2021 Fiscal Year Final Research Report
Artificial intelligence assisted endoscopy system targeting on automated detection
| Project/Area Number |
19K17504
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 53010:Gastroenterology-related
|
|---|
| Research Institution | Showa University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2022-03-31
|
| Keywords | 人工知能 / 大腸癌 / 大腸ポリープ / 大腸内視鏡 |
|---|
| Outline of Final Research Achievements |
In colonoscopy, it is an urgent issue to prevent tumor lesions from being missed. In this study, we developed a software program that assists endoscopists in detecting lesions using artificial intelligence (AI) and validated the software in a real clinical setting. The software runs in real time basis, and when a polyp appears on an endoscopic image, the software prompts the endoscopist to detect the lesion by indicating the sound and the location of the polyp with a rectangle. We conducted a prospective study using this AI. It was found that the detection rate of neoplastic polyps was higher in the group using the software. Based on these results, it was suggested that the risk of developing cancer in the future could be reduced if the patient underwent testing using AI.
|
| Free Research Field |
消化器内科
|
| Academic Significance and Societal Importance of the Research Achievements |
現時点では大腸内視鏡検査1回あたり、約25％程度の腫瘍性ポリープが見逃されていることが指摘されている。また大腸癌検診目的に大腸内視鏡検査を受けた数年後に発見される大腸癌の約60％がこのような見逃しに起因している。本研究成果のAIソフトウェアを使用することによって、見逃しを減らし結果的に大腸癌のり患リスクを低減できることが期待されている。
|
