| Presentation | 2019-03-06 Magnetic Resonance Angiography Image Restoration by Super Resolution based on Deep Learning Shizen Kitazaki, Masanori Kawakita, Yutaka Jitumatu, Shigehide Kuhara, Akio Hiwatashi, Jun'ichi Takeuchi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Magnetic Resonance Imaging (MRI) is one of the powerful techniques to acquire in vivo information. However, to obtain a three dimensional fine image of the whole brain, it takes thirty minutes to forty minutes by using a current standard MRI scanner. Thus, to mitigate the inconvenience of the patient, further reduction of imaging time is required. For the past 10 years, Compressed Sensing (CS) has contributed to research for acceleration and high definition of MRI by means of information processing. However, CS has a disadvantage that the computational complexity is the order of cubic of the number of samples. Thus, in the case of high resolution images, it requires a reconstruction time longer than the reduced inspection time. Recently, deep learning based approach has been intensively studied for this problem. In this research, we propose a deep learning method, in which we employ a super-resolution (SR) method based on convolutional neural networks. In our method, the SR processes are applied to various resolution images obtained from the input signal. We report the results of adapting the proposed method to MRA (Magnetic Resonance Angiography) images. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Magnetic Reasonance Imaging / super-resolution / Deep Neural Network / Convolution Neural Network |
| Paper # | IBISML2018-114 |
| Date of Issue | 2019-02-26 (IBISML) |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2019/3/5(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | RIKEN AIP |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Machine learning, etc. |
| Chair | Hisashi Kashima(Kyoto Univ.) |
| Vice Chair | Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
| Assistant | Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Magnetic Resonance Angiography Image Restoration by Super Resolution based on Deep Learning |
| Sub Title (in English) | |
| Keyword(1) | Magnetic Reasonance Imaging |
| Keyword(2) | super-resolution |
| Keyword(3) | Deep Neural Network |
| Keyword(4) | Convolution Neural Network |
| 1st Author's Name | Shizen Kitazaki |
| 1st Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 2nd Author's Name | Masanori Kawakita |
| 2nd Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 3rd Author's Name | Yutaka Jitumatu |
| 3rd Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 4th Author's Name | Shigehide Kuhara |
| 4th Author's Affiliation | Kyorin University(Kyorin Univ.) |
| 5th Author's Name | Akio Hiwatashi |
| 5th Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 6th Author's Name | Jun'ichi Takeuchi |
| 6th Author's Affiliation | Kyushu University(Kyushu Univ.) |
| Date | 2019-03-06 |
| Paper # | IBISML2018-114 |
| Volume (vol) | vol.118 |
| Number (no) | IBISML-472 |
| Page | pp.pp.65-72(IBISML), |
| #Pages | 8 |
| Date of Issue | 2019-02-26 (IBISML) |