Paper Abstract and Keywords |
Presentation |
2021-02-18 13:00
A Note on Automatic Diagnosis of Helicobacter Pylori Infection Based on EfficientNet with Flooding Loss Guang Li, Ren Togo (Hokkaido Univ.), Katsuhiro Mabe (Junpukai Health Maintenance Center), Shunpei Nishida (Olympus), Yoshihiro Tomoda, Hikari Shimizu (Olympus Medical Systems), Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Abstract |
(in Japanese) |
(See Japanese page) |
(in English) |
This paper presents a method for automatically diagnosing Helicobacter pylori (H. pylori) infection based on EfficientNet using gastric endoscopic images. We use the images cut in endoscopic videos before the release frames for an augmentation strategy in our method. Moreover, to prevent overfitting of the training process, we use the flooding version of cross-entropy loss. Our method achieves high diagnostic performance in a complex endoscopic image dataset containing two domains and eight different gastric positions. |
Keyword |
(in Japanese) |
(See Japanese page) |
(in English) |
Helicobacter pylori infection / endoscopic image / EfficientNet / / / / / |
Reference Info. |
ITE Tech. Rep., vol. 45, no. 4, ME2021-5, pp. 23-26, Feb. 2021. |
Paper # |
ME2021-5 |
Date of Issue |
2021-02-11 (MMS, ME, AIT) |
ISSN |
Print edition: ISSN 1342-6893 Online edition: ISSN 2424-1970 |
Download PDF |
|