Development of an Automated Method for the Detection of Chronic Lacunar Infarct Regions in Brain MR Images

Ryujiro YOKOYAMA  Xuejun ZHANG  Yoshikazu UCHIYAMA  Hiroshi FUJITA  Takeshi HARA  Xiangrong ZHOU  Masayuki KANEMATSU  Takahiko ASANO  Hiroshi KONDO  Satoshi GOSHIMA  Hiroaki HOSHI  Toru IWAMA  

IEICE TRANSACTIONS on Information and Systems   Vol.E90-D   No.6   pp.943-954
Publication Date: 2007/06/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e90-d.6.943
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
brain MRI,  lacunar infarct,  computer-aided diagnosis,  T1- and T2-weighted images,  mathematical morphology,  

Full Text: PDF(2.1MB)>>
Buy this Article

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.