Affordable Access

deepdyve-link
Publisher Website

Validation of automated Alberta Stroke Program Early CT Score (ASPECTS) software for detection of early ischemic changes on non-contrast brain CT scans.

Authors
  • Wolff, Lennard1
  • Berkhemer, Olvert A2, 3, 4
  • van Es, Adriaan C G M2
  • van Zwam, Wim H5
  • Dippel, Diederik W J2, 4
  • Majoie, Charles B L M3
  • van Walsum, Theo2, 6
  • van der Lugt, Aad2
  • 1 Department of Radiology & Nuclear Medicine, Erasmus MC, P. van Andel & L. Wolff, room Ne-515, Postbus 2040, 3000, CA, Rotterdam, the Netherlands. [email protected] , (Netherlands)
  • 2 Department of Radiology & Nuclear Medicine, Erasmus MC, P. van Andel & L. Wolff, room Ne-515, Postbus 2040, 3000, CA, Rotterdam, the Netherlands. , (Netherlands)
  • 3 Department of Radiology & Nuclear Medicine, Amsterdam University Medical Centers, location AMC, Amsterdam, the Netherlands. , (Netherlands)
  • 4 Department of Neurology, Erasmus MC, Rotterdam, the Netherlands. , (Netherlands)
  • 5 Department of Radiology, Maastricht UMC+, Maastricht, the Netherlands. , (Netherlands)
  • 6 Biomedical Imaging Group Rotterdam, Erasmus MC, Rotterdam, the Netherlands. , (Netherlands)
Type
Published Article
Journal
Neuroradiology
Publisher
Springer-Verlag
Publication Date
Apr 01, 2021
Volume
63
Issue
4
Pages
491–498
Identifiers
DOI: 10.1007/s00234-020-02533-6
PMID: 32857212
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

In ASPECTS, 10 brain regions are scored visually for presence of acute ischemic stroke damage. We evaluated automated ASPECTS in comparison to expert readers. Consecutive, baseline non-contrast CT-scans (5-mm slice thickness) from the prospective MR CLEAN trial (n = 459, MR CLEAN Netherlands Trial Registry number: NTR1804) were evaluated. A two-observer consensus for ASPECTS regions (normal/abnormal) was used as reference standard for training and testing (0.2/0.8 division). Two other observers provided individual ASPECTS-region scores. The Automated ASPECTS software was applied. A region score specificity of ≥ 90% was used to determine the software threshold for detection of an affected region based on relative density difference between affected and contralateral region. Sensitivity, specificity, and receiver-operating characteristic curves were calculated. Additionally, we assessed intraclass correlation coefficients (ICCs) for automated ASPECTS and observers in comparison to the reference standard in the test set. In the training set (n = 104), with software thresholds for a specificity of ≥ 90%, we found a sensitivity of 33-49% and an area under the curve (AUC) of 0.741-0.785 for detection of an affected ASPECTS region. In the test set (n = 355), the results for the found software thresholds were 89-89% (specificity), 41-57% (sensitivity), and 0.750-0.795 (AUC). Comparison of automated ASPECTS with the reference standard resulted in an ICC of 0.526. Comparison of observers with the reference standard resulted in an ICC of 0.383-0.464. The performance of automated ASPECTS is comparable to expert readers and could support readers in the detection of early ischemic changes.

Report this publication

Statistics

Seen <100 times