医用電子と生体工学
Online ISSN : 2185-5498
Print ISSN : 0021-3292
ISSN-L : 0021-3292
頭部MRI画像の知識に基づく自動セグメンテーションと3次元表示
鈴木 秀智鳥脇 純一郎
著者情報
ジャーナル フリー

1987 年 25 巻 1 号 p. 1-7

詳細
抄録
In this paper we present a procedure which automatically extracts soft tissues, such as subcutaneous fat, brain, and cerebral ventricle, from the multislice MRI images of head region, and displays their 3-dimensional images.
Segmentation of soft tissues is done by use of an iterative thresholding. In order to select the optimum threshold value automatically, we introduce a measure to evaluate the goodness of segmentation into this procedure. When the measure satisfies given conditions, iteration of thresholding terminates, and the final result of segmentation is extracted by using the current threshold value.
Since this procedure can execute segmentation and calculation of the goodness measure in each slice automatically, it remarkably decreases efforts of users. Moreover, the 3-dimensional display of the segmented tissues shows that this procedure can extract the shape of each soft tissue with reasonable precision for clinical use.
著者関連情報
© 日本生体医工学会
次の記事
feedback
Top