講演名 2014-09-02
Automatic blood vessel-based liver segmentation through the portal phase abdominal CT dataset
,
PDFダウンロードページ PDFダウンロードページへ
抄録(和)
抄録(英) Blood vessel (BV) has showed high performance at liver segmentation [1] achieving rank 1 on sliver07 (the official website for liver segmentation) as of August 3, 2014. This method of liver segmentation is semi-automatic including two stages: (1) semi-automatic abdominal blood vessels (ABVs) segmentation and (2) automatic liver segmentation based on segmented ABVs. First stage included three interactions in segmenting ABVs and one in classifying ABVs into hepatic and non-hepatic BVs. In this paper, we propose to develop ABVs segmentation to be fully automatic as a step for full automation of [1]. For automation of ABVs segmentation, average percentages of bone, kidneys and ABVs volumetries in the abdomen are estimated practically and separately. These volumetries are used for automatic ABVs segmentation based on shape and location information. Shapes of ABVs (tube-shaped) and kidneys (bean-shaped) are used to identify and segment kidneys automatically. By eliminating kidneys, bones and heart, ABVs are segmented. This method was applied to 50 datasets including diseased cases. Results shows that the proposed method is very promising at segmentation of ABVs.
キーワード(和)
キーワード(英) blood vessel / liver segmentation / CT image / portal phase
資料番号 MI2014-40
発行日

研究会情報
研究会 MI
開催期間 2014/8/26(から1日開催)
開催地(和)
開催地(英)
テーマ(和)
テーマ(英)
委員長氏名(和)
委員長氏名(英)
副委員長氏名(和)
副委員長氏名(英)
幹事氏名(和)
幹事氏名(英)
幹事補佐氏名(和)
幹事補佐氏名(英)

講演論文情報詳細
申込み研究会 Medical Imaging (MI)
本文の言語 ENG
タイトル(和)
サブタイトル(和)
タイトル(英) Automatic blood vessel-based liver segmentation through the portal phase abdominal CT dataset
サブタイトル(和)
キーワード(1)(和/英) / blood vessel
第 1 著者 氏名(和/英) / Ahmed S. Maklad
第 1 著者 所属(和/英)
Institute of Technology and Science, The University of Tokushima
発表年月日 2014-09-02
資料番号 MI2014-40
巻番号(vol) vol.114
号番号(no) 200
ページ範囲 pp.-
ページ数 5
発行日