Difference between revisions of "DBP2:MIND:Roadmap"

From NAMIC Wiki
Jump to: navigation, search
 
(31 intermediate revisions by 3 users not shown)
Line 3: Line 3:
 
=Brain Lesion Analysis in Neuropsychiatric Systemic Lupus Erythematosus=
 
=Brain Lesion Analysis in Neuropsychiatric Systemic Lupus Erythematosus=
  
==Objective==
+
[[Image:BrainVentriclesAndLesions.png‎|thumb|280px|Lesion volumes in yellow with ventricles and brain slice]]
We would like to create an end-to-end application entirely within NA-MIC Kit allowing individual analysis of white matter lesions. Such a workflow applied to lupus patients is one of goals of the MIND DBP. This page describes the technology roadmap for lesion analysis in the NA-MIC Kit. The basic components necessary for this project are:
+
=='''Objective'''==
 +
This page describes the technology roadmap for lesion analysis in the NA-MIC Kit. Our objective is to create an end-to-end application allowing individual analysis of white matter lesions. This workflow applied to lupus patients is one of goals of the [[DBP2:MIND:Introduction|MIND DBP]]. The basic components necessary for this project are:
 
* '''Registration''': co-registration of T1-weighted, T2-weighted, and FLAIR images
 
* '''Registration''': co-registration of T1-weighted, T2-weighted, and FLAIR images
 
* '''Tissue segmentation''': Should be multi-modality, correcting for intensity inhomogeneity and work on non-skull-stripped data.
 
* '''Tissue segmentation''': Should be multi-modality, correcting for intensity inhomogeneity and work on non-skull-stripped data.
 
* '''Lesion Localization''':  Each unique lesion should be detected and anatomical location summarized  
 
* '''Lesion Localization''':  Each unique lesion should be detected and anatomical location summarized  
 
* '''Lesion Load Measurement''': Measure volume of each lesion, summarize lesion load by regions
 
* '''Lesion Load Measurement''': Measure volume of each lesion, summarize lesion load by regions
* '''Time Series Analysis of white matter lesions''':
+
* '''Time Series Analysis of white matter lesions''': Compare lesions between multiple scans taken over time.
* '''Multi-scale Analysis of white matter lesions''':
+
* '''Multi-scale Analysis of white matter lesions''': Combine DTI, anatomical, and functional scans when analyzing lupus subjects.
 
* '''Tutorial''':  Documentation will be written for a tutorial and sample data sets will be provided
 
* '''Tutorial''':  Documentation will be written for a tutorial and sample data sets will be provided
  
==Roadmap==
+
=='''Roadmap'''==
We will obtain gray matter, white matter, CSF, and lesion maps for each subject based on T1-weighted, T2-weighted, and FLAIR images. Ultimately, the NA-MIC Kit will provide a workflow for individual and group analysis of lesions. It will be implemented as a set of Slicer3 modules that can be used interactively within the Slicer3 application as well as in batch on a computing cluster using [http://batchmake.org/ BatchMake].
+
We obtained gray matter, white matter, CSF, and lesion maps for each subject based on T1-weighted, T2-weighted, and FLAIR images. Ultimately, the NA-MIC Kit will provide a workflow for individual and group analysis of lesions. It will be implemented as a set of Slicer3 modules that can be used interactively within the Slicer3 application as well as in batch on a computing cluster using [http://batchmake.org/ BatchMake].
  
The current status of the main modules to be used are:
+
<center>
 +
{|
 +
|[[Image:Scully Figure3.jpg|thumb|400px|A. FLAIR with predicted probability of being lesion, B. FLAIR with manual segmentation, C. FLAIR with predicted probability after thresholding]]
 +
|[[Image:TractsLesionZoomOverlay.png‎|thumb|380px|White Matter Lesion Disruption of a U fiber]]
 +
|}
 +
{|
 +
|[[Image:ComapareViewL1L2Overview.jpg|thumb|400px| Compare Layout overview with baseline FLAIR image on top and followup FLAIR on bottom.  Each image is overlaid with that time point's predicted lesion segmentation.]]
 +
|[[Image:CompareViewLDiffZoomedIn.jpg|thumb|400px| Compare Layout zoomed in.  Baseline FLAIR on top and followup on bottom.  Images overlaid with a label map that represents changes in lesion.  Yellow represents lesion that's unchanged between baseline and followup, red represents new lesion in the followup, and blue represents lesion present at baseline that is no longer present at followup. ]]
 +
| [[Image:MIND-DBPLesionClassZoomDetail.png|thumb|158px| Zoomed detail. ]]
 +
|}
 +
</center>
  
=== Registration ===
+
===Software===
:* ITK has mutual information registration
+
*We have a very active project for this pipeline on the NITRC resource [http://www.nitrc.org/frs/?group_id=180 3DSlicerLupusLesionModule]
:* T1/T2/Flair co-registration implemented into EM-segment module
+
*The module can be checked out in Slicer3.6 using the extension manager or downloaded [http://www.nitrc.org/frs/download.php/570/LesionSegmentationApplications.tgz here].
 +
*Source code is available via [http://www.nitrc.org/plugins/scmcvs/cvsweb.php/lupuslesion/LesionSegmentationApplications/?cvsroot=lupuslesion cvs].
  
=== Lesion segmentation ===
 
Five algorithms (all within NA-MIC kit) for fully or semi-automated lesion analysis will be evaluated. These include:
 
:* [http://www.slicer.org/slicerWiki/index.php/Slicer3:EM#Old_.282007.29_Tutorial Slicer3 EM-segment Module] (Sandy Wells)
 
:* ITK stand-alone [http://www.ia.unc.edu/dev/download/itkems/index.htm itkEMS] Compare Lesion Analysis Tools (Prastawa/Gerig)
 
:* ITK stand-alone white matter lesion segmentation (Magnotta)
 
:* ITK K Nearest Neighbor classification based on the work of [http://www.midasjournal.org/browse/publication/281 Anabeek, et al]
 
:* ITK stand-alone segmentation combining elements of Boosting, Artificial Immune Systems, and Bayesian Classification. (Scully)
 
Manual tracing will serve as a bronze-standard:
 
:* Slicer3 Manual tracing by clinically trained rater (Gasparovic/Bockholt)
 
 
=== Lesion Localization ===
 
:* Slicer3 has tools for labeling white matter lesions and summarizing their anatomical location
 
 
=== Lesion Load Measurement ===
 
:* Slicer3 has tools for measurement of labelled lesions
 
 
=== Performance characterization and validation ===
 
:* Data will be collected at both 1.5 and 3T. Data at 1.5T will be obtained with the protocol utilized for the current project on lupus at UNM.
 
:* Data at 3T will be obtained with sequences optimized for segmentation by the group at Utah.
 
:* Comparisons will be based on the approach developed by Martin-Fernandez et al.
 
:* The algorithm with the best performance will be incorporated into the NA-MIC kit.
 
 
 
=== Tutorial ===
 
=== Tutorial ===
:* 10 Externally sharable T1,T2,Flair,Lesion Map data-sets (NIFTI format) will be made available to the scientific community
+
* A step-by-step guide for one example lupus case is available [http://www.nitrc.org/frs/download.php/571/Slicer3Training_WhiteMatterLesions_v2.0.ppt.pdf here].
:** 5 subjects with lupus and 5 healthy normal volunteers
+
* The data needed to run the tutorial is available [http://www.nitrc.org/frs/download.php/569/LesionSegmentationTutorialData.tgz here].
:* A tutorial will be created that will guide end-users through each step needed to complete a lesion analysis in the NA-MIC kit
 
:** A step-by-step guide will be produced for one example lupus cases within the tutorial and one example healthy normal volunteer
 
:** Measurements for all 10 subjects will also be provided so that users may compare their results with those of the tutorial
 
  
 
=== Schedule ===
 
=== Schedule ===
* Sequence Optimization and Data Collection
+
* 06/21/2010 - 06/25/2010 Release new version of module and tutorial including directions and data for longitudinal analysis at the Summer project week
:* '''10/15/2007''' T1, T2, FLAIR optimized sequences for Siemens 3T Trio Tim scanner ('''Jeremy, Bruce, Chuck''')
+
* 04/20/2010 Began updating module to use ITK review statistics
:** We will work with Bruce Fischl on using MEMPR, Mugler, and FLAIR sequences that have been optimized for maximum constrast and minimal geometric distortion across sequences
+
* 03/19/2010 Segmentation Method paper published in Frontiers in Human Neuroscience
:** '''DONE'''
+
* 01/04/2010 - 01/08/2010 Demonstrated longitudinal analysis and some of the multiscale work at the Winter Project Week / All Hands Meeting
:* '''3/31/2008''' collection of 5 lupus subjects on clinical sequence and optimized 3T sequence ('''Chuck''')
+
* 12/15/2009 Developed longitudinal analysis method
:** collected 2 patients and 3 controls so far
+
* 11/18/2009 Submitted paper on novel lesion segmentation method to Frontiers in Human Neuroscience
:*** as of 3/10/2008 there are 3-4 additional patients scheduled, since january 1, we have had 4 patients not able to complete the protocol so far
+
* 08/15/2009 Expanded lesion model to include additional cases
 
+
* 06/22/2009 - 06/26/2009 Summer Project Week
* Co-Registration and Atlas Registration
+
* 06/18/2009 - 06/23/2009 Attended Human Brain Mapping Conference with submitted abstract on lesion classification using novel method
:* '''1/31/2008''' optimized mutual information registration for clinical sequences and optimized 3T sequences ('''Jeremy''')
+
* 03/25/2009 - 04/02/2009 AAN conference outreach activity
:** we have tried the registration tools built-in to Slicer 3 EM-segment module so far
+
* 03/01/2009 Released final version of the novel lesion segmentation method as a Slicer module
:** DONE Brad has implemented this successfully into the EM-segment module
+
* 01/11/2009 Submitted abstract on novel lesion method for HBM 2009
 
+
* 01/06/2009 Initial version of the novel lesion segmentation method released as slicer module.
* Lesion segmentation
+
* 01/05/2009 - 01/09/2009 Winter Project Week / All Hands Meeting
:* '''3/17/2008''' complete lesion segmentation methods for Slicer3 EM-segment, ITK itkEMS, ITK lesion segmentation, and Slicer3 manual tracing ('''Jeremy, Chuck, Vince Magnotta, Kilian/Brad, Marcel''')
+
* 11/15/2008 - 11/19/2008 Abstract on initial version of the novel lesion method submitted to Society For Neuroscience conference and held a Conference / Outreach activity on the Slicer lesion segmentation tool.
:** Slicer3 EM-segment Module
+
* 09/11/2008 Began development on novel lesion segmentation method
:*** (Resolved) Currently has a bug that does not permit 3 channel segmentation [http://na-mic.org/Mantis/view.php?id=205 Mantis ID#0000205]
+
* 09/06/2008 - 09/10/2008 Participated in the MS lesion segmentation challenge, part of the 3D Segmentation in the Clinic: A Grand Challenge II
:**** (Resolved) Only using 2 channels such as T1/T2 or T1/FLAIR does not produce sensible/usable results
+
* 08/14/2008 EMSegment has been run against collected lupus cases.  Segmentations have improved but are still unusable
:*** (Resolved) Does not properly allow user to edit or change weighting of channels, this is crucial for hierarchical lesion classification. [http://na-mic.org/Mantis/view.php?id=204 Mantis ID#0000204]
+
* 07/01/2008 Made tutorial and sample data available to the scientific community
:*** EMSegment has been run against collected lupus cases.  Segmentations have improved but are still unusable as of 08/14/2008.
+
* 06/23/2008 - 06/27/2008 Presented lesion segmentation tutorial at the Summer Project Week
:**** Currently working with Killian on optimizing parameters in EMSegment to improve the lesion segmentation.
+
* 05/12/2008 Submitted SFN abstract on a lesion segmentation method based on Vince Magnotta's work
:**** Testing parameters and resulting segmentation on collected lupus cases.  
+
* 04/01/2008 Gasparovic has manually traced all tutorial cases with lesions using T2/Flair images following tracing guidelines and a qualitative neuroradiological review report
:** ITK itkEMS stand-alone package
+
* 03/31/2008 Completed collection of 5 lupus subjects on clinical sequence and optimized 3T sequence
:*** Marcel and Mark are in active collaboration with getting this method to work on-site, we have encountered compilation and memory problems with the package on mac and linux environments so far
+
* 03/17/2008 Applied itkEMS to sample lesion cases, results are shown [[DBP2:MIND:itkEMSResults|here]]
:*** 3/17/2008 update, marcel built a 64-bit linux version that appears to run successfully, current results are are shown [[DBP2:MIND:itkEMSResults|here]]
+
* 03/15/2008 Applied Vince Magnotta's lesions segmentation method to sample lesion cases, results are shown [[DBP2:MIND:itkBayesianLesion|here]]
:** ITK lesion classification stand-alone package
+
* 02/05/2008 Created intensity standardization method
:*** Vince Magnotta has develop an ITK-based 2 stage lesion segmentation method
+
* 01/10/2008 Performed initial segmentations using EMSegment and submitted bug reports
:**** stage one uses k-means tissue classification into grey, white, or csf of co-registered T1/T2
+
* 01/07/2008 - 01/11/2008 Winter Project Week / All Hands Meeting
:**** stage two use bayesian classifier into normal tissue or lesion using results of stage one and co-reigstered Flair
+
* 10/15/2007 optimized sequences for T1, T2, and FLAIR for Siemens 3T Trio Tim scanner
:***** current results of this method as of 3/17/2008 are shown [[DBP2:MIND:itkBayesianLesion|here]]
+
* 08/01/2007 Created project requirements and architecture
:***** This method has been run against all cases as of 05/01/08.  Currently working with Vince Magnotta to improve the performance.
+
* 06/25/2007 - 06/29/2007 Attended Project Week
:***** As of 08/14/2008, currently running a modified version of Vince's classifier that has been improved by replacing intensity thresholding with joint histogram feature vector occurrence thresholding.
 
:** ITK K Nearest Neighbor Classifier
 
:*** Mark Scully is currently implementing a K-NN lesion classifier using ITK.
 
:**** This approach allows for on the fly additions to the classification model.
 
:**** The same segmentation approach is applicable to multiple lesion types.
 
:**** The resulting label map contains the percent likelihood that a given voxel is a lesion.  This allows the clinician to adjust the thresholding to match their preference.
 
:*** On hold as of 1/12/2008 due to incomplete ITK algorithmic support
 
:** ITK Custom Classifier
 
:*** Mark Scully is currently implementing a combined approach classifier using ITK.
 
:**** This approach allows for on the fly additions to the classification model.
 
:**** The same segmentation approach is applicable to multiple lesion types.
 
:**** This approach takes advantage of multiple approaches and advancements in the literature, including feature generation, Gentle Boosting based feature reduction, Artificial Immune System based filtering, and Bayesian classification.
 
:*** As of 1/01/2009 this method is functional and built into the lesion segmentation slicer3 applications.
 
:***[[File:Scully_Figure1.png|Flowchart of lesion segmentation method]]
 
:***[[File:Scully_Figure4.png|ROC curve]]
 
 
 
 
 
 
 
:** Slicer3 Manual Tracing
 
:*** Gasparovic has manually traced all tutorial cases with lesions using T2/Flair images following tracing guidelines and a qualitative neuroradiological review report
 
:**** 4/1/2008 create manual tracing guidelines documentation and share here
 
* Lesion Localization
 
:* '''4/15/2008''' complete lesion localizations and maps for Slicer3 EM-segment, ITK itkEMS, ITK lesion segmentation, and Slicer3 manual tracing ('''Jeremy, Chuck, Vince Magnotta, Steve''')
 
 
 
* Lesion Measurement
 
:* '''4/20/2008''' complete lesion measurements and regional lesion load summaries for Slicer3 EM-segment, ITK itkEMS, ITK lesion segmentation, and Slicer3 manual tracing ('''Jeremy, Chuck, Vince Magnotta, Steve''')
 
 
 
* Performance characterization and validation
 
:* '''1/6/2008''' [[Media:DBP2_MIND_Lupus_200801_update.ppt | report]] to 2008 NA-MIC AHM on progress for performance and validation of lesion segmentation methods for EM-segment, BRAINS2, manual, UNC packages ('''Jeremy''')
 
:** '''DONE'''
 
:* '''5/15/2008''' submit abstract on reliability and summary of novel NA-MIC kit lesion analysis method ('''Jeremy, Chuck, Mark Scully, Brad, Kilian, others''')
 
:** plan is to submit SFN abstract and manuscript closely after
 
:* '''5/20/2008''' analyze NIH study clinical sample using NA-MIC kit lesion analysis method ('''Jeremy, Chuck, Mark Scully''')
 
:* '''7/1/2008''' submit manuscript on clinical application of NA-MIC kit lesion analysis method ('''Jeremy, Chuck, Mark Scully, Carlos Roldan, Bill Sibbitt''')
 
:* '''8/14/2008''' submit manuscript on the lesion segmentation methods as applied to MS lesions for MICCAI 2008. ('''Mark, Jeremy, Chuck, Vince Magnotta''')
 
:* '''1/11/2009''' submit abstract on the new lesion segmentation methods as applied to Lupus lesions for HBM 2009.
 
:* '''3/08/2009''' submit manuscript on the new lesion segmentation methods as applied to Lupus lesions for MICCAI 2009.
 
 
 
* Incorporation of approach into NA-MIC kit
 
:* '''1/6/2008''' Slicer3 Lesion Analysis Module that handles co-registration of T1, T2, and Flair ('''Mark Scully, Steve''')
 
:** DONE Brad completed this
 
:* ''5/1/2008''' extend Slicer3 Lesion Analysis Module to handle lesion localization and measurement ('''Mark Scully, Steve''')
 
:** ''08/01/2008'' currently locates all independent lesion clusters and identifies the anatomical regions, provided by a registered atlas, that the lesions overlap.
 
:* '''6/1/2008''' extend Slicer3 Lesion Analysis Module to implement the ITK-based lesion analysis algorithm/method (EM-segment, ITK itkEMS, ITK lesion segmentation) with the best performance ('''Mark Scully, Steve''')
 
:** a demonstration will be given at the 2008 NA-MIC AHM--we would consider this version a prototype and would be testing, refining the module through the clinical application phase ('''Jeremy, Mark Scully''')
 
:* '''6/15/2008''' functioning prototype version of lesion analysis Slicer3 Module complete ('''Mark Scully, Steve''')
 
:* '''8/14/2008''' in the process of creating a module that "chains" together all of the steps in the lesion segmentation analysis pipeline.
 
:* '''1/03/2009''' Newly developed lesion segmentation method with significantly increased performance incorporated into Slicer3 module.
 
* Tutorial and Data-sharing
 
:* '''6/20/2008''' present tutorial to 2008 NA-MIC programming week ('''Mark Scully, Jeremy, Sonja''')
 
:** A logical project for programming week for Jeremy and Sonja to finish public version of tutorial
 
:* '''7/1/2008''' make data sets and tutorial available to the scientific community ('''Mark Scully, Jeremy, Sonja''')
 
:** If we submit SFN abstract, we can advertise the availability during SFN Conference in November 2008
 
:*** We could think about advertising the roadmaps at the BIRN booth at SFN this year?
 
:* '''10/15/2008''' In the process of making the tutorial data available using XNAT.
 
 
 
 
 
 
 
Compare view of baseline and followup with color-coded lesion differences:
 
http://www.na-mic.org/Wiki/index.php/File:CompareViewFlairLesionDiffWholeBrain.png
 
 
 
Diffusion tracts intersecting a lesion volume:
 
http://www.na-mic.org/Wiki/index.php/File:LesionTractsNear.png
 
  
Axial slice with % predicted chance, thresholded predicted % chance, and manual tracing:
+
=== '''Publications''' ===
http://www.na-mic.org/Wiki/index.php/File:Scully_Figure3.jpg
+
* H. J. Bockholt, V. A. Magnotta, M. Scully, C. Gasparovic, B. Davis, K. Pohl, R. Whitaker, S. Pieper, C. Roldan, R. Jung, R. Hayek, W. Sibbitt, J. Sharrar, P. Pellegrino, R. Kikinis. A novel automated method for classification of white matter lesions in systemic lupus erythematosus. Presented at the 38th annual meeting of the Society for Neuroscience, Washingto, DC, 15 – 19 November 2008
 +
* Scully M., Magnotta V., Gasparovic C., Pelligrimo P., Feis D., Bockholt H.J. 3D Segmentation In The Clinic: A Grand Challenge II at MICCAI 2008 - MS Lesion Segmentation. IJ - 2008 MICCAI Workshop - MS Lesion Segmentation. Available  http://grand-challenge2008.bigr.nl/proceedings/pdfs/msls08/282_Scully.pdf
 +
* H Jeremy Bockholt, Josef Ling, Mark Scully, Adam Scott, Susan Lane, Vincent Magnotta, Tonya White, Kelvin Lim, Randy Gollub, Vince Calhoun. Real-time Web-scale Image Annotation for Semantic-based Retrieval of Neuropsychiatric Research Images. Presented at the 14th Annual Meeting of the Organization for Human Brain Mapping, Melbourne, Australia, 15 – 19 June, 2008.
 +
* H Jeremy Bockholt, Sumner Williams, Mark Scully, Vincent Magnotta, Randy Gollub, John Lauriello, Kelvin Lim, Tonya White, Rex Jung, Charles Schulz, Nancy Andreasen, Vince Calhoun. The MIND Clinical Imaging Consortium as an application for novel comprehensive quality assurance procedures in a multi-site heterogeneous clinical research study. Presented at the 14th Annual Meeting of the Organization for Human Brain Mapping, Melbourne, Australia, 15 – 19 June, 2008.
 +
* M Scully, B H Anderson, C Gasparovic, V A Magnotta, S Pieper, R Kikinis, P Pellegrino, T Lane, H J Bockholt. A Synergistic Combination of Supervised Machine Learning Methods for Analysis of White Matter Lesions in Neuropsychiatric Systemic Lupus Erythematosus. Presented at the 15th Annual Meeting of the Organization for Human Brain Mapping, San Francisco June, 2009.
 +
* Bockholt HJ, Scully M, Courtney W, Rachakonda S, Scott A, Caprihan A, Fries J, Kalyanam R, Segall J, de la Garza R, Lane S and Calhoun VD (2009) Mining the mind research network: a novel framework for exploring large scale, heterogeneous translational neuroscience research data sources. Front. Neuroinform. 3:36. doi:10.3389/neuro.11.036.2009
 +
* Scully M, Anderson B, Lane T, Gasparovic C, Magnotta V, Sibbitt W, Roldan C, Kikinis R and Bockholt HJ (2010) An automated method for segmenting white matter lesions through multi-level morphometric feature classification with application to lupus. Front. Hum. Neurosci. 4:27. doi:10.3389/fnhum.2010.00027. Available [http://www.frontiersin.org/humanneuroscience/paper/10.3389/fnhum.2010.00027/ here]
 +
* Scully, M., Lane, T., Gasparovic, C., Magnotta, V., Sibbitt, W., Roldan,C. , Kikinis, R., Bockholt, H. J. An Automated Method For Longitudinal Analysis of White Matter Lesions in Lupus (''in preparation'' for submission).
 +
* Bockholt, H.J.,  Gasparovic, C., Scully, M., Magnotta, V., Sibbitt, W., Kikinis, R., Roldan,C. A novel white matter lesion analysis for improved clinical application in lupus. (''in preparation'' for submission).
  
=== Team and Institute ===
+
=== '''Team and Institute''' ===
* Co-PI: H Jeremy Bockholt (jbockholt at mrn.org)
+
* Co-PI: [http://www.mrn.org/principal-investigators/h-jeremy-bockholt H Jeremy Bockholt(jbockholt at mrn.org)
* Co-PI: Charles Gasparovic (chuck at unm.edu)
+
* Co-PI: [http://www.mrn.org/principal-investigators/charles-gasparovic-ph-d Charles Gasparovic] (chuck at unm.edu)
* Software Engineer: Mark Scully (mscully at mrn.org)
+
* Software Engineer: Mark Scully (mark-scully at uiowa.edu)
* NA-MIC Engineering Contact: Steve Pieper, Isomics
+
* NA-MIC Engineering Contact: [http://www.na-mic.org/Wiki/index.php/User:Pieper Steve Pieper], Isomics
 
* NA-MIC Algorithms Contact: Ross Whitaker, Utah
 
* NA-MIC Algorithms Contact: Ross Whitaker, Utah
 
* Host Institues: The [http://www.mrn.org Mind Research Network] and [http://www.unm.edu The University of New Mexico]
 
* Host Institues: The [http://www.mrn.org Mind Research Network] and [http://www.unm.edu The University of New Mexico]
  
 
[[Category:Slicer]] [[Category:Segmentation]] [[Category:Registration]]
 
[[Category:Slicer]] [[Category:Segmentation]] [[Category:Registration]]

Latest revision as of 17:09, 18 January 2011

Home < DBP2:MIND:Roadmap
Back to NA-MIC Internal Collaborations, MIND DBP 2

Brain Lesion Analysis in Neuropsychiatric Systemic Lupus Erythematosus

Lesion volumes in yellow with ventricles and brain slice

Objective

This page describes the technology roadmap for lesion analysis in the NA-MIC Kit. Our objective is to create an end-to-end application allowing individual analysis of white matter lesions. This workflow applied to lupus patients is one of goals of the MIND DBP. The basic components necessary for this project are:

  • Registration: co-registration of T1-weighted, T2-weighted, and FLAIR images
  • Tissue segmentation: Should be multi-modality, correcting for intensity inhomogeneity and work on non-skull-stripped data.
  • Lesion Localization: Each unique lesion should be detected and anatomical location summarized
  • Lesion Load Measurement: Measure volume of each lesion, summarize lesion load by regions
  • Time Series Analysis of white matter lesions: Compare lesions between multiple scans taken over time.
  • Multi-scale Analysis of white matter lesions: Combine DTI, anatomical, and functional scans when analyzing lupus subjects.
  • Tutorial: Documentation will be written for a tutorial and sample data sets will be provided

Roadmap

We obtained gray matter, white matter, CSF, and lesion maps for each subject based on T1-weighted, T2-weighted, and FLAIR images. Ultimately, the NA-MIC Kit will provide a workflow for individual and group analysis of lesions. It will be implemented as a set of Slicer3 modules that can be used interactively within the Slicer3 application as well as in batch on a computing cluster using BatchMake.

A. FLAIR with predicted probability of being lesion, B. FLAIR with manual segmentation, C. FLAIR with predicted probability after thresholding
White Matter Lesion Disruption of a U fiber
Compare Layout overview with baseline FLAIR image on top and followup FLAIR on bottom. Each image is overlaid with that time point's predicted lesion segmentation.
Compare Layout zoomed in. Baseline FLAIR on top and followup on bottom. Images overlaid with a label map that represents changes in lesion. Yellow represents lesion that's unchanged between baseline and followup, red represents new lesion in the followup, and blue represents lesion present at baseline that is no longer present at followup.
Zoomed detail.

Software

  • We have a very active project for this pipeline on the NITRC resource 3DSlicerLupusLesionModule
  • The module can be checked out in Slicer3.6 using the extension manager or downloaded here.
  • Source code is available via cvs.

Tutorial

  • A step-by-step guide for one example lupus case is available here.
  • The data needed to run the tutorial is available here.

Schedule

  • 06/21/2010 - 06/25/2010 Release new version of module and tutorial including directions and data for longitudinal analysis at the Summer project week
  • 04/20/2010 Began updating module to use ITK review statistics
  • 03/19/2010 Segmentation Method paper published in Frontiers in Human Neuroscience
  • 01/04/2010 - 01/08/2010 Demonstrated longitudinal analysis and some of the multiscale work at the Winter Project Week / All Hands Meeting
  • 12/15/2009 Developed longitudinal analysis method
  • 11/18/2009 Submitted paper on novel lesion segmentation method to Frontiers in Human Neuroscience
  • 08/15/2009 Expanded lesion model to include additional cases
  • 06/22/2009 - 06/26/2009 Summer Project Week
  • 06/18/2009 - 06/23/2009 Attended Human Brain Mapping Conference with submitted abstract on lesion classification using novel method
  • 03/25/2009 - 04/02/2009 AAN conference outreach activity
  • 03/01/2009 Released final version of the novel lesion segmentation method as a Slicer module
  • 01/11/2009 Submitted abstract on novel lesion method for HBM 2009
  • 01/06/2009 Initial version of the novel lesion segmentation method released as slicer module.
  • 01/05/2009 - 01/09/2009 Winter Project Week / All Hands Meeting
  • 11/15/2008 - 11/19/2008 Abstract on initial version of the novel lesion method submitted to Society For Neuroscience conference and held a Conference / Outreach activity on the Slicer lesion segmentation tool.
  • 09/11/2008 Began development on novel lesion segmentation method
  • 09/06/2008 - 09/10/2008 Participated in the MS lesion segmentation challenge, part of the 3D Segmentation in the Clinic: A Grand Challenge II
  • 08/14/2008 EMSegment has been run against collected lupus cases. Segmentations have improved but are still unusable
  • 07/01/2008 Made tutorial and sample data available to the scientific community
  • 06/23/2008 - 06/27/2008 Presented lesion segmentation tutorial at the Summer Project Week
  • 05/12/2008 Submitted SFN abstract on a lesion segmentation method based on Vince Magnotta's work
  • 04/01/2008 Gasparovic has manually traced all tutorial cases with lesions using T2/Flair images following tracing guidelines and a qualitative neuroradiological review report
  • 03/31/2008 Completed collection of 5 lupus subjects on clinical sequence and optimized 3T sequence
  • 03/17/2008 Applied itkEMS to sample lesion cases, results are shown here
  • 03/15/2008 Applied Vince Magnotta's lesions segmentation method to sample lesion cases, results are shown here
  • 02/05/2008 Created intensity standardization method
  • 01/10/2008 Performed initial segmentations using EMSegment and submitted bug reports
  • 01/07/2008 - 01/11/2008 Winter Project Week / All Hands Meeting
  • 10/15/2007 optimized sequences for T1, T2, and FLAIR for Siemens 3T Trio Tim scanner
  • 08/01/2007 Created project requirements and architecture
  • 06/25/2007 - 06/29/2007 Attended Project Week

Publications

  • H. J. Bockholt, V. A. Magnotta, M. Scully, C. Gasparovic, B. Davis, K. Pohl, R. Whitaker, S. Pieper, C. Roldan, R. Jung, R. Hayek, W. Sibbitt, J. Sharrar, P. Pellegrino, R. Kikinis. A novel automated method for classification of white matter lesions in systemic lupus erythematosus. Presented at the 38th annual meeting of the Society for Neuroscience, Washingto, DC, 15 – 19 November 2008
  • Scully M., Magnotta V., Gasparovic C., Pelligrimo P., Feis D., Bockholt H.J. 3D Segmentation In The Clinic: A Grand Challenge II at MICCAI 2008 - MS Lesion Segmentation. IJ - 2008 MICCAI Workshop - MS Lesion Segmentation. Available http://grand-challenge2008.bigr.nl/proceedings/pdfs/msls08/282_Scully.pdf
  • H Jeremy Bockholt, Josef Ling, Mark Scully, Adam Scott, Susan Lane, Vincent Magnotta, Tonya White, Kelvin Lim, Randy Gollub, Vince Calhoun. Real-time Web-scale Image Annotation for Semantic-based Retrieval of Neuropsychiatric Research Images. Presented at the 14th Annual Meeting of the Organization for Human Brain Mapping, Melbourne, Australia, 15 – 19 June, 2008.
  • H Jeremy Bockholt, Sumner Williams, Mark Scully, Vincent Magnotta, Randy Gollub, John Lauriello, Kelvin Lim, Tonya White, Rex Jung, Charles Schulz, Nancy Andreasen, Vince Calhoun. The MIND Clinical Imaging Consortium as an application for novel comprehensive quality assurance procedures in a multi-site heterogeneous clinical research study. Presented at the 14th Annual Meeting of the Organization for Human Brain Mapping, Melbourne, Australia, 15 – 19 June, 2008.
  • M Scully, B H Anderson, C Gasparovic, V A Magnotta, S Pieper, R Kikinis, P Pellegrino, T Lane, H J Bockholt. A Synergistic Combination of Supervised Machine Learning Methods for Analysis of White Matter Lesions in Neuropsychiatric Systemic Lupus Erythematosus. Presented at the 15th Annual Meeting of the Organization for Human Brain Mapping, San Francisco June, 2009.
  • Bockholt HJ, Scully M, Courtney W, Rachakonda S, Scott A, Caprihan A, Fries J, Kalyanam R, Segall J, de la Garza R, Lane S and Calhoun VD (2009) Mining the mind research network: a novel framework for exploring large scale, heterogeneous translational neuroscience research data sources. Front. Neuroinform. 3:36. doi:10.3389/neuro.11.036.2009
  • Scully M, Anderson B, Lane T, Gasparovic C, Magnotta V, Sibbitt W, Roldan C, Kikinis R and Bockholt HJ (2010) An automated method for segmenting white matter lesions through multi-level morphometric feature classification with application to lupus. Front. Hum. Neurosci. 4:27. doi:10.3389/fnhum.2010.00027. Available here
  • Scully, M., Lane, T., Gasparovic, C., Magnotta, V., Sibbitt, W., Roldan,C. , Kikinis, R., Bockholt, H. J. An Automated Method For Longitudinal Analysis of White Matter Lesions in Lupus (in preparation for submission).
  • Bockholt, H.J., Gasparovic, C., Scully, M., Magnotta, V., Sibbitt, W., Kikinis, R., Roldan,C. A novel white matter lesion analysis for improved clinical application in lupus. (in preparation for submission).

Team and Institute