Related Experiment Video
Updated: May 14, 2025
10:23
Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management
Published on: June 23, 2023
2.2K
Microscope Upcycling: Transforming legacy microscopes into automated cloud-integrated imaging systems.
Drew Ehrlich1,2, Yohei Rosen1,3, David F Parks1,4
1UC Santa Cruz Genomics Institute, University of California, Santa Cruz, Santa Cruz, CA, USA.
Hardwarex
|April 11, 2025
Summary
Modern computerized microscopes offer benefits but are expensive. This study details hardware and software upgrades to make legacy inverted microscopes fully automated for machine learning microscopy data collection.
Area of Science:
- Biological imaging
- Laboratory automation
- Machine learning applications
Background:
- Computerized microscopes enhance biological research but are costly for academic labs.
- High costs hinder the creation of large, consistent datasets for machine learning analysis.
Purpose of the Study:
- To adapt legacy inverted microscopes with modern computerized features.
- To overcome cost barriers for advanced microscopy data acquisition in academic settings.
Main Methods:
- Implementing hardware modifications on older inverted microscopes.
- Developing software for automated X-Y positioning, focus stacking, and image acquisition.
- Establishing automated image storage protocols.
Main Results:
- Successfully automated key functions of legacy inverted microscopes.
- Enabled consistent, large-scale dataset generation for machine learning.
- Demonstrated a cost-effective approach to advanced microscopy.
Conclusions:
- Legacy laboratory microscopes can be upgraded to modern computerized standards.
- This approach democratizes access to advanced microscopy for machine learning in academia.
- Facilitates improved data analysis and sharing in biological research.
