Version 2.1.8

What's Changed

• Allow dataset.json creation without labels by @joeranbosma in #50
• Documentation bugfix by @joeranbosma in #52
• Update README.md with Lancet Onc bib by @anindox8 in #53
• Preprocessing: add option to only pad and never crop by @joeranbosma in #54

New Contributors

• @anindox8 made their first contribution in #53

Full Changelog: v2.1.6...v2.1.8

Version 2.1.6

What's Changed

• Remove common prefixes from filenames when checking DICOM slice filenames by @joeranbosma in #45
• dcm2mha type hinting and output filename by @joeranbosma in #46

Full Changelog: v2.1.4...v2.1.6

Version 2.1.4

What's Changed

• dcm2mha: remove localizer slices, improve logging by @joeranbosma in #39
• dcm2mha: reduce memory usage by @joeranbosma in #42
• Update README with dcm2mha options by @snorthman in #43
• mha2nnunet: reduce logging about skipping cases by @joeranbosma in #44

Full Changelog: v2.1.3...v2.1.4

Version 2.1.3

• Logging mha2nnunet (#32): Write the traceback to the log when an error occurs, instead of silently
  continuing.
• mha2nnunet: skip converted cases (#35)

Version 2.1.2

• Verify DICOM filenames bugfix (#31)
• Improve robustness (#29)
  • Read metadata more reliably
  • Cleanup terminal output, by prioritizing dicom.zip
  • Cleanup spacing naming & ensure in-plane resolution

Version 2.1.0

Read dicom zip
Implemented new DICOMImageReader to organise DICOM reading:

• Read DICOM data from a folder or dicom.zip.
• Improve support with pydicom: image origin and direction are now set correctly.
• Fix metadata reading with pydicom: metadata is now read in the same way as SimpleITK.
• Cleanup: split image reading with SimpleITK/pydicom to separate functions. Move pydicom-specific function get_pydicom_value to dcm2mha.py.
• Update slice from which metadata is read to align with pydicom (now orientation etc. is read from the same slice as the metadata, which is better consistency anyway).
• Added unit tests to verify image reading with SimpleITK and pydicom.

Add metadata reading to DICOMImageReader:

• metadata can now be read without extracting anything from the dicom.zip.
• bring the responsibility for checking DICOM filenames to DICOMImageReader.
• added tests for reading from dicom.zip.

Version 2.0.0

Major updates:

• Archives are now converted case-by-case, instead of performing each phase after the other (i.e. collecting metadata for all cases, then converting images).
• Logging has improved and now offers three levels of verbosity: 1) show full case log when something goes wrong (default), 2) show full log for all cases, and 0) off.
• Improved usability of command-line interface: both DICOM → MHA and MHA → nnU-Net conversions are now available, as well as the generation of the conversion settings.
• Conversion of dynamic contrast-enhanced (DCE) scans is now supported (but experimental, feedback is welcome).

Updates that may require you to update your existing scripts:

• Some parameter names have changed (e.g. input_path to input_dir in MHA2nnUNetConverter). Please refer to the README or source code for the new values.
• Conversion settings for DICOM → MHA now require the patient_id and study_id for each item.

Minor updates:

• Multiprocessing is now optional. Set num_threads=1 to turn off.
• Improved creation of dataset.json for nnUNet raw data archive.
• Any DICOM tag can now be used to match cases to their target MHA file.
• The way values from DICOM tags are matched with the provided values is now configurable. See Dicom2MHAConverter's docstring for details.

Improved testing:

• Test DICOM → MHA conversion from both Python and the command line interface
• Test conversion of DCE scans

Version 1.3.2

• Multiprocessing for dcm2mha and mha2nnunet (#3)
• Increase flexibility dcm2mha pipeline (#5)
• Allow centre crop to (maximal) physical space (#6)
• Improved resampling to original/reference scan (#6)

Version 1.2

Implemented a new resampling strategy to harmonize the different sequences for mha2nnunet. This new resampling method is simpler and better, so the old convoluted way has been removed.

Version 1.1.1

v1.1.1

Bugfix