Paper Info
Title
Development of an Automated Method for the Detection of Chronic Lacunar Infarct Regions in Brain MR Images
Abstract
The purpose of our study is to develop an algorithm that would enable the automated detection of lacunar infarct on T1-and T2-weighted magnetic resonance (MR) images. Automated identification of the lacunar infarct regions is not only useful in assisting radiologists to detect lacunar infarcts as a computer-aided detection (CAD) system but is also beneficial in preventing the occurrence of cerebral apoplexy in high-risk patients. The lacunar infarct regions are classified into the following two types for detection: “isolated lacunar infarct regions” and “lacunar infarct regions adjacent to hyperintensive structures.” The detection of isolated lacunar infarct regions was based on the multiple-phase binarization (MPB) method. Moreover, to detect lacunar infarct regions adjacent to hyperintensive structures, we used a morphological opening processing and a subtraction technique between images produced using two types of circular structuring elements. Thereafter, candidate regions were selected based on three features — area, circularity, and gravity center. Two methods were applied to the detected candidates for eliminating false positives (FPs). The first method involved eliminating FPs that occurred along the periphery of the brain using the region-growing technique. The second method, the multi-circular regions difference method (MCRDM), was based on the comparison between the mean pixel values in a series of double circles on a T1-weighted image. A training dataset comprising 20 lacunar infarct cases was used to adjust the parameters. In addition, 673 MR images from 80 cases were used for testing the performance of our method; the sensitivity and specificity were 90.1% and 30.0% with 1.7 FPs per image, respectively. The results indicated that our CAD system for the automatic detection of lacunar infarct on MR images was effective.
Year
DOI
Venue
2007
10.1093/ietisy/e90-d.6.943
IEICE Transactions
Keywords
Field
DocType
automated detection,lacunar infarct,automatic detection,automatic detection of lacunar infarct on mr images was effective. key words: brain mri,cad system,isolated lacunar infarct region,computer-aided detection,mathematical morphology,automated method,t1- and t2-weighted images,mr image,computer-aided diagnosis,chronic lacunar infarct regions,lacunar infarct case,brain mr images,lacunar infarct region,multi-circular regions difference method,region growing,false positive,magnetic resonance
Nuclear medicine,Mean value,Pattern recognition,Mathematical morphology,Computer science,Computer-aided diagnosis,Artificial intelligence,Cad system,Lacunar Infarcts,Subtraction,Opening,Magnetic resonance imaging
Journal
Volume
Issue
ISSN
E90-D
6
0916-8532
Citations 
PageRank 
References 
5
0.72
5
Authors
12
Name
Order
Citations
PageRank
Ryujiro Yokoyama112318.40
Xuejun Zhang27016.55
Yoshikazu Uchiyama3699.58
Hiroshi Fujita450.72
Takeshi Hara563979.10
Xiangrong Zhou632545.53
Masayuki Kanematsu79017.09
Takahiko Asano8141.95
Hiroshi Kondo951.06
Satoshi Goshima1091.71
Hiroaki Hoshi1110618.21
Toru Iwama12112.95