Coder Social home page Coder Social logo

atma's Introduction

ATMA project

ATMA (Automated Tracer for Myelinated Axons) is a user-friendly tool for interactive reconstruction of the geometry of fibers inside a peripheral nerve on its high resolution serial section images. Another feature of ATMA is the automatic detection of the nodes of Ranvier within this nerve. Most analysis operations are performed on a data sub-volume, followed by complete volume analysis in batch mode. Using it requires no experience in machine learning or image processing.

Key Words: Integer Linear Programing, Hungarian Algorithm, Random Forest, Union Finder, Image Analysis

Install

Check out the latest version with the command:

git clone [email protected]:RWalecki/ATMA.git

Quick Start (GUI)

Run the ATMA GUI:

cd ATMA
./run.sh
  1. Select Volume by clicking on 'Load Raw/Prediction Data'.

  2. Set range of sub volume (should not be larger than 100010001000 voxel). ATMA-GUI

  3. Enter initial parameter and run Axon Classification. ATMA-GUI

  4. Train Node Classifier. The "Zoom-in/out" button triggers the node-view. ATMA-GUI This image below shows a node of Ranvier (left) and a gap that occurs due to under-segmentation (right). ATMA-GUI

  5. Apply Batch Processing. The complete volume will be processed using the previously obtained parameters for classification (step 3) and the recently trained classifier for node of Ranvier detection (step 4).

Quick Start (CLT)

ATMA contains additional methods for axon segmentation and axon classification that are not implemented in the GUI version. These methods can be executed directly from the source code. (Note: do not forget to add the folder that contains ATMA to your PYTHONPATH)

import ATMA
import h5py


pred = h5py.File("./test.h5")["volume/data"]

#SEGMENTATION
a=ATMA.Segmentation.BioData.Nerve( pred )
a.sigmaSmooth = 0.7
a.thresMembra = 0.7
a.sizeFilter = [20,1000]
a.run()
Axon_bin = a.seg


#Gap Closing
b=GapClosing.Tokenizer.Data2Token( Axon_bin )
b.minSize = 3000
b.run()
Axon_id = b.data

Testing

nosetests 

REQUIREMENTS (CLT)

  • Python (tested with 2.7.4)
  • numpy (tested with 1.7.1)
  • vigra (tested with 1.8.0)
  • h5py (tested with 2.2.0b1)
  • munkres (tested with 1.0.6)

ADDITIONAL REQUIREMENTS FOR GUI VERSION

  • PyQt4 (tested with 4.10.3)
  • MayaVi (tested with 4.3.0)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.