Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* ops using segmentation masks now accept Segmentation * simplified loader/writer specification in IO ops * simplified loader/writer specification in IO ops * updated imports in pipeline * improved ops repr * minor fixes in IO and segmentation * matching roi names in StructureSet.to_segmentation is now case-insensitive * fixed segmentation method call in some functional ops * fixed typo in pipeline warning message * StructureSet now correctly handles ROIs with no contour data * fixed error when trying to detect CSV delimiter in MetadataWriter * MetadataWriter can now remove existing files from previous runs * MetadataWriter can now remove existing files from previous runs * Segmentation object now correctly handles indexing * fixed segmentation mask handling in image statistics computation * removed old structure set code * removed old structure set code * fixed label handling in image statistics computation * fixed label handling in image statistics computation * [In Progress] Adding documentation to ops.py * added support for dynamic path specification in writers * image CSV loader now accepts pandas DataFrames * fixed indentation error * fixed index column handling in ImageCSVLoader * Revert "fixed index column handling in ImageCSVLoader" This reverts commit fab58d2. * fixed index column handling in ImageCSVLoader * fixed index column handling in ImageCSVLoader * ImageCSVLoader now returns correct keys * ImageCSVLoader now correctly handles globbing in paths * more informative exception handling in pipeline * pipeline can now warn on error instead of raising exception * [Docs] Cleaned up extra whitespace in ops.py * Added convenience method to get all ops in a pipeline * Fix empty array check in structure set conversion * Fix segmentation to label image conversion * Update README.md * Fix spurious mixin in ops * Fix type error when passing Numpy array to rotate * [Bugfix] Fix slice number rounding when generating a mask from RTSTRUCT * Fix crop size issue in crop_to_bounding_box * Make imports easier * Improved handling of regular expressions in structure set * Fix slice matching issue when generating binary mask from RTStruct * Fix binary mask generation from RTStruct when missing labels are present * little updates * added seg.nrrd compatibility * supports RTSTRUCT processing without roi_names * Fixed contour (RTSTRUCT) handling to rasterize multiple contours better. * Fixed contour (RTSTRUCT) handling to rasterize multiple contours better. * fixed structureset.py:148 * RT dose pipeline completed and tested. Error in segmentation not resolved * PET readability added * PET readability added * Head-Neck-PET-CT pipeline + `read_dicom_auto` * final pipeline working for doses and PET * corrected the view * reading in sitk format from beginning * Completed PET overlay * Modified RT dose, pipeline working for PET_CT quebec dataset * Added DataGraph, now fetching subset of dataset is supported using graph query * added crawl.py * Introduced changes in DataGraph. Made the pipeline fully general. Made wrapper classes * Rectified some bugs, added reference to rtplan in the crawler * Now missing RTDOSE references are completed by RTPLAN * small change * Fixed dataset.csv writing issues * major refactoring * more refactoring * Update radcure_simple.py * Update loaders.py * Update pet.py * Delete .DS_Store * Delete .DS_Store * Delete .DS_Store * Delete .DS_Store * Delete .DS_Store * Delete .DS_Store * Delete .DS_Store * ignore .DS_Store * Update README.md * quick README under ops * tcia_sample * example bash script with path parsing, fixed reference_frame * housekeeping * fixed dataset.csv * sanity changes before purging dev-20200414 * Added test autopipeline and modalities, solved some autopipeline bugs, read_dicom_series and pet now supports series_id * PT/RTDOSE metadata to csv * fixed some bugs in autopipeline.py * now the pipeline saves on exit * deleted data * now checks for existing subject id * uncommented one line pytest * uncommented one line pytest * self.existing, dataset.csv fixed (#10) * Added test autopipeline and modalities, solved some autopipeline bugs, read_dicom_series and pet now supports series_id * PT/RTDOSE metadata to csv * fixed some bugs in autopipeline.py * now the pipeline saves on exit * deleted data * now checks for existing subject id * uncommented one line pytest * uncommented one line pytest Co-authored-by: Vishwesh <vishweshramanathan@gmail.com> * Added dataset class which can load from nrrds or directly from the dataset and convert to pytorch dataset * Create build-ci.yml * Update build-ci.yml * Update requirements.txt * bug fixes_1.0 * test and autopipe fixed * bug fixes 2 * bug fixes 2 * added visualizations and some more bug fixes * Create manual-test.yml * Update build-ci.yml * Update manual-test.yml * PR tests - macos/ubuntu failing (#13) * Added test autopipeline and modalities, solved some autopipeline bugs, read_dicom_series and pet now supports series_id * PT/RTDOSE metadata to csv * fixed some bugs in autopipeline.py * now the pipeline saves on exit * deleted data * now checks for existing subject id * uncommented one line pytest * uncommented one line pytest * Added dataset class which can load from nrrds or directly from the dataset and convert to pytorch dataset * bug fixes_1.0 * test and autopipe fixed * bug fixes 2 * fixed pipeline tests * clean tests * added workflow * yml * yml * matplotlib * trying other patient to avoid memoryerror * set roi_names to avoid memoryerror * cave * indents * Update manual-test.yml Co-authored-by: Vishwesh <vishweshramanathan@gmail.com> * fixed bugs regarding multiple connections, saving of metadata and loading of metadata * small bug fix * added demo.py * Ready for * Create main.yml (#15) * Changed dataset class returns * fix conflicts * fixed test autopipe * merging new features (#16) * Added test autopipeline and modalities, solved some autopipeline bugs, read_dicom_series and pet now supports series_id * PT/RTDOSE metadata to csv * fixed some bugs in autopipeline.py * now the pipeline saves on exit * deleted data * now checks for existing subject id * uncommented one line pytest * uncommented one line pytest * Added dataset class which can load from nrrds or directly from the dataset and convert to pytorch dataset * bug fixes_1.0 * test and autopipe fixed * bug fixes 2 * bug fixes 2 * added visualizations and some more bug fixes * fixed bugs regarding multiple connections, saving of metadata and loading of metadata * small bug fix * added demo.py * Changed dataset class returns * fix conflicts * fixed test autopipe Co-authored-by: Vishwesh <vishweshramanathan@gmail.com> * fix path backslash issues * fix path backslashes (#17) * Added test autopipeline and modalities, solved some autopipeline bugs, read_dicom_series and pet now supports series_id * PT/RTDOSE metadata to csv * fixed some bugs in autopipeline.py * now the pipeline saves on exit * deleted data * now checks for existing subject id * uncommented one line pytest * uncommented one line pytest * Added dataset class which can load from nrrds or directly from the dataset and convert to pytorch dataset * bug fixes_1.0 * test and autopipe fixed * bug fixes 2 * bug fixes 2 * added visualizations and some more bug fixes * fixed bugs regarding multiple connections, saving of metadata and loading of metadata * small bug fix * added demo.py * Changed dataset class returns * fix conflicts * fixed test autopipe * fix path backslash issues Co-authored-by: Vishwesh <vishweshramanathan@gmail.com> * Update main.yml * Update main.yml * Update README.md * Update main.yml (#18) * Update main.yml * Update requirements.txt * Update main.yml * Update main.yml * build binary/dist * removed linter * Update setup.py * Update README.md * Update README.md (#19) * Update README.md * added tests for Dataset class * added tests for Dataset class * Create LICENSE (#20) * Create LICENSE * Update setup.py * Seg.nrrd quick fix * Minor bug fixes * test fix * Added demo * Update setup.py (#23) * updated README * Update README.md (#24) * preliminary MRI functionality (MR-RTSTRUCT pairs) * Skim2257 quick fix (#26) * Updated crawler to force String on all meta fields * Update setup.py * first commit * removed test files, changed gitignore * changed file directory structure for imageautooutput * split mask up into each contour * change kwargs in put for basesubjectwriter * still kinda failing... * brought back basesubjectwriter * .imgtools directory * changed absolute paths to relative paths * changed os.path.join to pathlib.Path.as_posix() * removed unused cv2 import * removed cv2 import * appened is deprecated, changed to concat * debug print * removed debug print * added sparse mask class and generating function * testing out sparse mask * funky NaN problem * commented sparse mask * overwrite all subjects * space * overwrite false * metadata stuffs * metadata in dataset.csv * added modalities, num rtstruct and pixel size to metadata * metadata bugfix * a * fixed wrong variable names for metadata stuff * fixed pathlib float error * relative paths and output folder paths for dataset.csv * put metadata stuff into a util file * deal with empty metadata * messing around with sparse mask * tried to save sparse mask, did some stuff with nnunet output format * compliant with nnunet directory structure * CLI Interface, argparse moved to utils * fixed formatting problems with folder names * train test split * train size and random state optional * merge conflicts * changed warnings to not interrupt * changed to warnings.warn for generate_sparse_mask * merge * resolving conflicts? * args * changes for roi names as a dict * added regex dictionary option for non nnunet runs * sparse mask global labelling for contour name: index * got rid of file_name_convention stuff * conflicts resolved * yaml thing * added list capabilities for the roi names dictionary * dataset.json for nnunet * CLI "autonew" * changed all mutable defaults to None * moved autotest changes to autopipeline and addede a few CLI args * getting ready for merge to live * test_components, test_modalities works with new AutoPipeline * overwrite changes and error fix for nan paths again * fixed if statement * joblib parallel * warnings for missing patients * summary messages * updated, passing tests. Updated version to 0.4 * update test * yaml path cli * yaml error check * pandas error * Fixed read_dicom_auto * skips series check if seris is None * updated readme to reflect v0.4 changes * updated readme * minor change * remove .idea * remote .idea * git ignore * refactor nnunetutils to nnunet Co-authored-by: przebieglykaziu <mkazmierski.poznan@gmail.com> Co-authored-by: Minoru Nakano <minoru.nakano@gmail.com> Co-authored-by: Sejin Kim <sejinkim@uhnslurmbuildbox.uhnh4h.cluster> Co-authored-by: Sejin Kim <sejinkim@node88.uhnh4h.cluster> Co-authored-by: Sejin Kim <sejinkim@node40.uhnh4h.cluster> Co-authored-by: Sejin Kim <sejinkim@node97.uhnh4h.cluster> Co-authored-by: Sejin Kim <sejinkim@h4huhnlogin2.uhnh4h.cluster> Co-authored-by: Vishwesh Ramanathan <vishwesh@Vishweshs-Air.uhn.ca> Co-authored-by: Sejin Kim <sejinkim@node38.uhnh4h.cluster> Co-authored-by: Vishwesh Ramanathan <ramanav@node49.uhnh4h.cluster> Co-authored-by: Vishwesh Ramanathan <ramanav@node53.uhnh4h.cluster> Co-authored-by: Vishwesh <vishweshramanathan@gmail.com> Co-authored-by: Benjamin Haibe-Kains <bhaibeka@bhaibek1.uhn.ca> Co-authored-by: Sejin Kim <sejinkim@node89.uhnh4h.cluster> Co-authored-by: Sejin Kim <hello@sejin.kim> Co-authored-by: Sejin Kim <40668167+skim2257@users.noreply.github.com> Co-authored-by: Vishwesh Ramanathan <vishwesh@Vishweshs-MacBook-Air.local> Co-authored-by: Kevin Qu <kqu@uhnslurmbuildbox.uhnh4h.cluster> Co-authored-by: Kevin Qu <kqu@node90.uhnh4h.cluster>
- Loading branch information
20 people
authored
Jun 25, 2022
1 parent
0cce0ee
commit 66a85e2