/NeuriteOutgrowth

A tool for automatic neurite outgrowth and cell viability estimation using deep learning and graph theory.

Primary LanguageJupyter NotebookMIT LicenseMIT

Neurite Outgrowth Estimation Using Deep Learning & Graph Theory

A tool for automatic neurite outgrowth and cell viability estimation from microscopy images using deep learning and graph theory. It is optimized for Neuroblastoma cells in low power (20X) magnification and a dual FITC & DAPI channels setup. It can be used for large scale high-throughput drug screening and validation experiments.

image

Features

  • Estimate neurite outgrowth and toxicity for large scale experiments from microscopy images
  • Outlier removal algorithms for cleaner results
  • Graph representation of cell cultures and novel connectivity based features for neurite outgrowth
  • Neurite semantic segmentation
  • Nuclei instance segmentation from https://github.com/Lopezurrutia/DSB_2018
  • Cell instance segmentation
  • Cell foreground segmentation
  • Two neurite segmentaion datasets for live and fixed cells staining.

Getting Started

Installation

  1. Clone this repository

  2. Install dependencies

pip install -r requirements.txt
  1. Download the Mask RCNN weights (too large for Github) and place them in repository root directory.

Citation

To be writen :)