講演抄録/キーワード |
講演名 |
2019-05-17 11:20
Personalized head models from MRI using convolutional neural networks ○Essam Rashed・Jose Gomez-Tames・Akimasa Hirata(NITech) EST2019-3 エレソ技報アーカイブへのリンク:EST2019-3 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
Transcranial magnetic stimulation (TMS) is a non-invasive clinical technique used for treatment of several neurological diseases. The brain induced electric field is known for inter- /intra- subject variabilities, which make it difficult to accurately adjust TMS parameters for different subjects. Therefore, a computer simulation is frequently used to simulate different TMS setups using models generated from anatomical images (e.g. MRI) of the examined subject. Human head models are generated by segmentation of MRI images into different anatomical tissues with isotropic electric conductivity each. This process is time-consuming and requires a special experience to segment a relatively large number of tissues. In this paper, we propose a deep convolution neural network for human head segmentation that is convenient for simulation of electrical field distribution, such as TMS. The proposed network is used to generate personalized head models from MRI with high accuracy. Results indicate that the personalized head models generated using the proposed method demonstrate strong matching with those achieved from manually segmented ones. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Convolutional neural network / deep learning / image segmentation / transcranial magnetic stimulation / / / / |
文献情報 |
信学技報, vol. 119, no. 42, EST2019-3, pp. 9-12, 2019年5月. |
資料番号 |
EST2019-3 |
発行日 |
2019-05-10 (EST) |
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 |
EST2019-3 エレソ技報アーカイブへのリンク:EST2019-3 |