 , Andrew Makmur  1   2 , Wilson Ong  1 , Shilin Wang  5 , Ee Chin Teo  1 , Yiong Huak Chan  6 , Hwee Weng Dennis Hey  5 , Leok-Lim Lau  5 , Joseph Thambiah  5 , Hee-Kit Wong  5 , Gabriel Liu  5 , Naresh Kumar  5 , Beng Chin Ooi  3 , Jiong Hao Jonathan Tan  5
Affiliations

Exploring the Potential of a Deep Learning Model for Early CT Detection of High-Grade Metastatic Epidural Spinal Cord Compression and Its Impact on Treatment Delays

James Thomas Patrick Decourcy Hallinan et al. Cancers (Basel). .

Abstract

Background: Delay in diagnosing metastatic epidural spinal cord compression (MESCC) adversely impacts clinical outcomes. High-grade MESCC is frequently overlooked on routine staging CT scans. We aim to assess the potential of our deep learning model (DLM) in detecting high-grade MESCC and reducing diagnostic delays.

Methods: This retrospective review analyzed 140 patients with surgically treated MESCC between C7 and L2 during 2015-2022. An experienced radiologist (serving as the reference standard), a consultant spine surgeon, and the DLM independently classified staging CT scans into high-grade MESCC or not. The findings were compared to original radiologist (OR) reports; inter-rater agreement was assessed. Diagnostic delay referred to the number of days elapsed from CT to diagnostic MRI scan.

Results: Overall, 95/140 (67.8%) patients had preoperative CT scans. High-grade MESCC was identified in 84/95 (88.4%) of the scans by the radiologist (reference standard), but in only 32/95 (33.7%) of the preoperative scans reported by the OR. There was almost perfect agreement between the radiologist and the surgeon (kappa = 0.947, 95% CI = 0.893-1.000) (p < 0.001), and between the radiologist and the DLM (kappa = 0.891, 95% CI = 0.816-0.967) (p < 0.001). In contrast, inter-observer agreement between the OR and all other readers was slight (kappa range = 0.022-0.125). Diagnostic delay was potentially reduced by 20 ± 28 (range = 1-131) days.

Conclusions: The original radiologist reports frequently missed high-grade MESCC in staging CT. Our DLM for CT diagnosis of high-grade MESCC showed almost perfect inter-rater agreement with two experienced reviewers. This study is the first to demonstrate that the DLM could help reduce diagnostic delays. Further prospective research is required to understand its precise role in improving the early diagnosis/treatment of MESCC.

Keywords: Bilsky grading scale; computed tomography; metastatic epidural spinal cord compression; spinal metastases; treatment delays.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Example of high-grade (Bilsky grade 3) MESCC in a 43-year-old woman with breast cancer. Axial CT was performed in the portal-venous phase (left) with matching axial T2-weighted MRI (right) [43].
Figure 2
Figure 2
Potential delay intervals for patients with MESCC.
Figure 3
Figure 3
Flow chart of the study design. The DLM was compared against a radiologist (reference standard), spine surgeon, and the original radiology report issued at the time of the CT scan. All CT scans had matching MRI spine scans to confirm the diagnosis of metastatic epidural spinal cord compression (MESCC).
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Cole J.S., Patchell R.A. Metastatic epidural spinal cord compression. Lancet Neurol. 2008;7:459–466. doi: 10.1016/S1474-4422(08)70089-9. - DOI - PubMed
    1. Bach F., Larsen B.H., Rohde K., Børgesen S.E., Gjerris F., Bøge-Rasmussen T., Agerlin N., Rasmusson B., Stjernholm P., Sørensen P.S. Metastatic spinal cord compression. Occurrence, symptoms, clinical presentations and prognosis in 398 patients with spinal cord compression. Acta Neurochir. 1990;107:37–43. doi: 10.1007/BF01402610. - DOI - PubMed
    1. Loblaw D.A., Laperriere N.J., Mackillop W.J. A population-based study of malignant spinal cord compression in Ontario. Clin. Oncol. 2003;15:211–217. doi: 10.1016/S0936-6555(02)00400-4. - DOI - PubMed
    1. van Tol F.R., Choi D., Verkooijen H.M., Oner F.C., Verlaan J.J. Delayed presentation to a spine surgeon is the strongest predictor of poor postoperative outcome in patients surgically treated for symptomatic spinal metastases. Spine J. Off. J. N. Am. Spine Soc. 2019;19:1540–1547. doi: 10.1016/j.spinee.2019.04.011. - DOI - PubMed
    1. van Tol F.R., Suijkerbuijk K.P.M., Choi D., Verkooijen H.M., Oner F.C., Verlaan J.J. The importance of timely treatment for quality of life and survival in patients with symptomatic spinal metastases. Eur. Spine J. Off. Publ. Eur. Spine Soc. Eur. Spinal Deform. Soc. Eur. Sect. Cerv. Spine Res. Soc. 2020;29:3170–3178. doi: 10.1007/s00586-020-06599-x. - DOI - PubMed

LinkOut - more resources