DETECTION OF SESSILE SERRATED ADENOMA/POLYPS USING CONVOLUTIONAL NEURAL NETWORK
| Project/Area Number |
18K08010
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 53010:Gastroenterology-related
|
|---|
| Research Institution | Fukushima Medical University |
|---|
Principal Investigator |
TOGASHI KAZUTOMO 福島県立医科大学, 公私立大学の部局等, 教授 (10316531)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
歌野 健一 福島県立医科大学, 公私立大学の部局等, 准教授 (10728158)
朱 欣 会津大学, コンピュータ理工学部, 上級准教授 (70448645)
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 大腸腫瘍 / 大腸内視鏡検査 / コンピュータ自動診断 / 早期大腸癌 / 大腸鋸歯状病変 / sessile serrated lesions / CAD / artificial intelligence / computer-aided diagnosis / colorectal neoplasm / sessile serrated lesion / colonoscopy / ポリープ検出率 / 偽陽性率 / 自動解析アルゴリズム / 大腸ポリープ / ＳＳＬ / ＡＩ / Artifial Intelligence / colon polyp / sessile serrated adenoma / AI診断 |
|---|
| Outline of Final Research Achievements |
During colonoscopic procedures, endoscopists feel heavy mental burden to prevent from missing colorectal polyps. Therefore, computer-aid diagnosis (CADx) system is expected to relieve their burden. In this series of the research projects, we started developing a CADx system to detect small polyps, and we are now working on a validation trial in a clinical setting. Meanwhile we have developed another CADx system to propose a treatment strategy for early-stage colorectal cancers. After provisionally developing a CADx based on small number of endoscopic images, we have finally developed the CADx superior or equivalent to expert colonoscopists in diagnostic performance, by collecting over five thousand of the images from 10 hospitals across Japan. In addition, we have also developed a CADx to differentiate adenomatous from serrated lesions but failed to create a CADx to identify sessile serrated lesions. It is a next issue to be addressed.
|
| Academic Significance and Societal Importance of the Research Achievements |
大腸癌は、腺腫や鋸歯状病変などの大腸ポリープから発生し、この内視鏡的切除により大腸癌の発生は抑制されることは実証されている。しかし、大腸内視鏡検査による大腸ポリープ見落とし率は25%にまで達するとされ、大腸内視鏡医の精神的・肉体的負担は大きい。この研究では、世界的に普及している白色光非拡大内視鏡画像において、効果的に機能するコンピュータ自動診断装置の開発に成功し、実用化に向けての第一歩を踏み出した。開発したシステムを利用することにより、第一には内視鏡医の負担軽減が実現できるが、大腸内視鏡診療における医療の均てん化につながることも期待され、若手医師の教育での活用も想定される。
|
Report
(4 results)
Research Products
(24 results)
-
-
[Journal Article] Diagnostic performance of artificial intelligence to identify deeply invasive colorectal cancer on non-magnified plain endoscopic images.2020
Author(s)
Nakajima Y, Zhu X, Nemoto D, Li Q, Guo Z, Katsuki S, Hayashi Y, Utano K, Aizawa M, Takezawa T, Sagara Y, Shibukawa G, Yamamoto H, Lefor AK, Togashi K
-
Journal Title
Endosc Int Open
Volume: 8
Issue: 10
Pages: E1341-E1348
DOI
Related Report
Peer Reviewed / Open Access
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] A MACHINE-LEARNING ALGORITHM CAN DETECT DIMINUTIVE COLORECTAL POLYPS: READING TEST IN COMPARISON WITH HUMAN2019
Author(s)
Xin Zhu, Daiki Nemoto, Zhe Guo, Yu Wang, Qin Li, Masato Aizawa, Kenichi Utano, Noriyuki Isohata, Shungo Endo, David G Hewett, Kazutomo Togashi
Organizer
Digestive Disease Week 2019
Related Report
Int'l Joint Research
-
[Presentation] Identification of Deeply Invasive Colorectal Cancer on Non-Magnified Endoscopic Images Using Artificial Intelligence2019
Author(s)
Xin Zhu, Daiki Nemoto, Takaya Mizuno, Yuki Nakajima, Kenichi Utano, Masato Aizawa, Takahito Takezawa, Yuichi Sagara, Goro Shibukawa, Hironori Yamamoto, David G Hewett, Kazutomo Togashi
Organizer
Digestive Disease Week 2019
Related Report
Int'l Joint Research
-
-
-
