0.10.0

CHANGES

• [ENH] Update AFNI to the current latest version (#669).
• [ENH] Update pybids (#668)

0.9.10

With thanks to @justbennet for contributions

CHANGES

• [FIX] Update niworkflows (#656)
• [ENH] Recursively set read/Xecute permission for miniconda (#650)

0.9.9

With thanks to @justbennet for contributions on containerization.

• [ENH] Update nipype to the latest dev version, which includes many improvements and bugfixes.
• [ENH] Use new resource monitoring of nipype.

0.9.8

With thanks to Jan Varada (@jvarada) for the session/run filtering.

CHANGES

• [ENH] Report recall in cross-validation (requested by reviewer) (#633)
• [ENH] Hotfixes to 0.9.7 (#635)
• [FIX] Implement filters for session, run and task of BIDS input (#612)

0.9.7

CHANGES

• [ENH] Clip outliers in FD and SPIKES group plots (#593)
• [ENH] Second revision of the classifier (#555):
  • Set matplotlib plugin to agg in docker image
  • Migrate scalings to sklearn pipelining system
  • Add Satra's feature selection for RFC (with thanks to S. Ghosh for his suggestion)
  • Make model selection compatible with sklearn Pipeline
  • Multiclass classification
  • Add feature selection filter based on Sites prediction (requires pinning to development sklearn-0.19)
  • Add RobustLeavePGroupsOut, replace RobustGridSearchCV with the standard GridSearchCV of sklearn.
  • Choice between RepeatedStratifiedKFold and RobustLeavePGroupsOut in mriqc_clf
  • Write cross-validation results to an .npz file.
• [ENH] First revision of the classifier (#553):
  • Add the possibility of changing the scorer function.
  • Unifize labels for raters in data tables (to rater_1)
  • Add the possibility of setting a custom decision threshold
  • Write the probabilities in the prediction file
  • Revised mriqc_clf processing flow
  • Revised labels file for ds030.
  • Add IQMs for ABIDE and DS030 calculated with MRIQC 0.9.6.
• ANNOUNCEMENT: Dropped support for Python<=3.4
• WARNING (#596):
  We have changed the default number of threads for ANTs. Using parallelism with ANTs
  causes numerical instability on the calculated measures. The most sensitive metrics to this
  problem are the kurtosis calculations on the intensities of regions and qi_2.

0.9.6

MRIQC 0.9.6 incorporates the new MRIQCWebAPI and bugfixes.

CHANGES

• [ENH] Finished setting up MRIQC Web API
• [ENH] Better error message when --participant_label is set (#542)
• [FIX] Allow --load-classifier option to be empty in mriqc_clf (#544)
• [FIX] Borked bias estimation derived from Conform (#541)
• [ENH] Test against web API 0.3.2 (#540)
• [ENH] Change the default Web API address (#539)
• [ENH] MRIQCWebAPI: hash fields that may have PI (#538)
• [ENH] Added token authorization to MRIQCWebAPI client (#535)
• [FIX] Do not mask and antsAffineInitializer twice (#534)
• [FIX] Datasets where air (hat) mask is empty (#533)
• [ENH] Integration testing for MRIQCWebAPI (#520)
• [ENH] Use AFNI to calculate gcor (#531)
• [ENH] Refactor derivatives (#530)
• [ENH] New bold-IQM: dummy_trs (non-stady state volumes) (#524)
• [FIX] Order of BIDS components in IQMs CSV table (#525)
• [ENH] Improved logging of mriqc_run (#526)

0.9.5

A new release exploring the new intensity normalization.

Changes

• [ENH] Refactored structural metrics calculation (#513)
• [ENH] Calculate rotation mask (#515)
• [ENH] Intensity harmonization in the anatomical workflow (#510)
• [ENH] Set N4BiasFieldCorrection number of threads (#506)
• [ENH] Convert FWHM in pixel units (#503)
• [ENH] Add MRIQC client for feature crowdsourcing (#464)
• [DOC] Fix functional feature labels in documentation (docs_only) (#507)
• [FIX] New implementation for the rPVE feature (normalization, left-tail values) (#505)
• [ENH] Parse BIDS selectors (run, task, etc.), improve CLI (#504)

0.9.4

MRIQC 0.9.4 includes some bugfixes, and several maintenance patches (especially in continuous testing). Finally, a great speedup has been introduced in the new spatial normalization of T1w images (at the cost of accuracy).

Changes

• ANNOUNCEMENT: Dropped Python 2 support
• [ENH] Use versioneer to handle versions (#500)
• [ENH] Speed up spatial normalization (#495)
• [ENH] Resampling of hat mask and TPMs with linear interp (#498)
• [TST] Build documentation in CircleCI (#484)
• [ENH] Use full-resolution T1w images from ABIDE (#486)
• [TST] Parallelize tests (#493)
• [TST] Binding /etc/localtime stopped working in docker 1.9.1 (#492)
• [TST] Downgrade docker to 1.9.1 in circle (build_only) (#491)
• [TST] Check for changes in intermediate nifti files (#485)
• [FIX] Erroneous flag --n_proc in CircleCI (#490)
• [ENH] Add build_only tag to circle builds (#488)
• [ENH] Update Dockerfile (#482)
• [FIX] Ignore --profile flag with Linear plugin (#483)
• [DOC] Deep revision of the documentation (#479)
• [ENH] Minor improvements: SpatialNormalization and segmentation (#472)
• [ENH] Fixed typo for neurodebian install via apt-get (#478)
• [ENH] Updating fs2gif script (#465)
• [ENH] RF: Use niworkflows.interface.SimpleInterface (#468)
• [ENH] Add reproducibility of metrics tracking (#466)

0.9.3

• [ENH] Refactor of the Dockerfile to improve transparency, reduce size, and enable injecting code in Singularity (#457)
• [ENH] Make more the memory consumption estimates of each processing step more conservative to improve robustness (#456)
• [FIX] Minor documentation cleanups (#461)

0.9.2

• [ENH] Optional ICA reports for identifying spatiotemporal artifacts (#412)
• [ENH] Add --profile flag (#435)
• [ENH] Crashfiles are saved in plain text to improve portability (#434)
• [FIX] Fixes EPI mask erosion (#442)
• [ENH] Make FSL and AFNI motion correction more comparable by using the same scheme for defining the reference image (#444)
• [FIX] Temporarily disabling T1w quality classifier until it can be retrained on new measures (#447)