講演抄録/キーワード |
講演名 |
2020-03-11 14:10
Accuracy of Brain Tumor Detection and Classification Based on Under Sampled k-Space Signals ○Tania Sultana・Sho Kurosaki・Yutaka Jitsumatsu・Junichi Takeuchi(Kyushu Univ.) IBISML2019-46 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
The prime concern of Magnetic Resonance Imaging (MRI) is to optimize
examination time by assuring a good quality of the images. In this
aspect, a newly developed deep learning method,
called multi-resolution CNN (MRCNN), was proposed by Kitazaki
et al.
The key focus of MRCNN is that, it can restore high quality image from
under sampled $k$-space signals.
Kitazaki et al. evaluated its performance in term of Peak Signal to Noise Ratio
(PSNR). The aim of this study is to evaluate the performance of MRCNN
in the field of brain tumor detection and classification based on
transfer learning. This paper highlights the accuracy of detection
and classification using mRCNN is significantly higher in contrast
without MRCNN. |
キーワード |
(和) |
/ / / / / / / |
(英) |
MRI reconstruction / under sampled k-space signals / transfer learning / / / / / |
文献情報 |
信学技報, vol. 119, no. 476, IBISML2019-46, pp. 91-94, 2020年3月. |
資料番号 |
IBISML2019-46 |
発行日 |
2020-03-03 (IBISML) |
ISSN |
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 |
IBISML2019-46 |