Synaptic Vesicles Detection and Localization
The identification of synaptic vesicles in Electron Microscopy (EM) imaging can be an incredibly time-consuming task for researchers who are attempting to study aspects of cognition like information transfer or integration. In order to combat this, Barbara Imbrosci and colleagues created a Python-based synaptic vesicle classifier algorithm to identify neurotransmitter vesicles in EM images using Pytorch. The algorithm allows for efficient and automated identification of vesicles by use of an artificial neural network. The team utilized Convolutional Neural Networks (CNN) along with a segmentation algorithm that incorporates connected-component labeling and clustering to produce an output of an Excel file containing an overall summary of the total detected vesicles for each analyzed image. This is accompanied by individual sheets for each image which detail vesicle positions, distances to the nearest vesicle in nanometers, and the estimated area for each identified vesicle in square nanometers. They also created a GUI to make the classifier code accessible to everyone. More about the publication can be found here, and code to train the classifier and a guide to using the GUI is available on GitHub, along with code used for data analysis.
This research tool was created by your colleagues. Please acknowledge the Principal Investigator, cite the article in which the tool was described, and include an RRID in the Materials and Methods of your future publications. RRID: SCR_024910
Special thanks to Ellie Bashaw, a neuroscience undergraduate at American University, for providing this project summary.
Access the code from GitHub!
Check out the repository on GitHub.
Read more about it!
Check out more about the development and validation of this project from the eNeuro publication!
Check out projects similar to this!