Literature DB >> 30230091

CT Reconstruction Levels Affect Automated and Reader-Based ASPECTS Ratings in Acute Ischemic Stroke.

Fatih Seker1, Johannes Pfaff1, Simon Nagel2, Dominik Vollherbst1, Stephen Gerry3, Markus A Möhlenbruch1, Martin Bendszus1, Christian Herweh1.   

Abstract

BACKGROUND AND
PURPOSE: We investigated whether automated and reader-based ASPECTS in acute stroke patients are affected by different CT image reconstruction algorithms.
METHODS: ASPECTS were assessed by commercial software and four independent blinded readers (two residents and two consultants) from different CT reconstructions (filtered back projection and two different iterative reconstruction [IR] levels) in 43 acute stroke patients with proximal middle cerebral artery occlusion. Ground truth was provided by an expert with unrestricted data access.
RESULTS: The residents showed significant variations between IR levels and had a significantly lower internal consistency across different reconstructions compared to the software, which performed similarly to the consultants. The consultant as well as the software also showed different deviations from ground truth with different IR levels, which were least at IR strength level 2.
CONCLUSIONS: CT image postprocessing affects either automated or human ASPECTS in acute stroke patients. This effect was most pronounced in the less experienced readers, while the software had the most robust performance.
© 2018 by the American Society of Neuroimaging.

Entities:  

Keywords:  ASPECTS; CT; Stroke; filtered back projection; iterative reconstruction

Mesh:

Year:  2018        PMID: 30230091     DOI: 10.1111/jon.12562

Source DB:  PubMed          Journal:  J Neuroimaging        ISSN: 1051-2284            Impact factor:   2.486


  6 in total

1.  Automated versus manual imaging assessment of early ischemic changes in acute stroke: comparison of two software packages and expert consensus.

Authors:  Friederike Austein; Fritz Wodarg; Nora Jürgensen; Monika Huhndorf; Johannes Meyne; Thomas Lindner; Olav Jansen; Naomi Larsen; Christian Riedel
Journal:  Eur Radiol       Date:  2019-05-10       Impact factor: 5.315

2.  Novel and Efficient Quantitative Posterior-Circulation-Structure-Based Scale via Noncontrast CT to Predict Ischemic Stroke Prognosis: A Retrospective Study.

Authors:  Wen-Hui Fang; Ying-Chu Chen; Ming-Chen Tsai; Pi-Shao Ko; Ding-Lian Wang; Sui-Lung Su
Journal:  J Pers Med       Date:  2022-01-20

3.  Accuracy and Prognostic Role of NCCT-ASPECTS Depend on Time from Acute Stroke Symptom-onset for both Human and Machine-learning Based Evaluation.

Authors:  A Potreck; C S Weyland; F Seker; U Neuberger; C Herweh; A Hoffmann; S Nagel; M Bendszus; M A Mutke
Journal:  Clin Neuroradiol       Date:  2021-10-28       Impact factor: 3.649

4.  Hyperdense Artery Sign in Patients With Acute Ischemic Stroke-Automated Detection With Artificial Intelligence-Driven Software.

Authors:  Charlotte Sabine Weyland; Panagiotis Papanagiotou; Niclas Schmitt; Olivier Joly; Pau Bellot; Yahia Mokli; Peter Arthur Ringleb; A Kastrup; Markus A Möhlenbruch; Martin Bendszus; Simon Nagel; Christian Herweh
Journal:  Front Neurol       Date:  2022-04-05       Impact factor: 4.003

5.  Emerging Artificial Intelligence Imaging Applications for Stroke Interventions.

Authors:  E Lotan
Journal:  AJNR Am J Neuroradiol       Date:  2020-12-31       Impact factor: 3.825

Review 6.  How to Improve the Management of Acute Ischemic Stroke by Modern Technologies, Artificial Intelligence, and New Treatment Methods.

Authors:  Kamil Zeleňák; Antonín Krajina; Lukas Meyer; Jens Fiehler; Daniel Behme; Deniz Bulja; Jildaz Caroff; Amar Ajay Chotai; Valerio Da Ros; Jean-Christophe Gentric; Jeremy Hofmeister; Omar Kass-Hout; Özcan Kocatürk; Jeremy Lynch; Ernesto Pearson; Ivan Vukasinovic
Journal:  Life (Basel)       Date:  2021-05-27
  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.