| Presentation | 2023-11-14 Generation of pseudo-CT images from phalanges CR images based on deep learning Rensuke Ueno, Takaharu Yamazaki, Kazuaki Tanaka, Keizo Fukumoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, we perform generation to pseudo-CT images from phalanges CR images using deep learning. For the image generation method, pix2pix and CycleGAN, a type of adversarial generative network, are used. The dataset consists of 12 type images of the distal, middle, and basal phalanges of each of the four fingers of the left hand (index, middle, ring, and little fingers). As a result, the pix2pix method produced more accurate pseudo-CT images than CycleGAN. In addition, among the pseudo-CT images generated by pix2pix and CycleGAN, the generated images of the distal phalanges were relatively inaccurate, while those of the middle and basal phalanges showed the possibility of being used to measure the medullary cavity shape and width. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | CR image / CT image / Phalanges / Deep learning / Adversarial generation networks |
| Paper # | MICT2023-35,MI2023-28 |
| Date of Issue | 2023-11-07 (MICT, MI) |
| Conference Information | |
| Committee | MI / MICT |
|---|---|
| Conference Date | 2023/11/14(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Ryo Haraguchi(Univ. of Hyogo) / Hirokazu Tanaka(Hiroshima City Univ.) |
| Vice Chair | Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.) / Chika Sugimoto(Yokohama National Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) |
| Secretary | Hideaki Haneishi(Yamaguchi Univ.) / Takayuki Kitasaka(NAIST) / Chika Sugimoto(Okayama Pref. Univ.) / Daisuke Anzai(Hiroshima City Univ) |
| Assistant | Takeshi Hara(Gifu Univ.) / Kenichi Morooka(Okayama Univ.) / Dairoku Muramatsu(Univ. of Electro & Comm.) / Natsuki Nakayama(Nagoya Univ.) / Ami Tanaka(Ritsumeikan Univ.) / Kun Li(Kagawa Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging / Technical Committee on Healthcare and Medical Information Communication Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Generation of pseudo-CT images from phalanges CR images based on deep learning |
| Sub Title (in English) | Accuracy comparison using pix2pix and CycleGAN |
| Keyword(1) | CR image |
| Keyword(2) | CT image |
| Keyword(3) | Phalanges |
| Keyword(4) | Deep learning |
| Keyword(5) | Adversarial generation networks |
| 1st Author's Name | Rensuke Ueno |
| 1st Author's Affiliation | Saitama Institute of Technology(SIT) |
| 2nd Author's Name | Takaharu Yamazaki |
| 2nd Author's Affiliation | Saitama Institute of Technology(SIT) |
| 3rd Author's Name | Kazuaki Tanaka |
| 3rd Author's Affiliation | Neomedical Corporation(Neomedical Corporation) |
| 4th Author's Name | Keizo Fukumoto |
| 4th Author's Affiliation | Saitama Jikei Hospital(Saitama Jikei Hospital) |
| Date | 2023-11-14 |
| Paper # | MICT2023-35,MI2023-28 |
| Volume (vol) | vol.123 |
| Number (no) | MICT-256,MI-257 |
| Page | pp.pp.41-44(MICT), pp.41-44(MI), |
| #Pages | 4 |
| Date of Issue | 2023-11-07 (MICT, MI) |