Improvement of temporal resolution of scanning ion conductance microscopy using machine learning

2021 Fiscal Year Final Research Report

• Project/Area Number: 20K15309
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 34020:Analytical chemistry-related
• Research Institution: Tohoku University
• Principal Investigator: Ida Hiroki 東北大学, 学際科学フロンティア研究所, 助教 (80844422)
• Project Period (FY): 2020-04-01 – 2022-03-31
• Keywords: 走査型イオンコンダクタンス顕微鏡 / 電気化学 / 単一細胞計測 / 機械学習

Outline of Final Research Achievements

Visualization of nanoscale structures on living cell membranes allows for further understanding the details of cellular mechanisms. Scanning ion conductance microscopy (SICM) is a visualization technique for sub-micrometer structures on cell membranes. To obtain further information of rapid cellular reaction at nanoscale, it was aimed to improve temporal resolution of SICM using machine learning.
To collect large amount of training data needed for machine learning, a new SICM system was developed for long-term measurements. Moreover, high quality images for machine learning could be obtained using this system. Also, a program was developed to convert various sets of SICM data into training data.

Free Research Field

分析化学

Academic Significance and Societal Importance of the Research Achievements

外界と細胞を繋げている細胞膜のナノスケール形状を連続的に評価することは、細胞機能の理解を深める上で重要である。この様なナノ構造を生きた状態で可視化できる走査型イオンコンダクタンス顕微鏡の時間分解能をさらに向上させることで、観察できる細胞現象を広げ、その直接的な評価が可能になる。また、本研究を更に発展させることで、既に取得した画像や既存の装置系に対しても追加で情報を引き出すことが出来るようになり、解像度の向上などが見込める。