EUVIMEDEUVIMED entdecken
Crossref

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

James Thomas Patrick Decourcy Hallinan iD, Lei Zhu iD, Hui Wen Natalie Tan iD, Si Jian Hui, Xinyi Lim, Bryan Wei Loong Ong iD, Han Yang Ong iD, Sterling Ellis Eide, Amanda J L Cheng, Shuliang Ge, Tricia Kuah, Shi Wei Desmond Lim und 10 weitere

European Spine Journal · 2023

DOI: 10.1007/s00586-023-07706-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Spine Journal, 2023. Verfasst von James Thomas Patrick Decourcy Hallinan und 21 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Rd, Singapore, 119074, Singapore. james_hallinan@nuhs.edu.sg. Hauptthemen laut MEDLINE: Spinal Cord Compression, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: National Research Foundation Singapore, National University Cancer Institute, Singapore.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spinal Cord CompressionDeep LearningAdultHumansRetrospective StudiesSpineTomography, X-Ray Computed

Stichwörter der Autor:innen

Artificial intelligenceCTDeep learningEpidural spinal cord compressionMRIMetastatic epidural spinal cord compression

Autor:innen und Institutionen

  • Department of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Rd, Singapore, 119074, Singapore. james_hallinan@nuhs.edu.sg.
  • Department of Diagnostic Radiology, Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Drive, Singapore, 117597, Singapore. james_hallinan@nuhs.edu.sg.
  • Department of Computer Science, School of Computing, National University of Singapore, 13 Computing Drive, Singapore, 117417, Singapore.
  • Department of Orthopaedic Surgery, University Spine Centre, National University Health System, 1E, Lower Kent Ridge Road, Singapore, 119228, Singapore.
  • Orthopaedic Centre, Alexandra Hospital, 378 Alexandra Road, Singapore, 159964, Singapore.
  • Department of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Rd, Singapore, 119074, Singapore.

ORCID-Profile: James Thomas Patrick Decourcy Hallinan, Lei Zhu, Hui Wen Natalie Tan, Bryan Wei Loong Ong, Han Yang Ong, Naresh Kumar

Förderung

  • National Research Foundation Singapore
  • National University Cancer Institute, Singapore

Zitieren

APA

Hallinan, J. T. P. D., Zhu, L., Tan, H. W. N., Hui, S. J., Lim, X., Ong, B. W. L., Ong, H. Y., Eide, S. E., Cheng, A. J. L., Ge, S., Kuah, T., Lim, S. W. D., Low, X. Z., Teo, E. C., Yap, Q. V., Chan, Y. H., Kumar, N., Vellayappan, B. A., Ooi, B. C., …, & Tan, J. H. (2023). A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT. European Spine Journal. https://doi.org/10.1007/s00586-023-07706-4

Vancouver

Hallinan JTPD, Zhu L, Tan HWN, Hui SJ, Lim X, Ong BWL, et al. A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT. European Spine Journal. 2023. doi:10.1007/s00586-023-07706-4

BibTeX
@article{Hallinan2023,
  author = {Hallinan, James Thomas Patrick Decourcy and Zhu, Lei and Tan, Hui Wen Natalie and Hui, Si Jian and Lim, Xinyi and Ong, Bryan Wei Loong and Ong, Han Yang and Eide, Sterling Ellis and Cheng, Amanda J L and Ge, Shuliang and Kuah, Tricia and Lim, Shi Wei Desmond and Low, Xi Zhen and Teo, Ee Chin and Yap, Qai Ven and Chan, Yiong Huak and Kumar, Naresh and Vellayappan, Balamurugan A and Ooi, Beng Chin and Quek, Swee Tian and Makmur, Andrew and Tan, Jiong Hao},
  title = {A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT},
  journal = {European Spine Journal},
  year = {2023},
  doi = {10.1007/s00586-023-07706-4}
}
Kostenlos starten →