Paper Abstract and Keywords |
Presentation |
2012-12-12 15:10
Examination of Fuzzy Object Model using Brain Segmentation from Newborn Head MR Images Aya Hashioka (Univ. of Hyogo), Syoji Kobashi, Kei Kuramoto (Univ. of Hyogo/ WPI-IFReC), Yuki Wakata, Kumiko Ando, Reiichi Ishikura (Hyogo College of Medicine), Tomomoto Ishikawa (Ishikawa Hospital), Shozo Hirota (Hyogo College of Medicine), Yutaka Hata (Univ. of Hyogo/ WPI-IFReC) |
Abstract |
(in Japanese) |
(See Japanese page) |
(in English) |
Neonatal cerebral disorders such as hypoxic-ischemic encephalopathy might deform the brain shape, and reduce patient's cerebral functions. Early detecting and rapid cure of the cerebral disorders prevents the cerebral disorders developing worse. For quantitative diagnosis of the cerebral disorders, measurement of cerebral volume and surface area is effective. In this research, we propose an automated brain segmentation method for newborn brain. The proposed method produces fuzzy object models from learning dataset. Fuzzy object models express brain features by fuzzy membership functions. Using the FOMs, deformable surface model estimates subject's brain region. We applied the proposed method to 12 newborn subjects. From experimental results, the proposed method can segment the brain segmentation with high segmentation accuracy. |
Keyword |
(in Japanese) |
(See Japanese page) |
(in English) |
magnetic resonance images / newborn / brain segmentation / fuzzy object model / deformable surface model / / / |
Reference Info. |
ITE Tech. Rep., vol. 36, no. 54, ME2012-145, pp. 65-68, Dec. 2012. |
Paper # |
ME2012-145 |
Date of Issue |
2012-12-04 (ME) |
ISSN |
Print edition: ISSN 1342-6893 |
Download PDF |
|