Presentation | 2019-03-06 Examination of Super Resolution and Noise Removal for MicroCT Image Miku Mashimo, Hayaru Shouno, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The purpose of this research is to increase the resolution of MicroCT (Computed Tomography) images. The MicroCT image is used for applications such as analysis of cells, and in this research we dealt with images extracted as images from 3D data obtained by MicroCT Scanner. The MicroCT image is of the unit of $ mu m $, whereas the scale of the normal CT image is about 1 { rm pixel} in units of $ mm $, and if this resolution can be raised, it is possible to find various diseases and development medical field. The technique to generate the high resolution image from the low resolution one is called super-resolution. Among super resolution technologies in which various methods have been proposed, we used deep learning type super resolution to verification. The problem here is that many conventional super resolution technology don`t consider the noise in the input image. Normally, when a noised image is input to a model learned to raise the resolution, the noise is emphasized. It is a problem that the image becomes poor in image quality. In particular, MicroCT images have many noise generated during observation. For this reason, we examined how the two processes of denoising and super-resolution can be performed to make the MicroCT image an image that is easily visible to humans. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | super resolution / denoising / medical image / deep learning |
Paper # | NC2018-86 |
Date of Issue | 2019-02-25 (NC) |
Conference Information | |
Committee | NC / MBE |
---|---|
Conference Date | 2019/3/4(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | University of Electro Communications |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Yutaka Hirata(Chubu Univ.) / Masaki Kyoso(TCU) |
Vice Chair | Hayaru Shouno(UEC) / Taishin Nomura(Osaka Univ.) |
Secretary | Hayaru Shouno(Nagoya Univ.) / Taishin Nomura(NAIST) |
Assistant | Keiichiro Inagaki(Chubu Univ.) / Takashi Shinozaki(NICT) / Takumi Kobayashi(YNU) / Yasuyuki Suzuki(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Examination of Super Resolution and Noise Removal for MicroCT Image |
Sub Title (in English) | |
Keyword(1) | super resolution |
Keyword(2) | denoising |
Keyword(3) | medical image |
Keyword(4) | deep learning |
1st Author's Name | Miku Mashimo |
1st Author's Affiliation | The University of Electro-Communications(UEC) |
2nd Author's Name | Hayaru Shouno |
2nd Author's Affiliation | The University of Electro-Communications(UEC) |
Date | 2019-03-06 |
Paper # | NC2018-86 |
Volume (vol) | vol.118 |
Number (no) | NC-470 |
Page | pp.pp.227-232(NC), |
#Pages | 6 |
Date of Issue | 2019-02-25 (NC) |