Difference between revisions of "Resources"

From IACL
Jump to: navigation, search
(New page: ==<font color="#9f0000">RESOURCES</font>==)
 
(Again.)
 
(45 intermediate revisions by 6 users not shown)
Line 1: Line 1:
==<font color="#9f0000">RESOURCES</font>==
+
<meta name="title" content="Resources"/>
 +
{{TOCright}}
 +
{{h2|General Image Processing}}
 +
{{h3|GVF Software}}
 +
* 2D {{static|gvf/|GVF}} code for Matlab is [http://www.nitrc.org/frs/?group_id=271 available by following this link].
 +
* 2D Multigrid GVF code in C is [http://www.nitrc.org/frs/?group_id=271 available by following this link].
 +
* 3D GVF example Java code is [http://www.nitrc.org/plugins/scmcvs/cvsweb.php/toads-cruise/src/edu/jhu/ece/iacl/algorithms/gvf/GradVecFlowOptimized.java?rev=1.1;content-type=text%2Fplain;cvsroot=toads-cruise available here]. This 3D version is built around [http://www.nitrc.org/frs/?group_id=228 JIST].
 +
 
 +
 
 +
{{h3|JIST}}
 +
* The Java Image Science Toolkit (JIST) has a [http://www.nitrc.org/projects/jist/ project page] and [http://www.nitrc.org/frs/?group_id=228 downloads].
 +
 
 +
 
 +
{{h3|MGDM}}
 +
* Source code and demonstrations for the Multiple-object Geometric Deformable Model (MGDM) can be found on the [http://www.nitrc.org/projects/mgdm/ MGDM project page] hosted by NITRC.
 +
* A [https://iacl.jhu.edu/~john/mgdmMov.avi movie demo] of the decomposition and evolution of MGDM.
 +
 
 +
 
 +
 
 +
{{h2|Brain}}
 +
{{h3|2015 Longitudinal MS Lesion Segmentation Challenge}}
 +
* The [[MSChallenge|2015 Longitudinal MS Lesion Segmentation Challenge]] provides training and testing data for segmenting MS lesions over a multiple time-points of 14 patietns. '''[https://smart-stats-tools.org/lesion-challenge Results can still be submitted for testing through the automated website].'''
 +
 
 +
 
 +
{{h3|Validation Data for Cortical Reconstruction Algorithms}}
 +
* The [[cortical_data/|cortical validation resource]] for evaluation of cortical reconstruction algorithms on both normal subjects and subjects with White Matter lesions.
 +
 
 +
 
 +
{{h3|Cerebellar Lobule Segmentation using Graph Cuts}}
 +
* The graph-cut based segmentation of the cerebellum described in {{pub|author=Z. Yang, C. Ye, J.A. Bogovic, A. Carass, B.M. Jedynak, S.H. Ying, and J.L. Prince|title=Automated Cerebellar Lobule Segmentation with Application to Cerebellar Structural Analysis in Cerebellar Disease|jrnl=ni|number=127:435-444|when=2016|doi=10.1016/j.neuroimage.2015.09.032}}
 +
* {{iacl|~amod/cerlobule_seg_release_06_01_2016.tar.gz|Cerebellar Lobule Segmentation Code}} can be used to parcellate the cerebellum into lobules given a T1w MRI image.
 +
 
 +
 
 +
{{h3|Temporal Filtering for Consistent Segmentation}}
 +
* The temporal filtering of longitudinal MR images of the brain described in {{pub|author=S. Roy, A. Carass, J. Pacheco, M. Bilgel, S.M. Resnick, J.L. Prince, and D.L. Pham|title=Temporal filtering of longitudinal brain magnetic resonance images for consistent segmentation|journal=NeuroImage: Clinical|number=11:264-275|when=2016|doi=doi:10.1016/j.nicl.2016.02.005}}
 +
* Matlab executables are {{iacl|~roy/softwares/4dfilter_Feb19-2016.zip|available}}
 +
 
 +
 
 +
{{h3|PET Attentuation Correction}}
 +
* The PET attentuation correction method described in {{pub|author=S. Roy, W.-T. Wang, A. Carass, J.L. Prince, J.A. Butman, and D.L. Pham|title=[[PET Attenuation Correction using Synthetic CT from Ultrashort Echo-time MRI|PET Attenuation Correction Using Synthetic CT from Ultrashort Echo-Time MR Imaging]]|journal=Jrnl. of Nuclear Medicine|number=55:1-7|when=2014|doi=10.2967/jnumed.114.143958}}
 +
* Matlab executables are {{iacl|~roy/softwares/CTsynthesis.zip|available}}.
 +
 
 +
 
 +
{{h3|Rician Mixture Model}}
 +
* The Rician mixture model for segmenting the  brain is described in {{pub|author=S. Roy, A. Carass,  P.-L. Bazin, S.M. Resnick, and J.L. Prince|title=Consistent Segmentation using a Rician Classifier|jrnl=mia|number=16(2):524-535|when=2012|doi=doi:10.1016/j.media.2011.12.001|pubmed=22204754|pdf=/proceedings/iacl/2012/RoyxMIA13-Rician_Classifier.pdf}}
 +
* Matlab executables are {{iacl|~roy/softwares/ricemixmodel3D.zip|available}}.
 +
 
 +
 
 +
{{h3|Progression Score Model}}
 +
* The Progression Score Model Toolkit, including the expectation-maximization (EM) algorithm for fitting the nonlinear mixed effects model, can be obtained from [http://www.nitrc.org/projects/progscore/ the NITRC project page].
 +
 
 +
 
 +
{{h2|IMAGE Synthesis}}
 +
{{h3|MIMECS}}
 +
* MIMECS is described in: {{pub|author=S. Roy, A. Carass, and J.L. Prince|title=[[Magnetic Resonance Image Example Based Contrast Synthesis|Magnetic Resonance Image Example Based Contrast Synthesis]]|jrnl=tmi|number=32(12):2348-2363|when=2013|doi=10.1109/TMI.2013.2282126|pdf=/proceedings/iacl/2013/RoyxTMI13-MIMECS.pdf}}
 +
* Code and sample data is available on our NITRC Project Page titled [http://www.nitrc.org/projects/image_synthesis/ Image Synthesis].
 +
 
 +
 
 +
{{h3|Subject Specific Dictionary Learning (S3DL)}}
 +
* S3DL described in {{pub|author=S. Roy, A. Carass, J.L. Prince, and D.L. Pham|title=Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation|conf=mlmi2014|doi=10.1007/978-3-319-10581-9_31|period=}} and {{pub|author=S. Roy, Q. He, E. Sweeney, A. Carass, D.S. Reich, J.L. Prince, and D.L. Pham|title=Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation|journal=IEEE Journal of Biomedical and Health Informatics|number=19(5):1598-1609|when=2015|doi=10.1109/JBHI.2015.2439242}}
 +
* Matlab executables are {{iacl|~roy/softwares/S3DL_withlesion.zip|available}}.
 +
 
 +
 
 +
{{h3|REPLICA}}
 +
* Regression Ensembles with Patch Learning for Image Contrast Agreement (REPLICA) described in {{pub|author=A. Jog, A. Carass, S. Roy, D.L. Pham, and J.L. Prince|title=Random Forest Regression for Magnetic Resonance Image Synthesis|jrnl=mia|number=35:475-488|when=2017|doi=10.1016/j.media.2016.08.009|pubmed=27607469}}
 +
* Code and sample data is available on our NITRC Project Page titled [http://www.nitrc.org/projects/image_synthesis/ Image Synthesis].
 +
 
 +
 
 +
{{h2|Cardiac}}
 +
{{h3|HARP}}
 +
* For MATLAB demonstration software send an email to [[Image:harp_email.jpg]] and expect a reply within five business days. We also have a collection of [[HARP FAQ|frequently asked questions]] about our HARP software.
 +
 
 +
 
 +
 
 +
{{h2|Retinal}}
 +
{{h3|AURA Tools}}
 +
* The [http://www.nitrc.org/projects/aura_tools/ AURA Tools] software package allows for the automated processing and segmentation of Optical Coherence Tomography images of the macula cube. It is available from the NITRC website.
 +
:* Version 1.2 includes the software originally presented in: {{pub|author=A. Lang, A. Carass, M. Hauser, E.S. Sotirchos, P.A. Calabresi, H.S. Ying, and J.L. Prince|title=[[Retinal layer segmentation of macular OCT images|Retinal layer segmentation of macular OCT images using boundary classification]]|jrnl=bmoe|number=4(7):1133-1152|when=2013|doi=10.1364/BOE.4.001133|pmcid=3704094|pdf=/proceedings/iacl/2013/LanxBOE13-Retinal_layer_OCT.pdf}}
 +
 
 +
 
 +
{{h3|ASiMOV}}
 +
* The Automated segmentation of mouse OCT volumes (ASiMOV) toolkit is now available from the [http://www.nitrc.org/projects/aura_tools/ AURA Tools NITRC page].
 +
:* Version 0.1 includes the software originally presented in: {{pub|author=B.J. Antony, B.-J. Kim, A. Lang, A. Carass, J.L. Prince, and D.J. Zack|title=Automated segmentation of mouse OCT volumes (ASiMOV): Validation & clinical study of a light damage model|journal=PLoS ONE|number=12(8);e0181059|when=2017|doi=10.1371/journal.pone.0181059|pubmed=28817571}}
 +
:* Direct download link for [https://www.nitrc.org/frs/download.php/10836/ASiMOV-0.1.zip ASiMOV v0.1]
 +
 
 +
 
 +
{{h3|OCT MS and Healthy Controls Data}}
 +
* Data resource for Multiple Sclerosis and Healthy Controls:
 +
:* {{iacl|~aaron/data/OCT_Manual_Delineations-2018_June_29.zip|OCT_Manual_Delineations-2018_June_29.zip}} (1.8G) contains 35 OCT volumes from a Spectralis Scanner with corresponding manual delineations of nine retinal boundaries. The cohort contains 14 healthy controls and 21 multiple sclerosis patients with age and gender information.
 +
 
 +
 
 +
{{:Mouse_data}}

Latest revision as of 16:10, 30 June 2018

General Image Processing

GVF Software


JIST


MGDM

  • Source code and demonstrations for the Multiple-object Geometric Deformable Model (MGDM) can be found on the MGDM project page hosted by NITRC.
  • A movie demo of the decomposition and evolution of MGDM.


Brain

2015 Longitudinal MS Lesion Segmentation Challenge


Validation Data for Cortical Reconstruction Algorithms

  • The cortical validation resource for evaluation of cortical reconstruction algorithms on both normal subjects and subjects with White Matter lesions.


Cerebellar Lobule Segmentation using Graph Cuts

  • The graph-cut based segmentation of the cerebellum described in Z. Yang, C. Ye, J.A. Bogovic, A. Carass, B.M. Jedynak, S.H. Ying, and J.L. Prince, "Automated Cerebellar Lobule Segmentation with Application to Cerebellar Structural Analysis in Cerebellar Disease", NeuroImage, 127:435-444, 2016. (doi)
  • Cerebellar Lobule Segmentation Code can be used to parcellate the cerebellum into lobules given a T1w MRI image.


Temporal Filtering for Consistent Segmentation

  • The temporal filtering of longitudinal MR images of the brain described in S. Roy, A. Carass, J. Pacheco, M. Bilgel, S.M. Resnick, J.L. Prince, and D.L. Pham, "Temporal filtering of longitudinal brain magnetic resonance images for consistent segmentation", NeuroImage: Clinical, 11:264-275, 2016. (doi)
  • Matlab executables are available


PET Attentuation Correction


Rician Mixture Model

  • The Rician mixture model for segmenting the brain is described in S. Roy, A. Carass, P.-L. Bazin, S.M. Resnick, and J.L. Prince, "Consistent Segmentation using a Rician Classifier", Medical Image Analysis, 16(2):524-535, 2012. (PDF) (doi) (PubMed)
  • Matlab executables are available.


Progression Score Model

  • The Progression Score Model Toolkit, including the expectation-maximization (EM) algorithm for fitting the nonlinear mixed effects model, can be obtained from the NITRC project page.


IMAGE Synthesis

MIMECS


Subject Specific Dictionary Learning (S3DL)

  • S3DL described in S. Roy, A. Carass, J.L. Prince, and D.L. Pham, "Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation", Fifth International Workshop on Machine Learning in Medical Imaging (MLMI 2014), Boston, MA, September 14, 2014. (doi) and S. Roy, Q. He, E. Sweeney, A. Carass, D.S. Reich, J.L. Prince, and D.L. Pham, "Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation", IEEE Journal of Biomedical and Health Informatics, 19(5):1598-1609, 2015. (doi)
  • Matlab executables are available.


REPLICA

  • Regression Ensembles with Patch Learning for Image Contrast Agreement (REPLICA) described in A. Jog, A. Carass, S. Roy, D.L. Pham, and J.L. Prince, "Random Forest Regression for Magnetic Resonance Image Synthesis", Medical Image Analysis, 35:475-488, 2017. (doi) (PubMed)
  • Code and sample data is available on our NITRC Project Page titled Image Synthesis.


Cardiac

HARP

  • For MATLAB demonstration software send an email to Harp email.jpg and expect a reply within five business days. We also have a collection of frequently asked questions about our HARP software.


Retinal

AURA Tools

  • The AURA Tools software package allows for the automated processing and segmentation of Optical Coherence Tomography images of the macula cube. It is available from the NITRC website.


ASiMOV

  • The Automated segmentation of mouse OCT volumes (ASiMOV) toolkit is now available from the AURA Tools NITRC page.
  • Version 0.1 includes the software originally presented in: B.J. Antony, B.-J. Kim, A. Lang, A. Carass, J.L. Prince, and D.J. Zack, "Automated segmentation of mouse OCT volumes (ASiMOV): Validation & clinical study of a light damage model", PLoS ONE, 12(8);e0181059, 2017. (doi) (PubMed)
  • Direct download link for ASiMOV v0.1


OCT MS and Healthy Controls Data

  • Data resource for Multiple Sclerosis and Healthy Controls:
  • OCT_Manual_Delineations-2018_June_29.zip (1.8G) contains 35 OCT volumes from a Spectralis Scanner with corresponding manual delineations of nine retinal boundaries. The cohort contains 14 healthy controls and 21 multiple sclerosis patients with age and gender information.


IACL Mouse Data

  • In conjunction with the paper: B. J. Antony, B.-J. Kim, A. Lang, A. Carass, J. L. Prince, and D. J. Zack, “Automated Segmentation of Mouse OCT Volumes (ASiMOV): Validation & Clinical Study of a Light Damage Model”, PLOS ONE, In Press. We release mice_data_2017-July-18.zip which is the data and results presented in this paper. When using this data please cite the PLOS ONE paper. The download is 15.2GB.