Automatic segmentation method of cerebral arteries in MRA images:

DOI IR HANDLE 1 Citations
  • ASANO Tatsunori
    Dept. of Intelligent Image Information, Graduate School of Medicine, Gifu University
  • UCHIYAMA Yoshikazu
    Dept. of Biomedical Informatics, Graduate School of Medicine, Gifu University
  • ASANO Takahiko
    Dept. of Radiology, Graduate School of Medicine, Gifu University
  • KATO Hiroki
    Dept. of Radiology, Graduate School of Medicine, Gifu University
  • HARA Takeshi
    Dept. of Intelligent Image Information, Graduate School of Medicine, Gifu University
  • Zhou Xiangroug
    Dept. of Intelligent Image Information, Graduate School of Medicine, Gifu University
  • IWAMA Toru
    Dept. of Neurosurgery, Graduate School of Medicine, Gifu University
  • HOSHI Hiroaki
    Dept. of Radiology, Graduate School of Medicine, Gifu University
  • KINOSADA Yasutomi
    Dept. of Biomedical Informatics, Graduate School of Medicine, Gifu University
  • FUJITA Hiroshi
    Dept. of Intelligent Image Information, Graduate School of Medicine, Gifu University

Bibliographic Information

Other Title
  • MRA画像における脳動脈領域の抽出法
  • —大規模データベースを用いた評価—
  • Performance evaluation using large image database

Search this article

Abstract

The detection of cerebrovascular diseases such as unruptured aneurysm and stenosis is a major application of magnetic resonance angiography (MRA) . However, their accurate detection is often difficult for radiologists. Therefore, several computer-aided diagnosis (CAD) schemes have been developed in order to assist radiologists with image interpretation. The purpose of this study is to modify our segmentation method of cerebral arteries and its application to a large image database. For the segmentation of cerebral arteries, we first used a gray level transformation to calibrate voxel values. To adjust for variations in the positioning of patients, image registration was subsequently employed to maximize the overlapping of the cerebral arteries in the target image and reference image. The cerebral arteries were then segmented from the background using gray-level thresholding and region growing techniques. Finally, rule-based schemes with features such as size and anatomical location were employed to distinguish between cerebral arteries and false positives. Our method was applied to 876 clinical cases, which were obtained from three different hospitals. The segmentation of cerebral arteries in 98.1% (859/876) of the MRA studies was attained as an acceptable result. Therefore, our computerized method would be useful for the segmentation of cerebral arteries in MRA images.

Journal

Citations (1)*help

See more

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top