An image feature approach for computer-aided detection of ischemic stroke

Fuk-Hay Tang; Douglas K S Ng; Daniel H K Chow

doi:10.1016/j.compbiomed.2011.05.001

An image feature approach for computer-aided detection of ischemic stroke

Comput Biol Med. 2011 Jul;41(7):529-36. doi: 10.1016/j.compbiomed.2011.05.001. Epub 2011 May 24.

Authors

Fuk-Hay Tang¹, Douglas K S Ng, Daniel H K Chow

Affiliation

¹ The Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hum, Kowloon, Hong Kong. fuk-hay.tang@polyu.edu.hk

PMID: 21605853
DOI: 10.1016/j.compbiomed.2011.05.001

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.

MeSH terms

Algorithms
Brain Ischemia / diagnostic imaging*
Case-Control Studies
Databases, Factual
Humans
Image Interpretation, Computer-Assisted / methods*
Neural Networks, Computer
ROC Curve
Reproducibility of Results
Sensitivity and Specificity
Stroke / diagnostic imaging*
Tomography, X-Ray Computed