Discrimination of multi-drug resistant bacteria by machine learning.
| Project/Area Number |
17K08827
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Bacteriology (including mycology)
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
|
|---|
| 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: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 多剤耐性菌 / 電子顕微鏡 / 機械学習 / 細菌 |
|---|
| Outline of Final Research Achievements |
The emergence of multidrug-resistant bacteria is a global problem of today, and overcoming infectious diseases is one of the important medical issues. There is an urgent need to develop a method for suppressing the emergence of resistant bacteria, and a rapid detection method is required. The purpose of this study is to establish the image discrimination method of resistant bacteria using machine learning, paying attention to the morphological changes occurring in the process of multidrug resistance of bacteria.
As a result of working on the development of machine learning discrimination of electron microscope images using enoxacin resistant strains, we succeeded in image discrimination with accuracy of 90%. Furthermore, we succeeded in extracting and visualizing the structural features of resistant bacteria.
|
| Academic Significance and Societal Importance of the Research Achievements |
多剤耐性菌による感染症は世界的な問題であり、医療現場において耐性菌の出現を予測し感染拡大防止を講じる対策法の開発が重要な課題となっている。本研究は人工知能による画像識別法を用いて薬剤耐性菌の自動判別を行う学習アルゴリズムの構築に成功した。この成果により、多剤耐性化プロセスで生じる形態の変化から耐性菌の出現を予測し、院内感染拡大予防に役立つ情報基盤が提供できると考えられる。
|
Report
(4 results)
Research Products
(6 results)
