[SCHEMA] Start drafting validation rules for ASL data

src/schema/rules/sidecars/asl_validation.yaml

@@ -0,0 +1,259 @@
+# Rules for ASL data that are not defined in tables.
+---
+
+# 157
+ASLLabelingDurationNiftiLength:
+    code: LABELING_DURATION_LENGTH_NOT_MATCHING_NIFTI
+    description: |
+        The number of values for 'LabelingDuration' for this file does not match the 4th dimension of the NIfTI header.
+        'LabelingDuration' is the total duration of the labeling pulse train, in seconds,
+        corresponding to the temporal width of the labeling bolus for `(P)CASL`.
+        In case all control-label volumes (or deltam or CBF) have the same `LabelingDuration`, a scalar must be
+        specified.
+        In case the control-label volumes (or deltam or cbf) have a different `LabelingDuration`,
+        an array of numbers must be specified, for which any `m0scan` in the timeseries has a `LabelingDuration` of
+        zero.
+        In case an array of numbers is provided, its length should be equal to the number of volumes specified in
+        `*_aslcontext.tsv`. Corresponds to DICOM Tag 0018,9258 `ASL Pulse Train Duration`.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - sidecar contains "LabelingDuration"
+    - type(sidecar.LabelingDuration) == "array"
+    checks:
+    - data.shape[3] == sidecar.LabelingDuration.size
+
+# 165
+ASLContextConsistent:
+    code: ASLCONTEXT_TSV_NOT_CONSISTENT
+    description: |
+        The number of volumes in the '*_aslcontext.tsv' for this file does not match the number of
+        values in the NIfTI header.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    checks:
+    - data.shape[3] == associated["aslcontext"].shape[0]
+
+# 168
+ASLFlipAngleNiftiLength:
+    code: FLIP_ANGLE_NOT_MATCHING_NIFTI
+    description: |
+        The number of values for 'FlipAngle' for this file does not match the 4th dimension of the NIfTI header.
+        'FlipAngle' is the flip angle (FA) for the acquisition, specified in degrees.
+        Corresponds to: DICOM Tag 0018, 1314 `Flip Angle`.
+        The data type number may apply to files from any MRI modality concerned with a single value for this field,
+        or to the files in a file collection where the value of this field is iterated using the flip entity.
+        The data type array provides a value for each volume in a 4D dataset and should only be used when the
+        volume timing is critical for interpretation of the data, such as in ASL or variable flip angle fMRI sequences.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - sidecar contains "FlipAngle"
+    - type(sidecar.FlipAngle) == "array"
+    checks:
+    - data.shape[3] == sidecar.FlipAngle.size
+
+# 172
+ASLFlipAngleASLContextLength:
+    code: FLIP_ANGLE_NOT_MATCHING_ASLCONTEXT_TSV
+    description: |
+       The number of values for 'FlipAngle' for this file does not match the number of volumes in the
+       'sub-<label>[_ses-<label>][_acq-<label>][_rec-<label>][_run-<index>]_aslcontext.tsv'.
+       'FlipAngle' is the flip angle (FA) for the acquisition, specified in degrees.
+       Corresponds to: DICOM Tag 0018, 1314 `Flip Angle`.
+       The data type number may apply to files from any MRI modality concerned with a single value for this field,
+       or to the files in a file collection where the value of this field is iterated using the flip entity.
+       The data type array provides a value for each volume in a 4D dataset and should only be used when the volume
+       timing is critical for interpretation of the data, such as in ASL or variable flip angle fMRI sequences.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - sidecar contains "FlipAngle"
+    - type(sidecar.FlipAngle) == "array"
+    checks:
+    - associated["aslcontext"].shape[0] == sidecar.FlipAngle.size
+
+# 173
+ASLPostLabelingDelayNiftiLength:
+    code: POST_LABELING_DELAY_NOT_MATCHING_NIFTI
+    description: |
+        The number of values for 'PostLabelingDelay' for this file does not match the 4th dimension of the NIfTI
+        header.
+        'PostLabelingDelay' is the time, in seconds, after the end of the labeling (for (P)CASL) or middle of the
+        labeling pulse (for PASL) until the middle of the excitation pulse applied to the imaging slab
+        (for 3D acquisition) or first slice (for 2D acquisition).
+        Can be a number (for a single-PLD time series) or an array of numbers (for multi-PLD and Look-Locker).
+        In the latter case, the array of numbers contains the PLD of each volume (i.e. each 'control' and 'label')
+        in the acquisition order. Any image within the time-series without a PLD (e.g. an 'm0scan') is indicated by a
+        zero.
+        Based on DICOM Tags 0018,9079 Inversion Times and 0018,0082 InversionTime.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - sidecar contains "PostLabelingDelay"
+    - type(sidecar.PostLabelingDelay) == "array"
+    checks:
+    - data.shape[3] == sidecar.PostLabelingDelay.size
+
+# 174
+ASLPostLabelingDelayASLContextLength:
+    code: POST_LABELING_DELAY_NOT_MATCHING_ASLCONTEXT_TSV
+    description: |
+        The number of values for 'PostLabelingDelay' for this file does not match the number of volumes
+        in the 'sub-<label>[_ses-<label>][_acq-<label>][_rec-<label>][_run-<index>]_aslcontext.tsv'.
+        'PostLabelingDelay' is the time, in seconds, after the end of the labeling (for (P)CASL) or
+        middle of the labeling pulse (for PASL) until the middle of the excitation pulse applied to
+        the imaging slab (for 3D acquisition) or first slice (for 2D acquisition).
+        Can be a number (for a single-PLD time series) or an array of numbers (for multi-PLD and Look-Locker).
+        In the latter case, the array of numbers contains the PLD of each volume (i.e. each 'control' and 'label')
+        in the acquisition order.
+        Any image within the time-series without a PLD (e.g. an 'm0scan') is indicated by a zero.
+        Based on DICOM Tags 0018,9079 Inversion Times and 0018,0082 InversionTime.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - sidecar contains "PostLabelingDelay"
+    - type(sidecar.PostLabelingDelay) == "array"
+    checks:
+    - associated["aslcontext"].shape[0] == sidecar.PostLabelingDelay.size
+
+# 175
+ASLLabelingDurationASLContextLength:
+    code: LABELLING_DURATION_NOT_MATCHING_ASLCONTEXT_TSV
+    description: |
+        The number of values for 'LabelingDuration' for this file does not match the number of volumes
+        in the 'sub-<label>[_ses-<label>][_acq-<label>][_rec-<label>][_run-<index>]_aslcontext.tsv'.
+        'LabelingDuration' is the total duration of the labeling pulse train, in seconds,
+        corresponding to the temporal width of the labeling bolus for `(P)CASL`.
+        In case all control-label volumes (or deltam or CBF) have the same `LabelingDuration`,
+        a scalar must be specified.
+        In case the control-label volumes (or deltam or cbf) have a different `LabelingDuration`,
+        an array of numbers must be specified, for which any `m0scan` in the timeseries has a
+        `LabelingDuration` of zero.
+        In case an array of numbers is provided, its length should be equal to the number of volumes
+        specified in `*_aslcontext.tsv`.
+        Corresponds to DICOM Tag 0018,9258 `ASL Pulse Train Duration`.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - sidecar contains "LabelingDuration"
+    - type(sidecar.LabelingDuration) == "array"
+    checks:
+    - associated["aslcontext"].shape[0] == sidecar.LabelingDuration.size
+
+# 177
+ASLRepetitionTimePreparationASLContextLength:
+    code: REPETITIONTIMEPREPARATION_NOT_MATCHING_ASLCONTEXT_TSV
+    description: |
+        The number of values of 'RepetitionTimePreparation' for this file does not match the number of
+        volumes in the 'sub-<label>[_ses-<label>][_acq-<label>][_rec-<label>][_run-<index>]_aslcontext.tsv'.
+        'RepetitionTimePreparation' is the interval, in seconds, that it takes a preparation pulse block to
+        re-appear at the beginning of the succeeding (essentially identical) pulse sequence block.
+        The data type number may apply to files from any MRI modality concerned with a single value for this field.
+        The data type array provides a value for each volume in a 4D dataset and should only be used when the
+        volume timing is critical for interpretation of the data, such as in ASL.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - sidecar contains "RepetitionTimePreparation"
+    - type(sidecar.RepetitionTimePreparation) == "array"
+    checks:
+    - associated["aslcontext"].shape[0] == sidecar.RepetitionTimePreparation.size
+
+# 180
+ASLBackgroundSuppressionNumberPulses:
+    code: BACKGROUND_SUPPRESSION_PULSE_NUMBER_NOT_CONSISTENT
+    description: |
+        The 'BackgroundSuppressionNumberPulses' field is not consistent with the length of
+        'BackgroundSuppressionPulseTime'.
+        'BackgroundSuppressionNumberPulses' is the number of background suppression pulses used.
+        Note that this excludes any effect of background suppression pulses applied before the labeling.
+    level: warning
+    selectors:
+    - suffix == "asl"
+    - sidecar contains "BackgroundSuppressionNumberPulses"
+    - sidecar contains "BackgroundSuppressionPulseTime"
+    - type(sidecar.BackgroundSuppressionPulseTime) == "array"
+    checks:
+    - sidecar.BackgroundSuppressionPulseTime.size == sidecar.BackgroundSuppressionNumberPulses
+
+# 181
+ASLTotalAcquiredVolumesASLContextLength:
+    code: TOTAL_ACQUIRED_VOLUMES_NOT_CONSISTENT
+    description: |
+        The number of values for 'TotalAcquiredVolumes' for this file does not match number of
+        volumes in the 'sub-<label>[_ses-<label>][_acq-<label>][_rec-<label>][_run-<index>]_aslcontext.tsv'.
+        'TotalAcquiredVolumes' is the original number of 3D volumes acquired for each volume defined in the
+        'sub-<label>[_ses-<label>][_acq-<label>][_rec-<label>][_run-<index>]_aslcontext.tsv'.
+    level: warning
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - sidecar contains "TotalAcquiredVolumes"
+    checks:
+    - associated["aslcontext"].shape[0] == sidecar.TotalAcquiredVolumes
+
+# 196
+ASLEchoTimeASLContextLength:
+    code: ECHO_TIME_NOT_CONSISTENT
+    description: |
+        The number of values for 'EchoTime' for this file does not match number of volumes in the
+        'sub-<label>[_ses-<label>][_acq-<label>][_rec-<label>][_run-<index>]_aslcontext.tsv'.
+        'EchoTime' is the echo time (TE) for the acquisition, specified in seconds.
+    level: warning
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - sidecar contains "EchoTime"
+    - type(sidecar.EchoTime) == "array"
+    checks:
+    - associated["aslcontext"].shape[0] == sidecar.EchoTime.size
+
+# 198
+ASLM0TypeAbsentScan:
+    code: M0Type_SET_INCORRECTLY_TO_ABSENT
+    description: |
+        You defined M0Type as 'absent' while including a separate '*_m0scan.nii[.gz]' and
+        '*_m0scan.json', or defining the 'M0Estimate' field.
+        This is not allowed, please check that this field are filled correctly.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - associated contains "m0scan"
+    checks:
+    - sidecar.M0Type != "absent"
+
+# 199
+ASLM0TypeAbsentASLContext:
+    code: M0Type_SET_INCORRECTLY_TO_ABSENT_IN_ASLCONTEXT
+    description: |
+        You defined M0Type as 'absent' while including an m0scan volume within the '*_aslcontext.tsv'.
+        This is not allowed, please check that this field are filled correctly.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - associated["aslcontext"]["volume_type"] contains "m0scan"
+    checks:
+    - sidecar.M0Type != "absent"
+
+# 202
+ASLM0TypeIncorrect:
+    code: M0Type_SET_INCORRECTLY
+    description: |
+        M0Type was not defined correctly.
+        If 'M0Type' is equal to 'separate', the dataset should include a *_m0scan.nii[.gz] and *_m0scan.json file.
+    level: error
+    selectors:
+    - suffix == "asl"
+    - associated contains "aslcontext"
+    - sidecar.M0Type == "separate"
+    checks:
+    - associated contains "m0scan"

src/schema/rules/sidecars/dwi_validation.yaml

@@ -0,0 +1,39 @@
+# Rules for DWI data that are not defined in tables.
+---
+
+# 29
+DWIVolumeCount:
+    code: VOLUME_COUNT_MISMATCH
+    description: |
+        The number of volumes in this scan does not match the number of volumes in the
+        corresponding .bvec and .bval files.
+    level: error
+    selectors:
+    - suffix == "dwi"
+    - associated contains "bval"
+    - associated contains "bvec"
+    checks:
+    - associated["bval"].shape[0] == data.shape[3]
+    - associated["bvec"].shape[0] == data.shape[3]
+
+# 32
+DWIMissingBvec:
+    code: DWI_MISSING_BVEC
+    description: |
+        DWI scans must have a corresponding .bvec file.
+    level: error
+    selectors:
+    - suffix == "dwi"
+    checks:
+    - associated contains "bvec"
+
+# 33
+DWIMissingBval:
+    code: DWI_MISSING_BVAL
+    description: |
+        DWI scans must have a corresponding .bval file.
+    level: error
+    selectors:
+    - suffix == "dwi"
+    checks:
+    - associated contains "bval"

src/schema/rules/sidecars/events_validation.yaml

@@ -0,0 +1,16 @@
+# Rules for events data that are not defined in tables.
+---
+
+# 25
+EventsMissing:
+    code: EVENTS_TSV_MISSING
+    description: |
+        Task scans should have a corresponding events.tsv file.
+        If this is a resting state scan you can ignore this warning or rename the task to include the word "rest".
+    level: warning  # could be an error with the proper selectors, I think
+    selectors:
+    - entities contains "task"
+    - entities.task != "rest"
+    - entities.task not contains "rest"  # Alternative for including the word "rest"
+    checks:
+    - associated contains "events"