| アイテムタイプ |
共通アイテムタイプ(1) |
| 公開日 |
2025-04-07 |
| タイトル |
|
|
タイトル |
An Denoising Method Low-Dose CT Image Using Image Restoration Convolutional Neural Network |
|
言語 |
en |
| 著者 |
Sadamatsu, Yuta
Murakami, Seiichi
Guangxu, Li
神谷, 亨
|
| 著作権関連情報 |
|
|
権利情報 |
Copyright (c) 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
|
言語 |
en |
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Radiation is widely used in medicine to diagnose and treat disease. CT (Computed Tomography) scans allow early detection of externally invisible diseases and appropriate treatment. However, radiation exposure from the examination may result in a future risk of cancer. Efforts are therefore being made to reduce radiation exposure. During the examination, noise is generated in the image when the dose is reduced. Noise reduces the visibility of the image and may cause lesions to be missed. In this study, we focus on Convolutional Neural Networks (CNNs), a type of deep learning model that has recorded high accuracy in image processing tasks. The proportion of frequency components in an image has more low-frequency components and fewer high-frequency components. Since image features are treated equally across channels, important information such as noise and edges are easily lost. To solve this problem, we propose CNN with channel attention module. In addition, we employ MAE as the loss function to enable effective learning. Using whole body slice CT images of pigs, we evaluate the image quality by Peak Signal-to-Noise Ratio (PSNR) and show that the proposed method is effective. |
|
言語 |
en |
| 備考 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
23rd International Conference on Control, Automation and Systems, ICCAS 2023, October 17-20 2023, Yeosu, Korea |
|
言語 |
en |
| 書誌情報 |
en : 2023 23rd International Conference on Control, Automation and Systems (ICCAS)
p. 1737-1740,
発行日 2023-11-20
|
| 出版社 |
|
|
出版者 |
IEEE |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Convolution Neural Network |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Low-Dose CT |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Channel Attention |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
MAE |
| 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_6501 |
|
資源タイプ |
journal article |
| 出版タイプ |
|
|
出版タイプ |
AM |
|
出版タイプResource |
http://purl.org/coar/version/c_ab4af688f83e57aa |
| DOI |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.23919/ICCAS59377.2023.10317050 |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
2642-3901 |
| 会議記述 |
|
|
|
会議名 |
23rd International Conference on Control, Automation and Systems, ICCAS 2023 |
|
|
言語 |
en |
|
回次 |
23 |
|
|
開始年 |
2023 |
|
|
開始月 |
10 |
|
|
開始日 |
17 |
|
|
終了年 |
2023 |
|
|
終了月 |
10 |
|
|
終了日 |
20 |
|
|
開催地 |
Yeosu |
|
|
言語 |
en |
|
開催国 |
KOR |
| 査読の有無 |
|
|
値 |
yes |
| 連携ID |
|
|
値 |
14154 |
LaSEINE-2023_041.pdf (436.1 KB)
