| Presentation | 2018-07-24 Improving Accuracy of Lung nodules Detection by Transfer Learning Tatsuya Yamazaki, Hayato Yamakawa, Norihiko Yoshimura, Motohiko Yamazaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In Japan, cancer is the first leading cause of death and, in particular, fatalities of lung cancer is increasing recently. It is proved that the mortality rate of lung cancer can be decreased by remedy commencement with early detection. Although chest CT inspection is one of the detailed examinations for lung cancer, it has been an issue that the number of specialists who diagnose the chest CT images is not enough. On the other hand, usefulness of Deep Learning (DL), that can extract the features in the object images based on a large image database and classify the images, is growing. The issue of specialist shortage might be solved by applying DL to the diagnosis of lung CT images. However, such a large database of CT images is not always available. In this paper, for such a case, it is verified that accuracy of lung nodule detection can be improved by the transfer learning that train a DL model by making use of public databases including the same kind of chest CT images. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | CT Image / Lung Nodule / Deep Learning / Transfer Learning |
| Paper # | MI2018-29 |
| Date of Issue | 2018-07-17 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2018/7/24(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | aiina (Morioka, Iwate) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Imaging, etc. |
| Chair | Kensaku Mori(Nagoya Univ.) |
| Vice Chair | Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.) |
| Secretary | Yoshiki Kawata(Aichi Inst. of Tech.) / Yuichi Kimura(Nagoya Inst. of Tech.) |
| Assistant | Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Improving Accuracy of Lung nodules Detection by Transfer Learning |
| Sub Title (in English) | |
| Keyword(1) | CT Image |
| Keyword(2) | Lung Nodule |
| Keyword(3) | Deep Learning |
| Keyword(4) | Transfer Learning |
| 1st Author's Name | Tatsuya Yamazaki |
| 1st Author's Affiliation | Niigata University(Niigata Univ.) |
| 2nd Author's Name | Hayato Yamakawa |
| 2nd Author's Affiliation | Niigata University(Niigata Univ.) |
| 3rd Author's Name | Norihiko Yoshimura |
| 3rd Author's Affiliation | Niigata University(Niigata Univ.) |
| 4th Author's Name | Motohiko Yamazaki |
| 4th Author's Affiliation | Niigata University(Niigata Univ.) |
| Date | 2018-07-24 |
| Paper # | MI2018-29 |
| Volume (vol) | vol.118 |
| Number (no) | MI-150 |
| Page | pp.pp.39-43(MI), |
| #Pages | 5 |
| Date of Issue | 2018-07-17 (MI) |