2021 Fiscal Year Final Research Report
Development of an AI-based automatic traumatic bleeding regions detection system
| Project/Area Number |
19K20661
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 90110:Biomedical engineering-related
|
|---|
| Research Institution | University of Toyama (2020-2021)
Chiba University (2019) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2022-03-31
|
| Keywords | 画像処理 |
|---|
| Outline of Final Research Achievements |
We developed a system that automatically detects "traumatic bleeding regions" in CT images by using image processing techniques in order to support diagnosis in emergency medical care. The purpose of our system is to support physicians in making prompt treatment decisions in emergency situations, and to prevent the loss of healing opportunities.
In this study, we proposed an algorithm to automatically detect bleeding regions in CT images by using two different approaches based on image processing techniques.
|
| Free Research Field |
医用画像処理
|
| Academic Significance and Societal Importance of the Research Achievements |
外傷による死亡は，10万人あたりおよそ30人の割合で発生している．実際に死亡した外傷患者の内，修正予測外死亡数（防ぎ得た可能性の高い外傷死亡者数）は40%に迫る数値である．提案手法によって，救急医による造影CTを用いた読影診断を支援することにより，出血の見落としや読影時間を低減させ，外傷患者の処置に専念する時間を増やすことが可能となる．
|
