Development of the automatic evaluation system for medical procedure by using deep learning technology
| Project/Area Number |
17K08917
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Medical sociology
|
|---|
| Research Institution | Shimane University |
|---|
Principal Investigator |
KENJI KARINO 島根大学, 学術研究院医学・看護学系, 講師 (20379689)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
廣瀬 誠 松江工業高等専門学校, 情報工学科, 准教授 (40367660)
岡本 覚 島根大学, 総合理工学部, 名誉教授 (10204033)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2019: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | Kinectセンサー / モーションキャプチャー / 機械学習 / BLS / 姿勢解析 / 胸骨圧 / 医学教育 / 医療手技 |
|---|
| Outline of Final Research Achievements |
In this study, we developed an automatic evaluation system for the BLS procedure using Kinect sensor as a motion capture. Commercially available of an evaluation type simulator for BLS is able to evaluate the speed, depth, and chest recoil of chest compressions by the in-side sensor. But the in-side sensor is just only determined match or not match the criteria of assessment. Which means that in-side sensor is difficult to find improvement points for the subjects. Therefore, we were developed new evaluation system by use the Kinect sensor. In this research, we developed an original program applied development tools provided by Microsoft according to the movement of BLS. As a result, this original program is able to measure the speed and depth of chest compression of the BLS with the same accuracy as the evaluation simulator. And when the quality of chest compressions is decreasing, the posture of the subject can be analyzed to point out improvements such as angle of arm, posture.
|
| Academic Significance and Societal Importance of the Research Achievements |
技術を評価する目的は、手技の良し悪しを見るだけではなく、技術の改善に役立てる必要がある。本研究は、モーションキャプチャーと機械学習を組み合わせたシステムにより、手技の特徴を見出すことで客観的な評価を可能にした。また、手技の特徴は技術を改善するための指標となる。手技によって特徴が異なるため、本システムをそのまま使用することはできないが、プログラムの開発をVisual Studio 2013という開発ツールを用いてC++言語とOpenCVを用いて行っており、比較的容易に手技に合わせたプログラム開発が可能である。本研究の成果は、遠隔診療などにも応用が可能であり、他産業の技術継承にも応用が可能である。
|
Report
(4 results)
Research Products
(8 results)
