An Image Feature Approach for Computer-aided Detection of Ischemic Stroke

Fuk Tang, Douglas K. S Ng, Daniel H K Chow

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

We present a computer-aided detection (CAD) scheme for early detection of ischemic stroke with small lesions using image feature characteristics. A novel Circular Adaptive Region of Interest (CAROI) method is proposed to analyze the Computed Tomography (CT) images of the brain. Our result indicates that for the emergency physicians and radiology residents, there is a significant improvement in sensitivity and specificity when using CAD (P<0.005). A mathematical model is established incorporating the weighting of the feature changes. Our CAD scheme is promising for early detection of ischemic stroke and helps improve the efficiency and accuracy of clinical practice.
Original languageEnglish
Pages (from-to)529-536
Number of pages8
JournalComputers in Biology and Medicine
Volume41
Issue number7
DOIs
Publication statusPublished - Jul 2011

Fingerprint

Stroke
Radiology
Tomography
Brain
Emergencies
Theoretical Models
Mathematical models
Physicians
Sensitivity and Specificity

Cite this

Tang, Fuk ; Ng, Douglas K. S ; Chow, Daniel H K. / An Image Feature Approach for Computer-aided Detection of Ischemic Stroke. In: Computers in Biology and Medicine. 2011 ; Vol. 41, No. 7. pp. 529-536.
@article{d57f99e6a776448c96edc77fdfc44370,
title = "An Image Feature Approach for Computer-aided Detection of Ischemic Stroke",
abstract = "We present a computer-aided detection (CAD) scheme for early detection of ischemic stroke with small lesions using image feature characteristics. A novel Circular Adaptive Region of Interest (CAROI) method is proposed to analyze the Computed Tomography (CT) images of the brain. Our result indicates that for the emergency physicians and radiology residents, there is a significant improvement in sensitivity and specificity when using CAD (P<0.005). A mathematical model is established incorporating the weighting of the feature changes. Our CAD scheme is promising for early detection of ischemic stroke and helps improve the efficiency and accuracy of clinical practice.",
keywords = "Adaptive region of interest, Computer-aided detection, Image feature, Ischemic stroke",
author = "Fuk Tang and Ng, {Douglas K. S} and Chow, {Daniel H K}",
note = "Imported on 12 Apr 2017 - DigiTool details were: month (773h) = July 2011; Journal title (773t) = Computers in Biology and Medicine. ISSNs: 0010-4825;",
year = "2011",
month = "7",
doi = "10.1016/j.compbiomed.2011.05.001",
language = "English",
volume = "41",
pages = "529--536",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier",
number = "7",

}

An Image Feature Approach for Computer-aided Detection of Ischemic Stroke. / Tang, Fuk; Ng, Douglas K. S; Chow, Daniel H K.

In: Computers in Biology and Medicine, Vol. 41, No. 7, 07.2011, p. 529-536.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Image Feature Approach for Computer-aided Detection of Ischemic Stroke

AU - Tang, Fuk

AU - Ng, Douglas K. S

AU - Chow, Daniel H K

N1 - Imported on 12 Apr 2017 - DigiTool details were: month (773h) = July 2011; Journal title (773t) = Computers in Biology and Medicine. ISSNs: 0010-4825;

PY - 2011/7

Y1 - 2011/7

N2 - We present a computer-aided detection (CAD) scheme for early detection of ischemic stroke with small lesions using image feature characteristics. A novel Circular Adaptive Region of Interest (CAROI) method is proposed to analyze the Computed Tomography (CT) images of the brain. Our result indicates that for the emergency physicians and radiology residents, there is a significant improvement in sensitivity and specificity when using CAD (P<0.005). A mathematical model is established incorporating the weighting of the feature changes. Our CAD scheme is promising for early detection of ischemic stroke and helps improve the efficiency and accuracy of clinical practice.

AB - We present a computer-aided detection (CAD) scheme for early detection of ischemic stroke with small lesions using image feature characteristics. A novel Circular Adaptive Region of Interest (CAROI) method is proposed to analyze the Computed Tomography (CT) images of the brain. Our result indicates that for the emergency physicians and radiology residents, there is a significant improvement in sensitivity and specificity when using CAD (P<0.005). A mathematical model is established incorporating the weighting of the feature changes. Our CAD scheme is promising for early detection of ischemic stroke and helps improve the efficiency and accuracy of clinical practice.

KW - Adaptive region of interest

KW - Computer-aided detection

KW - Image feature

KW - Ischemic stroke

U2 - 10.1016/j.compbiomed.2011.05.001

DO - 10.1016/j.compbiomed.2011.05.001

M3 - Article

VL - 41

SP - 529

EP - 536

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 7

ER -