Automated Diagnosis of Obstetrics and Gynecology MRI Using Deep Learning
| Project/Area Number |
20K16780
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 52040:Radiological sciences-related
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2020: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | Deep learning / MRI / Endometrial cancer / CNN / Segmentation / endometrial cancer / deep learning / segmentation / 子宮体癌 / 子宮頸癌 / 深層学習 / セグメンテーション / 子宮 / 卵巣 |
|---|
| Outline of Research at the Start |
近年の医用画像解析では、画像から腫瘍の悪性度や予後など、解剖学的情報以上のデータを抽出する研究が行われている。従来の解析手法では、画像上での腫瘍の関心領域設定、画像的特徴量の設定を手動で行うのが一般的であるが、関心領域設定の労力が大きい、適切な特徴量の選択が難しい、という問題点が存在する。一方で、CNNでは、画像データ自体を直接解析することができるため、関心領域や特徴量設定の過程を全て自動化可能である。本研究では申請者らがMRI上での子宮の自動セグメンテーションを実現した手法を応用し、実臨床で適用可能な産婦人科MRIの自動診断プログラムを作成する。
|
| Outline of Final Research Achievements |
In this project, we realized automatic segmentation and staging of uterine endometrial cancer on MRI using convolutional neural networks, and reported the results at national and international conferences and in research papers. In parallel, we are continuing research to extend the same method to bladder cancer imaging, and have already reported some of the results in papers. We also incorporated Vision Transformer, a new deep learning method proposed during the research period, and showed that the method is applicable to medical image analysis of obstetrics and gynecology and urology. In the future, we plan to conduct a multicenter study for external validation of the developed model.
|
| Academic Significance and Societal Importance of the Research Achievements |
最近ではいわゆる人工知能を用いた医用画像解析が盛んに行われているが、産婦人科領域に関する研究報告は比較的少なかった。本研究では、MRI上で子宮体癌の検出や病期診断（深達度の判定）の自動化を実現することで、産婦人科領域の画像診断における深層学習の有用性を示した。この種の研究報告が増えることで、他の領域と同様に、産婦人科画像診断の質的向上や個別化医療を目指した画像解析が進展していくと考えられる。
|
Report
(4 results)
Research Products
(16 results)
-
-
-
-
-
-
-
-
-
-
[Presentation] Automatic segmentation of bladder cancer on diffusion weighted images using a convolutional neural network2022
Author(s)
Yusaku Moribata , Yasuhisa Kurata , Mizuho Nishio , Aki Kido , Satoshi Otani , Yuki Himoto , Naoko Nishio , Akihiro Furuta , Kimihiko Masui , Takashi Kobayashi , Yuji Nakamoto
Organizer
2022 ISMRM & SMRT Annual Meeting & Exhibition
Related Report
Int'l Joint Research
-
-
[Presentation] Automatic segmentation of bladder cancer on MRI using a convolutional neural network and reproducibility of radiomics features2022
Author(s)
Yusaku Moribata, Yasuhisa Kurata, Mizuho Nishio, Aki Kido, Satoshi Otani, Yuki Himoto, Naoko Nishio, Akihiro Furuta, Kimihiko Masui, Takashi Kobayashi, Yuji Nakamoto
Organizer
2022 ISMRM & SMRT Annual Meeting & Exhibition
Related Report
Int'l Joint Research
-
-
[Presentation] Automatic segmentation of uterine endometrial cancer on MRI with convolutional neural network2021
Author(s)
Yasuhisa Kurata, Mizuho Nishio, Yusaku Moribata, Aki Kido, Yuki Himoto, Satoshi Otani, Koji Fujimoto, Masahiro Yakami, Sachiko Minamiguchi, Masaki Mandai, Yuji Nakamoto
Organizer
2021 ISMRM & SMRT Annual Meeting & Exhibition
Related Report
Int'l Joint Research
-
-
