| Presentation | 2020-01-29 Imbalanced Subarachnoid Hemorrhage data automatic detection by using SMOTE algorithm based on deep learning Zhongyang Lu, Masahiro Oda, Yuichiro Hayashi, Hayato Ito, Takeyuki Watadani, Osamu Abe, Masahiro Hashimoto, Masahiro Jinzaki, Kensaku Mori, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Based on deep learning techniques, the performance of image classification has made significant progress. Especially in the medical image processing field, the CNNs are broadly utilized. However, for the most problems in the real world, the numbers of every class in the data set are not equal, called imbalanced data. It causes a low recall of the minority class. In this paper, we apply the SMOTE method to alleviate the imbalanced problem on anomaly detection. Sequentially, we utilize this strategy on the Subarachnoid Hemorrhage (SAH) detection with imbalanced data based on deep learning techniques and discuss the efficiency. In this study, 33 cases of SAH data combined with 33 cases, and 100 cases of normal brain CT, respectively, are applied to support our experiments. We utilize F-measure and ROC curve for evaluating the trained models. Trained on the 33 cases SAH and 100 cases normal dataset, the model got 0.731 AUC score without SMOTE processing. With SMOTE, acquired 0.830 AUC score, and during SMOTE and data augmentation, the performance was improved into a 0.875 AUC score. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep learning / Imbalanced classification / Subarachnoid Hemorrhage / data augmentation |
| Paper # | MI2019-75 |
| Date of Issue | 2020-01-22 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2020/1/29(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | OKINAWAKEN SEINENKAIKAN |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Image Engineering, Analysis, Recognition, etc. |
| Chair | Yoshiki Kawata(Tokushima Univ.) |
| Vice Chair | Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
| Secretary | Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
| Assistant | Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging |
|---|---|
| Language | ENG-JTITLE |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Imbalanced Subarachnoid Hemorrhage data automatic detection by using SMOTE algorithm based on deep learning |
| Sub Title (in English) | |
| Keyword(1) | Deep learning |
| Keyword(2) | Imbalanced classification |
| Keyword(3) | Subarachnoid Hemorrhage |
| Keyword(4) | data augmentation |
| 1st Author's Name | Zhongyang Lu |
| 1st Author's Affiliation | Nagoya University(Nagoya Univ) |
| 2nd Author's Name | Masahiro Oda |
| 2nd Author's Affiliation | Nagoya University(Nagoya Univ) |
| 3rd Author's Name | Yuichiro Hayashi |
| 3rd Author's Affiliation | Nagoya University(Nagoya Univ) |
| 4th Author's Name | Hayato Ito |
| 4th Author's Affiliation | Nagoya University(Nagoya Univ) |
| 5th Author's Name | Takeyuki Watadani |
| 5th Author's Affiliation | Department of Radiology,The University of Tokyo Hospital(Department of Radiology,The Univ of Tokyo Hospital) |
| 6th Author's Name | Osamu Abe |
| 6th Author's Affiliation | Department of Radiology,The University of Tokyo Hospital(Department of Radiology,The Univ of Tokyo Hospital) |
| 7th Author's Name | Masahiro Hashimoto |
| 7th Author's Affiliation | Department of Radiology,Keio University School of Medicine(Department of Radiology,Keio Univ School of Medicine) |
| 8th Author's Name | Masahiro Jinzaki |
| 8th Author's Affiliation | Department of Radiology,Keio University School of Medicine(Department of Radiology,Keio Univ School of Medicine) |
| 9th Author's Name | Kensaku Mori |
| 9th Author's Affiliation | Nagoya University(Nagoya Univ) |
| Date | 2020-01-29 |
| Paper # | MI2019-75 |
| Volume (vol) | vol.119 |
| Number (no) | MI-399 |
| Page | pp.pp.47-52(MI), |
| #Pages | 6 |
| Date of Issue | 2020-01-22 (MI) |