TUBITAK Destekli Projelerden Çıkan Yayınlar Topluluğu
Published January 1, 2023 | Version v1
Journal article Open

Automated LVO detection and collateral scoring on CTA using a 3D self-configuring object detection network: a multi-center study

Creators

  • 1. Sisli Hamidiye Etfal Res & Training Hosp, Radiol Dept, Istanbul, Turkiye
  • 2. Istanbul Istinye State Hosp, Neurol Dept, Istanbul, Turkiye
  • 3. Acibadem Mehmet Ali Aydinlar Univ, Sch Med, Istanbul, Turkiye
  • 4. Hevi Hlth, Artificial Intelligence & Informat Technol, Istanbul, Turkiye
  • 5. Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Radiol Dept, Istanbul, Turkiye
  • 6. Erzurum Ataturk Univ, Sch Med, Radiol Dept, Istanbul, Turkiye
  • 7. Istanbul Fatih Sultan Mehmet Training & Res Hosp, Radiol Dept, Istanbul, Turkiye
  • 8. Istanbul Bakirkoy Sadi Konuk Training & Res Hosp, Radiol Dept, Istanbul, Turkiye
  • 9. Istanbul Tech Univ, Comp Engn Dept, Istanbul, Turkiye
  • 10. Acibadem Mehmet Ali Aydinlar Univ, Sch Med, Radiol Dept, Istanbul, Turkiye

Description

The use of deep learning (DL) techniques for automated diagnosis of large vessel occlusion (LVO) and collateral scoring on computed tomography angiography (CTA) is gaining attention. In this study, a state-of-the-art self-configuring object detection network called nnDetection was used to detect LVO and assess collateralization on CTA scans using a multi-task 3D object detection approach. The model was trained on single-phase CTA scans of 2425 patients at five centers, and its performance was evaluated on an external test set of 345 patients from another center. Ground-truth labels for the presence of LVO and collateral scores were provided by three radiologists. The nnDetection model achieved a diagnostic accuracy of 98.26% (95% CI 96.25-99.36%) in identifying LVO, correctly classifying 339 out of 345 CTA scans in the external test set. The DL-based collateral scores had a kappa of 0.80, indicating good agreement with the consensus of the radiologists. These results demonstrate that the self-configuring 3D nnDetection model can accurately detect LVO on single-phase CTA scans and provide semi-quantitative collateral scores, offering a comprehensive approach for automated stroke diagnostics in patients with LVO.

Files

bib-37afdc3a-785d-491d-9845-a1b186987361.txt

Files (384 Bytes)

Name Size Download all
md5:ec9cb326051581ba6c3edb6551c47d9c
384 Bytes Preview Download