WEKO3
アイテム
Deep-Neural-Network based image diagnosis: comparing various image preprocessing
https://repo.qst.go.jp/records/66661
https://repo.qst.go.jp/records/6666188148c15-57ce-4d09-b1d4-3ec02c4c0609
Item type | 会議発表用資料 / Presentation(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2018-03-19 | |||||
タイトル | ||||||
タイトル | Deep-Neural-Network based image diagnosis: comparing various image preprocessing | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_c94f | |||||
資源タイプ | conference object | |||||
アクセス権 | ||||||
アクセス権 | metadata only access | |||||
アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
著者 |
Tachibana, Yasuhiko
× Tachibana, Yasuhiko× Obata, Takayuki× Kershaw, Jeffrey× Ikoma, Yoko× Kishimoto, Riwa× Higashi, Tatsuya× 立花 泰彦× 小畠 隆行× Kershaw Jeffrey× 生駒 洋子× 岸本 理和× 東 達也 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | The purpose of this study was to investigate how image preprocessing might help overcome two problems for deep-neural-network (DNN) based image diagnosis: the need for a large training database to achieve high accuracy and the difficulty humans have in understanding the internal decision process. Five DNNs were trained with a brain image series (preprocessed in five different ways), to judge the age-range of a volunteer. The performance of the DNNs was then compared statistically. The results suggested that image preprocessing may facilitate higher accuracy, and also make it easier to understand how and why a judgement was made. | |||||
会議概要(会議名, 開催地, 会期, 主催者等) | ||||||
内容記述タイプ | Other | |||||
内容記述 | ISMRM 2016 2016 Annual Meeting | |||||
発表年月日 | ||||||
日付 | 2017-04-24 | |||||
日付タイプ | Issued |