vesicle: Volumetric Evaluation of Synaptic Inferfaces using Computer vision at Large Scale

vesicle provides a context-aware method for scalable synapse detection in anisotropic electron microscopy data. We provide two methods for object detection: vesicle-rf and vesicle-cnn, which have computational and performance tradeoffs.

This work also resulted in the creation of a general-purpose object detection framework that can be used in a LONI pipelining environment. We explain this detection paradigm and provide vesicle-rf code as an example.

[ZIP] [TAR.GZ]

vesicle Contact Us

If you have questions about vesicle, or have data to analyze, let us know: support@neurodata.io

Documentation

• Introduction
• Configuration
• NeuroData
• Frequently Asked Questions (FAQ)

Tutorials

• vesicle-rf
• vesicle-cnn

Paper

• BMVC 2015
• vesicle results

Further Reading

• vesicle-rf Functions
• vesicle-rf Utilities
• vesicle-cnn Functions
• LONI Modules
• Gitter chatroom
• Mailing List
• Github repo
• Release Notes

If you use vesicle or its data derivatives, please cite:

William Gray Roncal, Michael Pekala, Verena Kaynig-Fittkau, Dean M Kleissas, Joshua T Vogelstein, Hanspeter Pfister, Randal Burns, R Jacob Vogelstein, Mark A Chevillet and Gregory D Hager. VESICLE: Volumetric Evaluation of Synaptic Interfaces using Computer Vision at Large Scale. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 81.1-81.13. BMVA Press, September 2015.