講演抄録/キーワード |
講演名 |
2014-01-27 13:30
Evaluation of an automated identification system of unruptured intracranial aneurysm candidates based on a blob structure enhancement filter at 3.0 T magnetic resonance angiography ○Ze Jin・Hidetaka Arimura(Kyushu Univ.)・Yukunori Korogi(Univ. Hospital of Occupational & Environmental Health)・Fumio Yamashita・Makoto Sasaki(Medical Iwate Univ.) MI2013-102 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
An automated identification system of unruptured intracranial aneurysm candidates based on a three-dimensional (3D) blob structure enhancement (BSE) filter was evaluated for 3.0 T magnetic resonance angiography (MRA). Ten cases with 10 unruptured aneurysms (diameter, 2.4 to 8.4 mm; mean, 6.6 mm) were used in this study. The isotropic 3D magnetic resonance angiography images with 512 x 512 x (224-250) voxels (voxel size, 0.35 mm) were processed by use of the BSE filter. The initial candidates were identified by use of a multiple gray-level thresholding technique on the BSE images and a region growing technique with monitoring some image features. A number of false-positives were removed by using different rules on 17 image features related to gray levels and morphology. Support vector machine, which can learn the image features of true positives and false positives, was used for further removal of false-positives. With this system, 94.1% of aneurysms were correctly detected with 2.1 false-positives per patient based on a leave-one-out-by-patient test method. This computer-aided diagnostic system would be useful in assisting radiologists for the detection of intracranial aneurysms in 3.0 T MRA. |
キーワード |
(和) |
/ / / / / / / |
(英) |
/ / / / / / / |
文献情報 |
信学技報, vol. 113, no. 410, MI2013-102, pp. 249-253, 2014年1月. |
資料番号 |
MI2013-102 |
発行日 |
2014-01-19 (MI) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
MI2013-102 |
|