You are here

Article Text

Article menu

Download PDFPDF

SNIS 20th annual meeting electronic poster abstracts
E-105 Validation of rapid noncontrast stroke CT platform for ICH and LVO detection
Free
  1. V Yedavalli1,
  2. J Heit2,
  3. S Dehkharghani3,
  4. H Haerian4,
  5. J McMenamy5,
  6. J Honce6,
  7. V Timpone6,
  8. C Harnain7,
  9. A Kesselman2,
  10. A Filly8,
  11. A Beardsley9,
  12. B Sakamoto10,
  13. C Song7,
  14. J Montuori11,
  15. B Navot12,
  16. F Mena13,
  17. D Giurguitiu14,
  18. F Kitamura15,
  19. F Lima16,
  20. H Coelho16,
  21. F Mont’Alverne16,
  22. G Albers17
  1. 1Department of Radiology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
  2. 2Department of Radiology, Stanford University, Stanford, CA, USA
  3. 3Department of Radiology, New York University, New York, NY, USA
  4. 4Department of Radiology, Mt. Sinai Hospital of Baltimore, Baltimore, MD, USA
  5. 5Department of Radiology, University of Colorado, Denver, CO, USA
  6. 6Department of Radiology, University of Colorado, Aurora, CO, USA
  7. 7Department of Radiology, Cornell University, New York, NY, USA
  8. 8Department of Radiology, Community Hospital of the Monterrey Peninsula, CA, Carmel-By-The-Sea, CA, USA
  9. 9Department of Radiology, University of Virginia, Gainesville, VA, USA
  10. 10Department of Radiology, Dameron Hospital, Stockton, CA, USA
  11. 11Department of Radiology, Capital Health, Camden, NJ, USA
  12. 12Department of Radiology, Columbia University, New York, NY, USA
  13. 13Department of Radiology, Clinical Las Condes, Santiago, Chile
  14. 14Department of Radiology, Augusta University Medical Center, Augusta, GA, USA
  15. 15Department of Radiology, Dasa Hospital, Sao Paulo, Brazil
  16. 16Department of Radiology, Hospital Geral de Fortaleza, Fortaleza, Brazil
  17. 17Department of Neurology, Stanford University, Stanford, CA, USA

Abstract

Introduction/Purpose Noncontrast CT (NCCT) is the first line screening modality to evaluate for intracerebral hemorrhage (ICH) and early ischemic changes in the setting of acute ischemic stroke (AIS). Large vessel occlusions (LVOs) are a major cause of AIS, but challenging to detect on NCCT alone. The purpose of this study is to evaluate a fully-automated AI platform called RAPID NCCT Stroke (iSchemaView, Menlo Park, CA) for ICH and LVO detection as compared to expert neuroimaging readers.

Materials and Methods In this IRB approved retrospective, multicenter study, 244 patients with suspected acute stroke were included. Stand-alone performance of the RAPID NCCT Stroke platform was assessed (based on the consensus of 3 neuroradiologists who determined reference standard from CT/CTA) and sensitivity and specificity were determined. The platform’s performance was then compared to expert interpretation by neuroimaging readers comprised of eight general radiologists (GR) and three neuroradiologists (NR) in detecting ICH and hyperdense vessel sign (HVS) as a marker of LVO. The primary hypothesis was that the sensitivity of RAPID NCCT Stroke for detection of LVO would be superiority to GR readers and non-inferiority to NR readers. Receiver operating characteristics (ROC) curve was used to evaluate the performance of each reader based on a rating system from 1 to 5 to express confidence in LVO detection. P < 0.05 was considered significant.

Results A total of 244 cases were included in this study. Of the 244, 115 were LVOs and 26 were ICHs. One hundred three cases did not have LVO nor ICH. Stand-alone performance of the platform demonstrated sensitivities and specificities of 96.2% and 99.5% respectively for ICH as well as 63.5% and 95.1% for LVO detection. In assessing non-inferiority of the platform compared to all 11 readers, the platform achieved a significantly higher sensitivity (63.5% versus 43.6%, p < 0.0001), meeting criteria for both non-inferiority and superiority. When compared to the eight GR readers only, the platform also showed superiority with significantly higher sensitivity (63.5% versus 40.9%, p = 0.001).

Conclusion The RAPID NCCT Stroke platform demonstrated superior performance to radiologists for detecting LVO from a NCCT. This could lead to earlier identification of LVO and faster treatment times. Prospective studies are needed for further validation.

View this table:
Abstract E-105 Table 1

Disclosures V. Yedavalli: 2; C; RAPID (iSchemaview, Menlo Park, CA). J. Heit: 2; C; RAPID (iSchemaview, Menlo Park, CA). S. Dehkharghani: None. H. Haerian: None. J. McMenamy: None. J. Honce: None. V. Timpone: None. C. Harnain: None. A. Kesselman: None. A. Filly: None. A. Beardsley: None. B. Sakamoto: None. C. Song: None. J. Montuori: None. B. Navot: None. F. Mena: None. D. Giurguitiu: None. F. Kitamura: None. F. Lima: None. H. Coelho: None. F. Mont’Alverne: None. G. Albers: 4; C; RAPID (IschemaView, Menlo Park, CA).

https://doi.org/10.1136/jnis-2023-SNIS.205

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.