계명대학교 의학도서관 Repository

Automated ASPECTS Scoring of CT Scans for Acute Ischemic Stroke Patients Using Machine Learning

Metadata Downloads
Author(s)
H. KuangX M. NajmX D. ChakrabortyX N. MarajX S.I. SohnX M. GoyalX M.D. HillX A.M. DemchukX B.K. MenonX W. Qiu
Keimyung Author(s)
Sohn, Sung Il
Department
Dept. of Neurology (신경과학)
Journal Title
American Journal of Neuroradiology
Issued Date
2018
Abstract
BACKGROUND AND PURPOSE:

Alberta Stroke Program Early CT Score (ASPECTS) was devised as a systematic method to assess the extent of early ischemic change on noncontrast CT (NCCT) in patients with acute ischemic stroke (AIS). Our aim was to automate ASPECTS to objectively score NCCT of AIS patients.

MATERIALS AND METHODS:

We collected NCCT images with a 5-mm thickness of 257 patients with acute ischemic stroke (<8 hours from onset to scans) followed by a diffusion-weighted imaging acquisition within 1 hour. Expert ASPECTS readings on DWI were used as ground truth. Texture features were extracted from each ASPECTS region of the 157 training patient images to train a random forest classifier. The unseen 100 testing patient images were used to evaluate the performance of the trained classifier. Statistical analyses on the total ASPECTS and region-level ASPECTS were conducted.

RESULTS:

For the total ASPECTS of the unseen 100 patients, the intraclass correlation coefficient between the automated ASPECTS method and DWI ASPECTS scores of expert readings was 0.76 (95% confidence interval, 0.67-0.83) and the mean ASPECTS difference in the Bland-Altman plot was 0.3 (limits of agreement, -3.3, 2.6). Individual ASPECTS region-level analysis showed that our method yielded κ = 0.60, sensitivity of 66.2%, specificity of 91.8%, and area under curve of 0.79 for 100 × 10 ASPECTS regions. Additionally, when ASPECTS was dichotomized (>4 and ≤4), κ = 0.78, sensitivity of 97.8%, specificity of 80%, and area under the curve of 0.89 were generated between the proposed method and expert readings on DWI.

CONCLUSIONS:

The proposed automated ASPECTS scoring approach shows reasonable ability to determine ASPECTS on NCCT images in patients presenting with acute ischemic stroke.
Keimyung Author(s)(Kor)
손성일
Publisher
School of Medicine (의과대학)
Citation
H. Kuang et al. (2018). Automated ASPECTS Scoring of CT Scans for Acute Ischemic Stroke Patients Using Machine Learning. American Journal of Neuroradiology. doi: 10.3174/ajnr.A5889
Type
Article
ISSN
0195-6108
Source
http://www.ajnr.org/content/early/2018/11/29/ajnr.A5889.long
DOI
10.3174/ajnr.A5889
URI
https://kumel.medlib.dsmc.or.kr/handle/2015.oak/41089
Appears in Collections:
1. School of Medicine (의과대학) > Dept. of Neurology (신경과학)
공개 및 라이선스
  • 공개 구분공개
  • 엠바고Forever
파일 목록

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.