| Presentation | 2021-03-15 Evaluation of Bayesian Active Learning for Segmentation of Liver and Spleen in Large Scale Abdominal MR Data Sets Bin Zhang, Yoshito Otake, Mazen Soufi, Masatoshi Hori, Noriyuki Tomiyama, Yoshinobu Sato, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Manual annotation in image segmentation is time-consuming and expensive. In order to obtain large number of annotated data set efficiently, Bayesian active learning has been proposed. The key component in the iteration in Bayesian active learning is the selection of query slices (or voxels) which maximize the performance of the model trained in the next iteration. We need to take account for (1) uncertainty estimated from the model trained in the previous iteration, i.e., the distance from the existing training data set, and (2) similarity among the query images. The large batch acquisition with diverse images far from the existing data set enables higher efficiency in active learning. In this study, we investigated the performance and efficiency of several Bayesian active learning approaches specifically for segmentation of liver and spleen in a realistic simulation study using 251 fully annotated abdominal MR data set. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Bayesian U-net / Bayesian active learning |
| Paper # | MI2020-60 |
| Date of Issue | 2021-03-08 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2021/3/15(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Imaging |
| 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 |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Evaluation of Bayesian Active Learning for Segmentation of Liver and Spleen in Large Scale Abdominal MR Data Sets |
| Sub Title (in English) | |
| Keyword(1) | Bayesian U-net |
| Keyword(2) | Bayesian active learning |
| 1st Author's Name | Bin Zhang |
| 1st Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 2nd Author's Name | Yoshito Otake |
| 2nd Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 3rd Author's Name | Mazen Soufi |
| 3rd Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 4th Author's Name | Masatoshi Hori |
| 4th Author's Affiliation | Kobe University, Graduate School of Medicine(Kobe University) |
| 5th Author's Name | Noriyuki Tomiyama |
| 5th Author's Affiliation | Osaka University, Graduate School of Medicine(Osaka University) |
| 6th Author's Name | Yoshinobu Sato |
| 6th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| Date | 2021-03-15 |
| Paper # | MI2020-60 |
| Volume (vol) | vol.120 |
| Number (no) | MI-431 |
| Page | pp.pp.62-65(MI), |
| #Pages | 4 |
| Date of Issue | 2021-03-08 (MI) |