[![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2FBBQuercus%2FdeepBlink.svg?type=shield)](https://app.fossa.com/projects/git%2Bgithub.com%2FBBQuercus%2FdeepBlink?ref=badge_shield)
deepBlink
Threshold independent detection and localization of diffraction-limited spots.
Overview
In biomedical microscopy data, a common task involves the detection of diffraction-limited spots that visualize single proteins, domains, mRNAs, and many more. These spots were traditionally detected with mathematical operators such as Laplacian of Gaussian. These operators, however, rely on human input ranging from image-intensity thresholds, approximative spot sizes, etc. This process is tedious and not always reliable. DeepBlink relies on neural networks to automatically find spots without the need for human intervention. DeepBlink is available as a ready-to-use command-line interface.
Usage | Example |
---|---|
Installation
This package is built for Python versions newer than 3.6.
DeepBlink can easily be installed with pip:
pip install deepblink
Additionally for GPU support, install tensorflow-gpu
through pip and with the
appropriate CUDA
and cuDNN
verions matching your GPU setup.
Usage
Inferencing on deepBlink is performed at the command line as follows:
deepblink [-h] [-o OUTPUT] [-t {csv,txt}] [-r RADIUS] [-v] [-V] MODEL INPUT
More detailed information is availabe in our documentation.
[![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2FBBQuercus%2FdeepBlink.svg?type=large)](https://app.fossa.com/projects/git%2Bgithub.com%2FBBQuercus%2FdeepBlink?ref=badge_large)