WEKO3
アイテム
Deep learning-based DWI Denoising method that suppressed the "instability" problem
https://repo.qst.go.jp/records/84071
https://repo.qst.go.jp/records/840713b765f30-38f7-4600-8f8d-e285d1425632
| Item type | 会議発表用資料 / Presentation(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2021-12-08 | |||||
| タイトル | ||||||
| タイトル | Deep learning-based DWI Denoising method that suppressed the "instability" problem | |||||
| 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 |
Nozaki, Hayato
× Nozaki, Hayato× Yasuhiko, Tachibana× Otsuka, Yujiro× Uchida, Wataru× Saito, Yuya× Kamagata, Koji× Aoki, Shigeki× Yasuhiko, Tachibana |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | Synopsis Deep learning-based noise reduction technique for DWI contains a risk of outputting values that are greatly deviating from what it should be because of the instability problem of deep learning. The neural network model was designed in this study to suppress this risk which can fix the generated value for each pixel within the range of values of neighboring pixels in the original image. The results of the volunteer study suggested that the proposed method has potential to provide effective denoising beside suppressing the instability risk. |
|||||
| 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 2021 | |||||
| 発表年月日 | ||||||
| 日付 | 2021-05-19 | |||||
| 日付タイプ | Issued | |||||
