| Project/Area Number |
18K16600
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 56010:Neurosurgery-related
|
|---|
| Research Institution | Nihon University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2019: ¥260,000 (Direct Cost: ¥200,000、Indirect Cost: ¥60,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 深層学習 / 脳卒中 / 頭部外傷 / 画像診断 / 人工知能 / 画像認識 / 頭部CT画像 / 画像判定 / 頭部CT |
|---|
| Outline of Final Research Achievements |
Acute stroke and severe head injury require prompt diagnosis and professional treatment. However, not all medical institutions have specialists. Therefore, the diagnostic imaging may be delayed.
In recent years, a technique called deep learning has been in the limelight. The purpose of this study was to create a head CT image judgment device using a deep learning method to assist in medical diagnosis.
For CT images with high urgency and severity, the program was able to judge with an accuracy of over 90%.Then, the results analyzed by the workstation were installed in a compact and mass-produced device. The device was able to judge the CT image in a few seconds.It had the judgment accuracy and speed that could be used clinically.
|
| Academic Significance and Societal Importance of the Research Achievements |
急性期脳卒中や重症頭部外傷では迅速な診断および専門的加療が必要である。しかし全ての医療機関に専門家が配置されているわけではなく、適切な判断が行われない可能性がある。本研究では深層学習の手法を用いて頭部CT画像の判定装置を作成し、診断の補助として用いることを目的とした。
同様の目的で遠隔診療が考えられる。しかし、対応する医師の負担が生じることや、個人情報である医用画像を施設外に送信する必要がありセキュリティー上の懸念が生じる。本研究で開発した画像判定装置を用いればこれらの問題が解決され、適切な医療を受ける機会が確保出来ると考えられた。
|
