Difference between revisions of "SidongLiu Update"

From NAMIC Wiki
Jump to: navigation, search
 
(88 intermediate revisions by 3 users not shown)
Line 1: Line 1:
* Feb 24 - Feb 28
+
=Jan 30 - Jan 31=
** Partners orientation
+
Travel:
** MICCAI 2014 paper submissions
+
* Depart from Sydney - Jan 30
 +
* Arrive in Boston - Jan 31
 
<br \>
 
<br \>
* Mar 12 - Mar 14
+
 
** BWH orientation
+
 
** Start to work at SPL, 75 Fransic St
+
=Feb 03 - Feb 07=
 +
BWH:
 +
* Attend Partners orientation - Feb 06
 
<br \>
 
<br \>
* Mar 17 - Mar 21
+
 
** EMBC 2014 paper submission
+
=Feb 10 - Feb 14=
** Implement a new functionality for peritumoral tract exploration
+
Publication:
 +
* Prepare MICCAI 2014 papers
 
<br \>
 
<br \>
* Mar 24 - Mar 28
+
 
** MICCAI 2014 paper reviews
+
 
** SNMMI 2014 abstract papers accepted
+
=Feb 17 - Feb 21=
** Reformat the Hausdorff outputs
+
DTI Project:
 +
* Develop TractROIShellSeeding module in Slicer
 
<br \>
 
<br \>
* Mar 31 - Apr 4
+
 
** Submit postdoctoral fellowship application
+
 
** Start to work at SPL, Boylston St
+
=Feb 24 - Feb 28=
 +
Publication:
 +
* MICCAI 2014 paper submissions
 
<br \>
 
<br \>
* Apr 7 - Apr 11
+
 
** Make CMIG journal paper revision submission
+
 
** Prepare the ACM MM 2014 abstract
+
=Mar 12 - Mar 14=
** Work on DTI Editor module ("tract extractor")
+
BWH:
** The fiber selection function can be found in Diffusion -> Tractography -> FiberBundleLabelSelect module.
+
* Attend BWH orientation
** The fiber bundle cropping function can be found in Tractography Display module (http://wiki.slicer.org/slicerWiki/index.php/Documentation/4.3/Modules/TractographyDisplay)
+
* Start to work at SPL, 75 Fransic St
** Sidong's next task would be learn qt.QImage object and see how to manipulate it in Python. Check Steve's code (https://github.com/pieper/CompareVolumes/blob/master/CompareVolumes.py)
 
** A control panel style mosaic to flexibly display different teams or patients. A summary table showing the statistics.
 
 
<br \>
 
<br \>
* Apr 14 - Apr 18
+
 
** Try Brain Visa trick on mac (http://brainvisa.info/forum/viewtopic.php?f=2&t=1713#p6399)
+
 
** Explore Nipype to see whether we can convert Gifti to VTK or STL, or other compatible format with Slicer (http://www.mit.edu/~satra/nipype-nightly/users/examples/dmri_connectivity.html)
+
=Mar 17 - Mar 21=
** Discuss the response letter for MICCAI 2014 submissions
+
Publication:
** Next task would be
+
* Make EMBC 2014 paper submission
*** Load the test data and create the scene views manually
+
 
*** Link the scene views to individual 3D mosaic viewers
+
DTI Project:
*** Test one MRI volume in 4 viewers first; then test 4 MRI volumes in 4 viewers; finally test the DTI data
+
* Implement a new functionality for peritumoral tract exploration
 
<br \>
 
<br \>
* Apr 21 - Apr 25
+
 
** Made progress to the Mosaic Viewer module. Now it could display and manipulate multiple independent 3D viewers at the same time
+
=Mar 24 - Mar 28=
** Discussed DTI Challenge preparation. Need to install Evernote and Live Minutes to enhance collaboration
+
Publication:
** Next step would be to finalize the Mosaic Viewer by creating a scene view for the it
+
* Submit MICCAI 2014 paper reviews
** Submitted the Grants-in-Aid application
+
* SNMMI 2014 abstract papers accepted
** The original test dataset is a HARDI dataset with 69 gradients plus 4 baselines, and we extracted 30 volumes whose b-values equal to 1000.
+
 
 +
DTI Project:
 +
* Reformat the Hausdorff outputs
 
<br \>
 
<br \>
* April 28 - May 02
+
 
** Finalized the Mosaic Viewer module.
+
=Mar 31 - Apr 4=
** Successfully loaded and corrected the Brain Visa surface files into Slicer. Next step would be streamline the process. There might be three potential solutions:
+
USYD:
*** Build CLI modules (SlicerToBrainVisa Import and Export) to integrate Brain Visa morphologist tools in Slicer. Check NiftyReg extension as an example (https://github.com/spujol/niftyregExtension) and Hello World tutorial to learn how to integrate .cxx  plugins (http://www.slicer.org/slicerWiki/images/2/22/ProgrammingIntoSlicer3.6_SoniaPujol.pdf). Note this tutorial might need to be updated to Slicer 4.
+
* Submit postdoctoral fellowship application
*** Build a Python wrapper which point to the Brain Visa executable files and run Brain Visa in Slicer. 
+
 
*** Write a simple script to 1) convert nhdr to Nifty; 2) filp left / right by changing RAS to LPI coordinate system; 3) run Morphologist pipeline in Brain Visa; 4) load output .ply file in Slicer; and 5) apply 'BrainVisatoSlicer' transform if the coordinate differences were independent to the datasets.
+
BWH:
** Test the DWIConverter module to convert DICOM to nhdr using the datasets '...high-b.raw.gz' dataset and compare the output to '...high-b.nhdr'.
+
* Start to work at SPL, 1249 Boylston St
** New tasks regarding the test dataset:  
 
*** Create the tractography for extracted dataset only using single tensor algorithm
 
*** Compare the result to that of original dataset using UKF extension
 
*** Run the DTIPrep extension on both datasets (original and extracted)
 
 
<br \>
 
<br \>
* May 05 - May 09
+
 
** Reconstruct the tensors using eigen values and eigen vectors. Slicer could not handle eigen vectors directly, so we ned to calculate the 7 coefficients in the tensor matrix.  
+
 
** Our multi-channel pattern analysis paper was accepted by CMIG.
+
=Apr 7 - Apr 11=
 +
Publication:
 +
* Make CMIG journal paper revision submission
 +
* Prepare the ACM MM 2014 abstract
 +
 
 +
DTI Project:
 +
* Work on DTI Editor module ("tract extractor")
 +
* The fiber selection function can be found in Diffusion -> Tractography -> FiberBundleLabelSelect module.
 +
* The fiber bundle cropping function can be found in Tractography Display module (http://wiki.slicer.org/slicerWiki/index.php/Documentation/4.3/Modules/TractographyDisplay)
 +
* Sidong's next task would be learn qt.QImage object and see how to manipulate it in Python. Check Steve's code (https://github.com/pieper/CompareVolumes/blob/master/CompareVolumes.py)
 +
* A control panel style mosaic to flexibly display different teams or patients. A summary table showing the statistics.
 
<br \>
 
<br \>
* May 12 - May 16
+
 
** Run DTIPrep for all the datasets.  
+
 
** Clean up and classify all the processed datasets.
+
=Apr 14 - Apr 18=
** Send email to Francois checking what are the differences VC and QCed results.
+
DTI Project:
** Send BrainVisa screenshots to Sonia, describing the sulci recognition problems.
+
* Try Brain Visa trick on mac (http://brainvisa.info/forum/viewtopic.php?f=2&t=1713#p6399)
** Run UKF tractography with 1-6 seeds per voxel, 2 tensors, other parameters by default.
+
* Explore Nipype to see whether we can convert Gifti to VTK or STL, or other compatible format with Slicer (http://www.mit.edu/~satra/nipype-nightly/users/examples/dmri_connectivity.html)
 +
* Discuss the response letter for MICCAI 2014 submissions
 +
* Design Mosaic Viewer outlines
 +
** Load the test data and create the scene views manually
 +
** Link the scene views to individual 3D mosaic viewers
 +
** Test one MRI volume in 4 viewers first; then test 4 MRI volumes in 4 viewers; finally test the DTI data
 
<br \>
 
<br \>
* May 19 - May 23
+
 
** Process the new dataset 'test1'
+
 
** Solve the DTIPrep problems.
+
=Apr 21 - Apr 25=
*** 1. Why there are 4 baseline images in the original dataset, but only one is left after processing?  All the baselines are merged into one image.
+
DTI Project:
*** 2. How to see the sphere after quality check? We need to first save the results, and then load the XML to DTIPrep.  
+
* Make progress to the Mosaic Viewer module. Now it can display and manipulate multiple independent 3D viewers at the same time
*** 3. Why the gradient directions are changed after processing? This might be a bug, resulted from rounding errors.
+
* Discuss DTI Challenge preparation. Need to install Evernote and Live Minutes to enhance collaboration
*** 4. Why there are holes in the QCed DTI dataset? We need to reset the parameter 'DTI_bCompute - DTI_baselineThreshold'.
+
* Next step would be to finalize the Mosaic Viewer by creating a scene view for the it
 +
* The original test dataset is a HARDI dataset with 69 gradients plus 4 baselines, and we extracted 30 volumes whose b-values equal to 1000.
 +
 
 +
USYD:
 +
* Submit the Grants-in-Aid application
 
<br \>
 
<br \>
* May 26 - May 30
+
 
** Submit propagation matrix fusion paper to ICARCV 2014.
+
 
** Rerun DTIPrep on 'test1'. After testing with different settings, we found when this parameter is set to less than 50, the holes disappear.
+
=April 28 - May 02=
 +
DTI Project:
 +
* Finalize the Mosaic Viewer module.
 +
* Successfully load and corrected the Brain Visa surface files into Slicer. Next step would be streamline the process. There might be three potential solutions:
 +
** Build CLI modules (SlicerToBrainVisa Import and Export) to integrate Brain Visa morphologist tools in Slicer. Check NiftyReg extension as an example (https://github.com/spujol/niftyregExtension) and Hello World tutorial to learn how to integrate .cxx  plugins (http://www.slicer.org/slicerWiki/images/2/22/ProgrammingIntoSlicer3.6_SoniaPujol.pdf). Note this tutorial might need to be updated to Slicer 4.
 +
** Build a Python wrapper which point to the Brain Visa executable files and run Brain Visa in Slicer.
 +
** Write a simple script to 1) convert nhdr to Nifty; 2) filp left / right by changing RAS to LPI coordinate system; 3) run Morphologist pipeline in Brain Visa; 4) load output .ply file in Slicer; and 5) apply 'BrainVisatoSlicer' transform if the coordinate differences were independent to the datasets.
 +
* Test the DWIConverter module to convert DICOM to nhdr using the datasets '...high-b.raw.gz' dataset and compare the output to '...high-b.nhdr'.
 +
* New tasks regarding the test dataset:
 +
** Create the tractography for extracted dataset only using single tensor algorithm
 +
** Compare the result to that of original dataset using UKF extension
 +
** Run the DTIPrep extension on both datasets (original and extracted)
 
<br \>
 
<br \>
* Jun 02 - Jun 06
+
 
** Run BrainVisa on T1 and T2 registered data, use label map as a mask to filter out the lesion from the generated surface. Try 'Resample Scalar/Vector/DWI Volume' module, set 'Interpolation Type' to ws.
+
 
** Run 'Slicer Surface Toolbox' to refine BrainVisa surface. Chcek 'splitting' box in Normals.
+
=May 05 - May 09=
** Convert DICOM to FSL (nifty) format.
+
DTI Project:
** Invited to be NA-MIC tutorial contest judge.
+
* Reconstruct the tensors using eigen values and eigen vectors. Slicer could not handle eigen vectors directly, so we ned to calculate the 7 coefficients in the tensor matrix.  
** Attend Junichi's experiment
+
 
 +
Publication:
 +
* CMIG multi-channel pattern analysis paper accepted
 
<br \>
 
<br \>
* Jun 09 - Jun 13
+
 
** Test DWIConvert on Sample Data - DWIVolume
+
 
*** NrrdToFSL: Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert --conversionMode NrrdToFSL --inputVolume ./dwi.nhdr --outputVolume ./dwi_fsl.nii.gz --outputBValues ./bvals.txt --outputBVectors ./bvec.txt
+
=May 12 - May 16=
*** FSLToNrrd: Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert --conversionMode FSLToNrrd --inputVolume ./dwi_fsl.nii.gz --outputVolume ./dwi_reconverted.nrrd --inputBValues ./bvals.txt --inputBVectors ./bvec.txt
+
DTI Project:
** Test DWIConvert on 'test1' dataset
+
* Run DTIPrep for all the datasets.
 +
* Clean up and classify all the processed datasets.
 +
* Send email to Francois checking what are the differences VC and QCed results.
 +
* Send BrainVisa screenshots to Sonia, describing the sulci recognition problems.
 +
* Run UKF tractography with 1-6 seeds per voxel, 2 tensors, other parameters by default.
 +
 
 +
Publication:
 +
* CMIG multi-channel pattern analysis paper available online http://www.sciencedirect.com/science/article/pii/S0895611114000639
 
<br \>
 
<br \>
* Jun 16 - Jun 20
+
 
** Prepare the DS-2019 extension
+
 
** Process the dataset of patient2 with BrainVisa
+
=May 19 - May 23=
** Process the dataset of patient3 with BrainVisa
+
DTI Project:
** MICCAI 2014 Machine Learning Challenge result was revealed and we ranked 10th in 50 teams.  
+
* Process the new dataset 'test1'
 +
* Solve the DTIPrep problems.
 +
** 1 Why there are 4 baseline images in the original dataset, but only one is left after processing? 
 +
** - All the baselines are merged into one image.
 +
** 2. How to see the sphere after quality check?
 +
** - We need to first save the results, and then load the XML to DTIPrep.
 +
** 3. Why the gradient directions are changed after processing?
 +
** - This might be a bug, resulted from rounding errors.
 +
** 4. Why there are holes in the QCed DTI dataset?
 +
** - We need to reset the parameter 'DTI_bCompute - DTI_baselineThreshold'.  
 
<br \>
 
<br \>
* Jun 23 - Jun 27 (NA-MIC 2014 SUMMER PROJECT WEEK)
+
 
** CAD Toolbox for Neurodegenerative Disease Diagnosis (http://www.na-mic.org/Wiki/index.php/2014_Summer_Project_Week:CAD_Toolbox_for_Neurological_Disorders)
+
 
** Serve as NA-MIC tutorial contest judge
+
=May 26 - May 30=
** Process the dataset of patient2_1 with DWIConverter
+
Publication:
** Prepare the DICTA 2014 abstract
+
* Submit propagation matrix fusion paper to ICARCV 2014.
 +
 
 +
DTI Project:
 +
* Rerun DTIPrep on 'test1'. After testing with different settings, we found when this parameter is set to less than 50, the holes disappear.
 
<br \>
 
<br \>
* Jun 30 - Jul 04
+
 
** Reprocess the dataset of patient2_1 with DWI Converter
+
 
** Test 'DICOM-TO-NIFTI-CONVERTER' matlab toolbox (http://www.mathworks.com/matlabcentral/fileexchange/41874-dicom-to-nifti-converter/content/dicom2nifti.m). However, this toolbox is not usable for our SIEMENS data, because it only work with DICOM files from Phillips Achieva 3T R2.6 with
+
=Jun 02 - Jun 06=
*** Slice orientation  : transverse
+
DTI Project:
*** Patient position  : head first
+
* Run BrainVisa on T1 and T2 registered data, use label map as a mask to filter out the lesion from the generated surface. Try 'Resample Scalar/Vector/DWI Volume' module, set 'Interpolation Type' to ws.
*** Patient orientation: supine
+
* Run 'Slicer Surface Toolbox' to refine BrainVisa surface. Chcek 'splitting' box in Normals.
*** Fold-over direction: AP
+
* Convert DICOM to FSL (nifty) format.
*** Fat shift direction: P
+
 
*** Gradient resolution: high (DTI)
+
NA-MIC Project:
*** Gradient overplus  : yes (DTI)
+
* Invited as one of the NA-MIC tutorial contest judges.
*** Sort images        : b=0 volume first (DTI)
+
 
** Make the submission for DICTA 2014
+
BWH:
 +
* Attend Junichi's MRI-Robotic experiment
 +
 
 +
Publication:
 +
* TBE Deep-Learning paper submission
 
<br \>
 
<br \>
*  Jul 07 - Jul 11
+
 
** Finalize DS-2019 extension, turns out that no need to extend it
+
 
** Mosaic Viewer first workable version
+
=Jun 09 - Jun 13=
** ICARCV paper accepted
+
DTI Project:
** Be awarded the Sydney University Graduates Union of North America (SUGUNA) Alumni Scholarship.
+
* Test DWIConvert on Sample Data - DWIVolume
 +
** NrrdToFSL: Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert --conversionMode NrrdToFSL --inputVolume ./dwi.nhdr --outputVolume ./dwi_fsl.nii.gz --outputBValues ./bvals.txt --outputBVectors ./bvec.txt
 +
** FSLToNrrd: Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert --conversionMode FSLToNrrd --inputVolume ./dwi_fsl.nii.gz --outputVolume ./dwi_reconverted.nrrd --inputBValues ./bvals.txt --inputBVectors ./bvec.txt
 +
* Process the dataset of 'test1' with DWIConverter
 +
 
 +
* Update (2015-07-03):
 +
** Replace the original 'Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert' to 'Slicer --launch DWIConvert'
 +
<br \>
 +
 
 +
=Jun 16 - Jun 20=
 +
BWH:
 +
* Prepare the DS-2019 extension
 +
 
 +
DTI Project:
 +
* Process the dataset of 'patient2' with BrainVisa
 +
* Process the dataset of 'patient3' with BrainVisa
 +
 
 +
Publication:
 +
* MICCAI 2014 Machine Learning Challenge (MLC) result was revealed and we ranked 10th in 50 teams.
 +
<br \>
 +
 
 +
 
 +
=Jun 23 - Jun 27=
 +
NA-MIC Project:
 +
* NA-MIC 2014 SUMMER PROJECT WEEK
 +
* CAD Toolbox for Neurodegenerative Disease Diagnosis (http://www.na-mic.org/Wiki/index.php/2014_Summer_Project_Week:CAD_Toolbox_for_Neurological_Disorders)
 +
* Serve as NA-MIC tutorial contest judge
 +
 
 +
DTI Project:
 +
* Process the dataset of 'patient2_1' with DWIConverter. The b-values were found wrong.
 +
 
 +
Publication:
 +
* Prepare the DICTA 2014 abstract
 +
<br \>
 +
 
 +
 
 +
=Jun 30 - Jul 04=
 +
DTI Project:
 +
* Reprocess the dataset of 'patient2_1' with DWI Converter. The b-values seem correct.
 +
* Test 'DICOM-TO-NIFTI-CONVERTER' matlab toolbox (http://www.mathworks.com/matlabcentral/fileexchange/41874-dicom-to-nifti-converter/content/dicom2nifti.m). However, this toolbox is not usable for our SIEMENS data, because it only work with DICOM files from Phillips Achieva 3T R2.6 with
 +
** Slice orientation : transverse
 +
** Patient position  : head first
 +
** Patient orientation: supine
 +
** Fold-over direction: AP
 +
** Fat shift direction: P
 +
** Gradient resolution: high (DTI)
 +
** Gradient overplus  : yes (DTI)
 +
** Sort images        : b=0 volume first (DTI)
 +
 
 +
Publication:
 +
* Make the submission for DICTA 2014
 +
 
 +
 
 +
<br \>
 +
= Jul 07 - Jul 11=
 +
BWH:
 +
* Finalize DS-2019 extension, turns out that no need to extend it
 +
 
 +
DTI Project:
 +
* Mosaic Viewer first workable version
 +
 
 +
Publication:
 +
* ICARCV 2014 paper accepted
 +
 
 +
USYD:
 +
* Awarded the Sydney University Graduates Union of North America (SUGUNA) Alumni Scholarship
 +
<br \>
 +
 
 +
 
 +
=Jul 14 - Jul 18=
 +
Publication:
 +
* Submit EMBC 2014 camera-ready version
 +
* Submit DTIChallenge 2014 camera-ready version
 +
 
 +
USYD:
 +
* Application for Postgraduate Research Travel Scheme was approved
 +
 
 +
 
 +
<br \>
 +
=Jul 21 - Jul 25=
 +
Publication:
 +
* Invited to give an oral presentation in MICCAI -MLC workshop
 +
 
 +
DTI Project:
 +
* Update Mosaic Viewer. Now it can restore the exact snapshot as saved in the scene views.
 +
<br \>
 +
 
 +
 
 +
=Jul 28 - Aug 01=
 +
USYD:
 +
* Co-supervise Tom's new student, Nur, on his 18pt research project - Feature Extraction and Coding for Diffusion MRI
 +
 
 +
ADNI Project:
 +
* Test new FreeSurfer features extracted from the ADNI datasets by UCSF lab, the performance of multi-class classification (NC/MCI/AD) is 81.25%.
 +
<br \>
 +
 
 +
 
 +
=Aug 04 - Aug 08=
 +
Publication:
 +
* Submit ICARCV 2014 camera-ready version
 +
* Make the MIA 2014 BoVW paper initial submission
 +
 
 +
USYD:
 +
* Refine Fan's visiting scholar request
 +
<br \>
 +
 
 +
 
 +
=Aug 11 - Aug 15=
 +
USYD:
 +
* Start PhD thesis writing
 +
 
 +
 
 +
<br \>
 +
=Aug 18 - Aug 22=
 +
DTI Project:
 +
* Add a new feature in Mosaic Viewer. Now all the viewers can be synchronized through the 'Sync Camera' function.
 +
** Step 1: load or create the scene views
 +
** Step 2: select the master viewer where the user defines the orientation via 'view to synchronize' drop list.
 +
** Step 3: click 'Sync Camera' button, the orientation will propagate to all other viewers.
 +
<br \>
 +
 
 +
 
 +
=Aug 25 - Aug 29=
 +
Travel:
 +
* Attend EMBC 2014 conference in Chicago, Sep 27 - 31.
 +
<br \>
 +
 
 +
=Sep 01 - Sep 05=
 +
BWH:
 +
* Move home to Allston
 +
 
 +
DTI Project:
 +
* Process the dataset of 'patient4' with BrainVisa
 +
 
 +
Publication:
 +
* Prepare the ACALCI 2015 abstract
 +
<br \>
 +
 
 +
 
 +
=Sep 08 - Sep 12=
 +
Publication:
 +
* Prepare the MIA cross-view pattern analysis manuscript
 +
* Submit the ACALCI 2015 abstract paper.
 +
 
 +
DTI Project:
 +
* Process the datasets for patient 4 with DTIPrep, including the original DWI dataset and the truncated DWI dataset.
 +
* DTI Challenge logistics
 +
** Attend the DTIChallenge preparation meeting, arrange the conference room and test the systems.
 +
** Process the dataset for patient 3 with BrainVisa.
 +
** Summarize the DTI Challenge review results.
 +
** Generate the box plots for DTI Challenge review results.
 +
** Prepare the envelops and folders.
 +
** Print out the onsite review forms.
 +
** Prepare the USB keys.
 +
<br \>
 +
 
 +
 
 +
=Sep 14 - Sep 19=
 +
DTI Project:
 +
* Attend the MICCAI DTI Challenge, Sep 14
 +
* Attend the MICCAI main conference, Sep 15 - Sep 17
 +
* Attend the MICCAI CADDementia Challenge, Sep 18 morning
 +
* Attend the MICCAI Machine Learning Challenge, Sep 18 afternoon
 +
<br \>
 +
 
 +
 
 +
=Sep 22 - Oct 03=
 +
* Two weeks' leave
 +
<br \>
 +
 
 +
=Oct 06 - Oct 10=
 +
Lung project:
 +
* Manually draw the boundaries between the bronchi in right lung
 +
* Generate the models using the Draw Model tool in Slicer 3.6.4.
 +
* Save the models and the scene and check their compatibility with Slicer 4.
 +
<br \>
 +
 
 +
 
 +
=Oct 13 - Oct 17=
 +
Lung Project:
 +
* Update color look up table http://wiki.na-mic.org/Wiki/index.php/Lung_Segments_Color_Map
 +
* Regenerate the models for the dataset
 +
* Literature review on automated segmentation of lung segments. http://lola11.com/
 +
* Try airway segmentation on Slicer 4 with lung project dataset.
 +
[Error!]
 +
Found SharedObject Module
 +
ModuleType: SharedObjectModule
 +
Airway Segmentation command line:
 +
 
 +
slicer:0x127abf2c0 --processinformationaddress 0x10f4ce890 --labelValue 2 --seed 2.62861,-49.8569,-70.25 --seed 11.4569,-52.7997,-99.25 --seed -9.14251,-53.7807,-99.25 slicer:0x11370ee00#vtkMRMLScalarVolumeNode2 slicer:0x11370ee00#vtkMRMLScalarVolumeNode3
 +
 
 +
 
 +
NA-MIC Project:
 +
* Update Slicer4 programming tutorial slides and code.
 +
<br \>
 +
 
 +
 
 +
=Oct 20 - Oct 24=
 +
Lung Project:
 +
* Literature review on the vessel-based lung segmentation
 +
* Recreate the scene fro Slicer4 with the vessel models included
 +
* Update the color code for the models
 +
 
 +
Publication:
 +
* Finalize the MIA paper manuscript
 +
* Finalize the TBE paper manuscript
 +
* Finalize PhD thesis manuscript
 +
<br \ >
 +
 
 +
=Oct 27 - Oct 31=
 +
Lung Project:
 +
* Check the vessel segmentation tool in the Cardiac Agaston tutorial with Jessica http://wiki.na-mic.org/Wiki/index.php/CardiacAgatstonScoring_TutorialContestSummer2014
 +
 
 +
Publication:
 +
* Make the TBME paper submission
 +
* Make the MIA paper submission
 +
* Make thesis submission
 +
<br \>
 +
 
 +
 
 +
=Nov 03 - Nov 07=
 +
Lung Project:
 +
* Download and install VMTK
 +
 
 +
Publication:
 +
* TBME paper review
 +
* TBME revision submission
 +
* ACALCI camera-ready version submission
 +
* Prepare ISBI 2014 papers
 +
<br \>
 +
 
 +
=Nov 10 - Nov 14=
 +
Travel:
 +
* Attend the [http://gcbme.embs.org/brain2014/ IEEE EMBS Grand Challenge Conference]
 +
* Participate the Young Investigator Award Competition
 +
 
 +
<br \>
 +
 
 +
=Nov 17 - Nov 21=
 +
 
 +
BCC Project:
 +
 
 +
* Literature review for Brain Connectome Computing (BCC) project.
 +
 
 +
Publication:
 +
 
 +
* Our recent paper, Multi-Modal Neuroimaging Feature Learning for Multi-Class Diagnosis of Alzheimer's Disease, is accepted to publish in IEEE TBME.
 +
 
 +
<br \>
 +
 
 +
=Nov 24 - Nov 28=
 +
 
 +
BCC Project:
 +
* Outline the research proposal: background, aims, methods, tasks, timelines and resources
 +
 
 +
Publication:
 +
* Make ISBI 2014 paper submissions
 +
 
 +
<br \>
 +
 
 +
=Dec 01 - Dec 05=
 +
 
 +
BCC Project:
 +
 
 +
* Design the website of for BCC project.
 +
* Prepare the application for Amazon Web Service (AWS) in education research grants.
 +
http://aws.amazon.com/education/aws-in-education-research-grants/
 +
 
 +
<br \>
 +
 
 +
=Dec 08 - Dec 12=
 +
 
 +
Conference:
 +
* Prepare ICARCV 2014 slides (presented by Tom)
 +
 
 +
MRMD Project:
 +
* Design the experiment for graph-based multi-modal retrieval
 +
* Prepare the draft for Multi-modal Retrieval in Medical Domain (MRMD) Workshop at ECIR 2015.
 +
http://www.visceral.eu/workshops/mrmd-2015/
 +
 
 +
Sonia's To do list:
 +
*Document the steps for running Brain Visa from a neuro case
 +
*Document the steps for running DTI Prep in Slicer4.4
 +
 
 +
<br \>
 +
 
 +
=Dec 15 - Dec 19=
 +
* End of project
 
<br \>
 
<br \>

Latest revision as of 08:02, 3 July 2015

Home < SidongLiu Update

Jan 30 - Jan 31

Travel:

  • Depart from Sydney - Jan 30
  • Arrive in Boston - Jan 31



Feb 03 - Feb 07

BWH:

  • Attend Partners orientation - Feb 06


Feb 10 - Feb 14

Publication:

  • Prepare MICCAI 2014 papers



Feb 17 - Feb 21

DTI Project:

  • Develop TractROIShellSeeding module in Slicer



Feb 24 - Feb 28

Publication:

  • MICCAI 2014 paper submissions



Mar 12 - Mar 14

BWH:

  • Attend BWH orientation
  • Start to work at SPL, 75 Fransic St



Mar 17 - Mar 21

Publication:

  • Make EMBC 2014 paper submission

DTI Project:

  • Implement a new functionality for peritumoral tract exploration


Mar 24 - Mar 28

Publication:

  • Submit MICCAI 2014 paper reviews
  • SNMMI 2014 abstract papers accepted

DTI Project:

  • Reformat the Hausdorff outputs


Mar 31 - Apr 4

USYD:

  • Submit postdoctoral fellowship application

BWH:

  • Start to work at SPL, 1249 Boylston St



Apr 7 - Apr 11

Publication:

  • Make CMIG journal paper revision submission
  • Prepare the ACM MM 2014 abstract

DTI Project:



Apr 14 - Apr 18

DTI Project:



Apr 21 - Apr 25

DTI Project:

  • Make progress to the Mosaic Viewer module. Now it can display and manipulate multiple independent 3D viewers at the same time
  • Discuss DTI Challenge preparation. Need to install Evernote and Live Minutes to enhance collaboration
  • Next step would be to finalize the Mosaic Viewer by creating a scene view for the it
  • The original test dataset is a HARDI dataset with 69 gradients plus 4 baselines, and we extracted 30 volumes whose b-values equal to 1000.

USYD:

  • Submit the Grants-in-Aid application



April 28 - May 02

DTI Project:

  • Finalize the Mosaic Viewer module.
  • Successfully load and corrected the Brain Visa surface files into Slicer. Next step would be streamline the process. There might be three potential solutions:
    • Build CLI modules (SlicerToBrainVisa Import and Export) to integrate Brain Visa morphologist tools in Slicer. Check NiftyReg extension as an example (https://github.com/spujol/niftyregExtension) and Hello World tutorial to learn how to integrate .cxx plugins (http://www.slicer.org/slicerWiki/images/2/22/ProgrammingIntoSlicer3.6_SoniaPujol.pdf). Note this tutorial might need to be updated to Slicer 4.
    • Build a Python wrapper which point to the Brain Visa executable files and run Brain Visa in Slicer.
    • Write a simple script to 1) convert nhdr to Nifty; 2) filp left / right by changing RAS to LPI coordinate system; 3) run Morphologist pipeline in Brain Visa; 4) load output .ply file in Slicer; and 5) apply 'BrainVisatoSlicer' transform if the coordinate differences were independent to the datasets.
  • Test the DWIConverter module to convert DICOM to nhdr using the datasets '...high-b.raw.gz' dataset and compare the output to '...high-b.nhdr'.
  • New tasks regarding the test dataset:
    • Create the tractography for extracted dataset only using single tensor algorithm
    • Compare the result to that of original dataset using UKF extension
    • Run the DTIPrep extension on both datasets (original and extracted)



May 05 - May 09

DTI Project:

  • Reconstruct the tensors using eigen values and eigen vectors. Slicer could not handle eigen vectors directly, so we ned to calculate the 7 coefficients in the tensor matrix.

Publication:

  • CMIG multi-channel pattern analysis paper accepted



May 12 - May 16

DTI Project:

  • Run DTIPrep for all the datasets.
  • Clean up and classify all the processed datasets.
  • Send email to Francois checking what are the differences VC and QCed results.
  • Send BrainVisa screenshots to Sonia, describing the sulci recognition problems.
  • Run UKF tractography with 1-6 seeds per voxel, 2 tensors, other parameters by default.

Publication:



May 19 - May 23

DTI Project:

  • Process the new dataset 'test1'
  • Solve the DTIPrep problems.
    • 1 Why there are 4 baseline images in the original dataset, but only one is left after processing?
    • - All the baselines are merged into one image.
    • 2. How to see the sphere after quality check?
    • - We need to first save the results, and then load the XML to DTIPrep.
    • 3. Why the gradient directions are changed after processing?
    • - This might be a bug, resulted from rounding errors.
    • 4. Why there are holes in the QCed DTI dataset?
    • - We need to reset the parameter 'DTI_bCompute - DTI_baselineThreshold'.



May 26 - May 30

Publication:

  • Submit propagation matrix fusion paper to ICARCV 2014.

DTI Project:

  • Rerun DTIPrep on 'test1'. After testing with different settings, we found when this parameter is set to less than 50, the holes disappear.



Jun 02 - Jun 06

DTI Project:

  • Run BrainVisa on T1 and T2 registered data, use label map as a mask to filter out the lesion from the generated surface. Try 'Resample Scalar/Vector/DWI Volume' module, set 'Interpolation Type' to ws.
  • Run 'Slicer Surface Toolbox' to refine BrainVisa surface. Chcek 'splitting' box in Normals.
  • Convert DICOM to FSL (nifty) format.

NA-MIC Project:

  • Invited as one of the NA-MIC tutorial contest judges.

BWH:

  • Attend Junichi's MRI-Robotic experiment

Publication:

  • TBE Deep-Learning paper submission



Jun 09 - Jun 13

DTI Project:

  • Test DWIConvert on Sample Data - DWIVolume
    • NrrdToFSL: Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert --conversionMode NrrdToFSL --inputVolume ./dwi.nhdr --outputVolume ./dwi_fsl.nii.gz --outputBValues ./bvals.txt --outputBVectors ./bvec.txt
    • FSLToNrrd: Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert --conversionMode FSLToNrrd --inputVolume ./dwi_fsl.nii.gz --outputVolume ./dwi_reconverted.nrrd --inputBValues ./bvals.txt --inputBVectors ./bvec.txt
  • Process the dataset of 'test1' with DWIConverter
  • Update (2015-07-03):
    • Replace the original 'Slicer-build/lib/Slicer-4.3/cli-modules/DWIConvert' to 'Slicer --launch DWIConvert'


Jun 16 - Jun 20

BWH:

  • Prepare the DS-2019 extension

DTI Project:

  • Process the dataset of 'patient2' with BrainVisa
  • Process the dataset of 'patient3' with BrainVisa

Publication:

  • MICCAI 2014 Machine Learning Challenge (MLC) result was revealed and we ranked 10th in 50 teams.



Jun 23 - Jun 27

NA-MIC Project:

DTI Project:

  • Process the dataset of 'patient2_1' with DWIConverter. The b-values were found wrong.

Publication:

  • Prepare the DICTA 2014 abstract



Jun 30 - Jul 04

DTI Project:

  • Reprocess the dataset of 'patient2_1' with DWI Converter. The b-values seem correct.
  • Test 'DICOM-TO-NIFTI-CONVERTER' matlab toolbox (http://www.mathworks.com/matlabcentral/fileexchange/41874-dicom-to-nifti-converter/content/dicom2nifti.m). However, this toolbox is not usable for our SIEMENS data, because it only work with DICOM files from Phillips Achieva 3T R2.6 with
    • Slice orientation : transverse
    • Patient position : head first
    • Patient orientation: supine
    • Fold-over direction: AP
    • Fat shift direction: P
    • Gradient resolution: high (DTI)
    • Gradient overplus : yes (DTI)
    • Sort images : b=0 volume first (DTI)

Publication:

  • Make the submission for DICTA 2014



Jul 07 - Jul 11

BWH:

  • Finalize DS-2019 extension, turns out that no need to extend it

DTI Project:

  • Mosaic Viewer first workable version

Publication:

  • ICARCV 2014 paper accepted

USYD:

  • Awarded the Sydney University Graduates Union of North America (SUGUNA) Alumni Scholarship



Jul 14 - Jul 18

Publication:

  • Submit EMBC 2014 camera-ready version
  • Submit DTIChallenge 2014 camera-ready version

USYD:

  • Application for Postgraduate Research Travel Scheme was approved



Jul 21 - Jul 25

Publication:

  • Invited to give an oral presentation in MICCAI -MLC workshop

DTI Project:

  • Update Mosaic Viewer. Now it can restore the exact snapshot as saved in the scene views.



Jul 28 - Aug 01

USYD:

  • Co-supervise Tom's new student, Nur, on his 18pt research project - Feature Extraction and Coding for Diffusion MRI

ADNI Project:

  • Test new FreeSurfer features extracted from the ADNI datasets by UCSF lab, the performance of multi-class classification (NC/MCI/AD) is 81.25%.



Aug 04 - Aug 08

Publication:

  • Submit ICARCV 2014 camera-ready version
  • Make the MIA 2014 BoVW paper initial submission

USYD:

  • Refine Fan's visiting scholar request



Aug 11 - Aug 15

USYD:

  • Start PhD thesis writing



Aug 18 - Aug 22

DTI Project:

  • Add a new feature in Mosaic Viewer. Now all the viewers can be synchronized through the 'Sync Camera' function.
    • Step 1: load or create the scene views
    • Step 2: select the master viewer where the user defines the orientation via 'view to synchronize' drop list.
    • Step 3: click 'Sync Camera' button, the orientation will propagate to all other viewers.



Aug 25 - Aug 29

Travel:

  • Attend EMBC 2014 conference in Chicago, Sep 27 - 31.


Sep 01 - Sep 05

BWH:

  • Move home to Allston

DTI Project:

  • Process the dataset of 'patient4' with BrainVisa

Publication:

  • Prepare the ACALCI 2015 abstract



Sep 08 - Sep 12

Publication:

  • Prepare the MIA cross-view pattern analysis manuscript
  • Submit the ACALCI 2015 abstract paper.

DTI Project:

  • Process the datasets for patient 4 with DTIPrep, including the original DWI dataset and the truncated DWI dataset.
  • DTI Challenge logistics
    • Attend the DTIChallenge preparation meeting, arrange the conference room and test the systems.
    • Process the dataset for patient 3 with BrainVisa.
    • Summarize the DTI Challenge review results.
    • Generate the box plots for DTI Challenge review results.
    • Prepare the envelops and folders.
    • Print out the onsite review forms.
    • Prepare the USB keys.



Sep 14 - Sep 19

DTI Project:

  • Attend the MICCAI DTI Challenge, Sep 14
  • Attend the MICCAI main conference, Sep 15 - Sep 17
  • Attend the MICCAI CADDementia Challenge, Sep 18 morning
  • Attend the MICCAI Machine Learning Challenge, Sep 18 afternoon



Sep 22 - Oct 03

  • Two weeks' leave


Oct 06 - Oct 10

Lung project:

  • Manually draw the boundaries between the bronchi in right lung
  • Generate the models using the Draw Model tool in Slicer 3.6.4.
  • Save the models and the scene and check their compatibility with Slicer 4.



Oct 13 - Oct 17

Lung Project:

[Error!] Found SharedObject Module ModuleType: SharedObjectModule Airway Segmentation command line:

slicer:0x127abf2c0 --processinformationaddress 0x10f4ce890 --labelValue 2 --seed 2.62861,-49.8569,-70.25 --seed 11.4569,-52.7997,-99.25 --seed -9.14251,-53.7807,-99.25 slicer:0x11370ee00#vtkMRMLScalarVolumeNode2 slicer:0x11370ee00#vtkMRMLScalarVolumeNode3


NA-MIC Project:

  • Update Slicer4 programming tutorial slides and code.



Oct 20 - Oct 24

Lung Project:

  • Literature review on the vessel-based lung segmentation
  • Recreate the scene fro Slicer4 with the vessel models included
  • Update the color code for the models

Publication:

  • Finalize the MIA paper manuscript
  • Finalize the TBE paper manuscript
  • Finalize PhD thesis manuscript


Oct 27 - Oct 31

Lung Project:

Publication:

  • Make the TBME paper submission
  • Make the MIA paper submission
  • Make thesis submission



Nov 03 - Nov 07

Lung Project:

  • Download and install VMTK

Publication:

  • TBME paper review
  • TBME revision submission
  • ACALCI camera-ready version submission
  • Prepare ISBI 2014 papers


Nov 10 - Nov 14

Travel:


Nov 17 - Nov 21

BCC Project:

  • Literature review for Brain Connectome Computing (BCC) project.

Publication:

  • Our recent paper, Multi-Modal Neuroimaging Feature Learning for Multi-Class Diagnosis of Alzheimer's Disease, is accepted to publish in IEEE TBME.


Nov 24 - Nov 28

BCC Project:

  • Outline the research proposal: background, aims, methods, tasks, timelines and resources

Publication:

  • Make ISBI 2014 paper submissions


Dec 01 - Dec 05

BCC Project:

  • Design the website of for BCC project.
  • Prepare the application for Amazon Web Service (AWS) in education research grants.

http://aws.amazon.com/education/aws-in-education-research-grants/


Dec 08 - Dec 12

Conference:

  • Prepare ICARCV 2014 slides (presented by Tom)

MRMD Project:

  • Design the experiment for graph-based multi-modal retrieval
  • Prepare the draft for Multi-modal Retrieval in Medical Domain (MRMD) Workshop at ECIR 2015.

http://www.visceral.eu/workshops/mrmd-2015/

Sonia's To do list:

  • Document the steps for running Brain Visa from a neuro case
  • Document the steps for running DTI Prep in Slicer4.4


Dec 15 - Dec 19

  • End of project