Go to: content | top | bottom | search
 
 
-
You are hereMedical Image Analysis Laboratory > Software

Software

Multi-channel MRI segmentation of eye structures and tumors | MBIS: Multivariate Bayesian Image Segmentation tool | fP-CMC: Fast Patch-based Continuous Min-Cut segmentation
 

Multi-channel MRI segmentation of eye structures and tumors

An open source software for computing the automatic segmentation of eye structures and tumors in 3D Magnetic Resonance Imaging.

The software is available inhttps://doi.org/10.5281/zenodo.400920

The testing data set is available inhttps://osf.io/5t3nq/

Works using this software should cite:

  • "Multi-channel MRI segmentation of eye structures and tumors using patient-specific features", C. Ciller, S. De Zanet, K. Kamnitsas, P. Maeder, B. Glocker, F.L. Munier, D. Rueckert, J.-Ph. Thiran; M. Bach Cuadra; R. Sznitman (2017), PLOS ONE 12(3): e0173900. doi: 10.1371/journal.pone.0173900‚Äč
  • "Virtual Machine and dataset for Multi-channel MRI segmentation of eye structures and tumors using patient-specific features", C. Ciller, S. De Zanet, K. Kamnitsas, P. Maeder, B. Glocker, F.L. Munier, D. Rueckert, J.-Ph. Thiran; M. Bach Cuadra; R. Sznitman (2017), https://doi.org/10.5281/zenodo.400920

journal.pone.0173900.g001.PNG

TOP ^

MBIS: Multivariate Bayesian Image Segmentation tool

An open source multivariate statistical n-classes clustering tool including graph-cuts optimization with specialization to brain Magnetic Resonance imaging.

 

Works using MBIS should cite:

Oscar Esteban, Gert Wollny, Sai Subrahmanyam Gorthi, María J. Ledesma-Carbayo, Jean-Philippe Thiran, Andrés Santos, Meritxell Bach Cuadra, MBIS: Multivariate Bayesian Image Segmentation tool, Comp Meth Prog Biomed 115(2):76–94, 2014.

DOI: 10.1016/j.cmpb.2014.03.003

 

You can download the code at https://github.com/oesteban/MBIS.

 

MBIS.png

TOP ^

fP-CMC: Fast Patch-based Continuous Min-Cut segmentation

This software presents a semi-supervised segmentation framework for B-mode ultrasound imaging. It is applicable to any kind of target and imaging settings. Our methodology uses a graph of image patches to represent the ultrasound image and user-assisted initialization with labels, which acts as soft priors. The segmentation problem is formulated as a continuous minimum cut problem and solved with an efficient optimization algorithm.

 

Works using fP-CMC should cite:

Anca Ciurte, Xavier Bresson, Olivier Cuisenaire, Nawal Houhou, Sergiu Nedevschi, Jean-Philippe Thiran, Meritxell Bach Cuadra, Semi-Supervised Segmentation of Ultrasound Images based on Patch Representation and Continuous Min Cut. Plos One, Volume 9, Number 7, July 2014. DOI: 10.1371/journal.pone.0100972.

 

To download the code please click here.

 

fPCMC_scheme.png

TOP ^

Search:
 Go
 
rss/atom
CIBM - Signal Processing Core, CHUV Unit - BH 08 - Rue du Bugnon 46 - CH-1011 Lausanne  - Switzerland  -  Tel. +41 21 314 67 75
Swiss University