SidongLiu Update
From NAMIC Wiki
Home < SidongLiu Update
Contents
- 1 Jan 30 - Jan 31
- 2 Feb 03 - Feb 07
- 3 Feb 10 - Feb 14
- 4 Feb 17 - Feb 21
- 5 Feb 24 - Feb 28
- 6 Mar 12 - Mar 14
- 7 Mar 17 - Mar 21
- 8 Mar 24 - Mar 28
- 9 Mar 31 - Apr 4
- 10 Apr 7 - Apr 11
- 11 Apr 14 - Apr 18
- 12 Apr 21 - Apr 25
- 13 April 28 - May 02
- 14 May 05 - May 09
- 15 May 12 - May 16
- 16 May 19 - May 23
- 17 May 26 - May 30
- 18 Jun 02 - Jun 06
- 19 Jun 09 - Jun 13
- 20 Jun 16 - Jun 20
- 21 Jun 23 - Jun 27
- 22 Jun 30 - Jul 04
- 23 Jul 07 - Jul 11
- 24 Jul 14 - Jul 18
- 25 Jul 21 - Jul 25
- 26 Jul 28 - Aug 01
- 27 Aug 04 - Aug 08
- 28 Aug 11 - Aug 15
- 29 Aug 18 - Aug 22
- 30 Aug 25 - Aug 29
- 31 Sep 01 - Sep 05
- 32 Sep 08 - Sep 12
- 33 Sep 15 - Sep 19
- 34 Sep 22 - Oct 03
- 35 Oct 06 - Oct 10
- 36 Oct 13 - Oct 17
- 37 Oct 20 - Oct 24
- 38 Oct 27 - Oct31
- 39 Nov 03 - Nov 07
- 40 Nov 10 - Nov 14
- 41 Nov 17 - Nov 21
- 42 Nov 24 - Nov 28
- 43 Dec 01 - Dec 05
- 44 Dec 08 - Dec 12
- 45 Dec 15 - Dec 19
Jan 30 - Jan 31
- Depart from Sydney - Jan 30
- Arrive in Boston - Jan 31
Feb 03 - Feb 07
- Attend Partners orientation - Feb 06
Feb 10 - Feb 14
- Prepare MICCAI 2014 papers
Feb 17 - Feb 21
- Develop TractROIShellSeeding module in Slicer
Feb 24 - Feb 28
- MICCAI 2014 paper submissions
Mar 12 - Mar 14
- Attend BWH orientation
- Start to work at SPL, 75 Fransic St
Mar 17 - Mar 21
- Make EMBC 2014 paper submission
- Implement a new functionality for peritumoral tract exploration
Mar 24 - Mar 28
- Submit MICCAI 2014 paper reviews
- SNMMI 2014 abstract papers accepted
- Reformat the Hausdorff outputs
Mar 31 - Apr 4
- Submit postdoctoral fellowship application
- Start to work at SPL, 1249 Boylston St
Apr 7 - Apr 11
- Make CMIG journal paper revision submission
- Prepare the ACM MM 2014 abstract
- 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.
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)
- 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
Apr 21 - Apr 25
- 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
- Submit the Grants-in-Aid application
- 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.
April 28 - May 02
- 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
- 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.
- CMIG multi-channel pattern analysis paper accepted
May 12 - May 16
- 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.
- CMIG multi-channel pattern analysis paper available online http://www.sciencedirect.com/science/article/pii/S0895611114000639
May 19 - May 23
- 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
- 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.
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.
- Convert DICOM to FSL (nifty) format.
- Invited as one of the NA-MIC tutorial contest judges.
- Attend Junichi's MRI-Robotic experiment
- TBE Deep-Learning paper submission
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
- 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
Jun 16 - Jun 20
- Prepare the DS-2019 extension
- Process the dataset of 'patient2' with BrainVisa
- Process the dataset of 'patient3' with BrainVisa
- MICCAI 2014 Machine Learning Challenge (MLC) result was revealed and we ranked 10th in 50 teams.
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
- Process the dataset of 'patient2_1' with DWIConverter. The b-values were found wrong.
- Prepare the DICTA 2014 abstract
Jun 30 - Jul 04
- 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)
- Make the submission for DICTA 2014
Jul 07 - Jul 11
- Finalize DS-2019 extension, turns out that no need to extend it
- Mosaic Viewer first workable version
- ICARCV 2014 paper accepted
- Awarded the Sydney University Graduates Union of North America (SUGUNA) Alumni Scholarship
Jul 14 - Jul 18
- Submit EMBC 2014 camera-ready version
- Application for Postgraduate Research Travel Scheme was approved
- Submit DTIChallenge 2014 camera-ready version
Jul 21 - Jul 25
- Invited to give an oral presentation in MICCAI -MLC workshop
- Update Mosaic Viewer. Now it can restore the exact snapshot as saved in the scene views.
Jul 28 - Aug 01
- Co-supervise Tom's new student, Nur, on his 18pt research project - Feature Extraction and Coding for Diffusion MRI
- 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
- Submit ICARCV 2014 camera-ready version
- Refine Fan's visiting scholar request
- Make the MIA 2014 BoVW paper initial submission
Aug 11 - Aug 15
- PhD thesis writing
Aug 18 - Aug 22
- 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
- Attend EMBC 2014 conference in Chicago, Sep 27 - 31.
Sep 01 - Sep 05
- Move home to Allston
- Process the dataset of 'patient4' with BrainVisa
- Prepare the ACALCI 2015 abstract
Sep 08 - Sep 12
- Prepare the MIA cross-view pattern analysis manuscript
- Finalize PhD thesis
- Submit the ACALCI 2015 abstract paper.
- 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 15 - Sep 19
- Attend MICCAI 2014 conference in Boston
Sep 22 - Oct 03
- Two weeks' leave
Oct 06 - Oct 10
Lung project:
- Graw 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:
- 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.
- Check the vessel segmentation tool in the Cardiac Agaston tutorial with Jessica http://wiki.na-mic.org/Wiki/index.php/CardiacAgatstonScoring_TutorialContestSummer2014
- Try airway segmentation on Slicer 4 with lung project dataset.
NA-MIC Project:
- Update Slicer4 programming tutorial slides and code.
Oct 20 - Oct 24
Oct 27 - Oct31
Nov 03 - Nov 07
Nov 10 - Nov 14
Nov 17 - Nov 21
Nov 24 - Nov 28
Dec 01 - Dec 05
Dec 08 - Dec 12
Dec 15 - Dec 19
- End of project