def group_options(options, timepoint):
options = copy.deepcopy(options)
if options.mbm.lsq6.target_type == TargetType.pride_of_models:
options = copy.deepcopy(options)
targets = get_closest_model_from_pride_of_models(pride_of_models_dict=get_pride_of_models_mapping(
pride_csv=options.mbm.lsq6.target_file,
output_dir=options.application.output_directory,
pipeline_name=options.application.pipeline_name),
time_point=timepoint)
options.mbm.lsq6 = options.mbm.lsq6.replace(target_type=TargetType.initial_model,
target_file=targets.registration_standard.path)
# resolution = (options.registration.resolution
# or get_resolution_from_file(targets.registration_standard.path))
# options.registration = options.registration.replace(resolution=resolution)
# FIXME use of registration_standard here is quite wrong ...
# part of the trouble is that mbm calls registration_targets itself,
# so we can't send this RegistrationTargets to `mbm` directly ...
# one option: add yet another optional arg to `mbm` ...
else:
targets = s.defer(registration_targets(lsq6_conf=options.mbm.lsq6,
app_conf=options.application, reg_conf=options.registration,
first_input_file=imgs.filename.iloc[0]))
resolution = (options.registration.resolution or
get_resolution_from_file(targets.registration_standard.path))
# This must happen after calling registration_targets otherwise it will resample to options.registration.resolution
options.registration = options.registration.replace(resolution=resolution)
return options
def group_options(options, timepoint):
options = copy.deepcopy(options)
if options.mbm.lsq6.target_type == TargetType.pride_of_models:
options = copy.deepcopy(options)
targets = get_closest_model_from_pride_of_models(pride_of_models_dict=get_pride_of_models_mapping(
pride_csv=options.mbm.lsq6.target_file,
output_dir=options.application.output_directory,
pipeline_name=options.application.pipeline_name),
time_point=timepoint)
options.mbm.lsq6 = options.mbm.lsq6.replace(target_type=TargetType.initial_model,
target_file=targets.registration_standard.path)
# resolution = (options.registration.resolution
# or get_resolution_from_file(targets.registration_standard.path))
# options.registration = options.registration.replace(resolution=resolution)
# FIXME use of registration_standard here is quite wrong ...
# part of the trouble is that mbm calls registration_targets itself,
# so we can't send this RegistrationTargets to `mbm` directly ...
# one option: add yet another optional arg to `mbm` ...
else:
targets = s.defer(registration_targets(lsq6_conf=options.mbm.lsq6,
app_conf=options.application, reg_conf=options.registration,
first_input_file=imgs.filename.iloc[0]))
resolution = (options.registration.resolution or
get_resolution_from_file(targets.registration_standard.path))
# This must happen after calling registration_targets otherwise it will resample to options.registration.resolution
options.registration = options.registration.replace(resolution=resolution)
return options
def two_level(grouped_files_df, options: TwoLevelConf):
"""
grouped_files_df - must contain 'group':<any comparable, sortable type> and 'file':MincAtom columns
""" # TODO weird naming since the grouped_files_df isn't a GroupBy object? just files_df?
s = Stages()
if grouped_files_df.isnull().values.any():
raise ValueError("NaN values in input dataframe; can't go")
if options.mbm.lsq6.target_type == TargetType.bootstrap:
# won't work since the second level part tries to get the resolution of *its* "first input file", which
# hasn't been created. We could instead pass in a resolution to the `mbm` function,
# but instead disable for now:
raise ValueError(
"Bootstrap model building currently doesn't work with this pipeline; "
"just specify an initial target instead")
elif options.mbm.lsq6.target_type == TargetType.pride_of_models:
pride_of_models_mapping = get_pride_of_models_mapping(
pride_csv=options.mbm.lsq6.target_file,
output_dir=options.application.output_directory,
pipeline_name=options.application.pipeline_name)
# FIXME this is the same as in the 'tamarack' except for names of arguments/enclosing variables
def group_options(options, group):
options = copy.deepcopy(options)
if options.mbm.lsq6.target_type == TargetType.pride_of_models:
targets = get_closest_model_from_pride_of_models(
pride_of_models_dict=pride_of_models_mapping, time_point=group)
options.mbm.lsq6 = options.mbm.lsq6.replace(
target_type=TargetType.initial_model,
target_file=targets.registration_standard.path)
else:
# this will ensure that all groups have the same resolution -- is it necessary?
targets = s.defer(
registration_targets(
lsq6_conf=options.mbm.lsq6,
app_conf=options.application,
reg_conf=options.registration,
first_input_file=grouped_files_df.file.iloc[0]))
resolution = (options.registration.resolution
or get_resolution_from_file(
targets.registration_standard.path))
# This must happen after calling registration_targets otherwise it will resample to options.registration.resolution
options.registration = options.registration.replace(
resolution=resolution)
# no need to check common space settings here since they're turned off at the parser level
# (a bit strange)
return options
first_level_results = (
grouped_files_df.groupby(
'group', as_index=False
) # the usual annoying pattern to do a aggregate with access
.aggregate({'file': lambda files: list(files)
}) # to the groupby object's keys ... TODO: fix
.rename(columns={
'file': "files"
}).assign(build_model=lambda df: df.apply(
axis=1,
func=lambda row: s.defer(
mbm(imgs=row.files,
options=group_options(options, row.group),
prefix="%s" % row.group,
output_dir=os.path.join(
options.application.output_directory, options.
application.pipeline_name + "_first_level",
"%s_processed" % row.group))))))
# TODO replace .assign(...apply(...)...) with just an apply, producing a series right away?
# FIXME right now the same options set is being used for both levels -- use options.first/second_level
second_level_options = copy.deepcopy(options)
second_level_options.mbm.lsq6 = second_level_options.mbm.lsq6.replace(
run_lsq6=False)
second_level_options.mbm.segmentation.run_maget = False
second_level_options.mbm.maget.maget.mask_only = False
second_level_options.mbm.maget.maget.mask = False
# FIXME this is probably a hack -- instead add a --second-level-init-model option to specify which timepoint should be used
# as the initial model in the second level ??? (at this point it doesn't matter due to lack of lsq6 ...)
if second_level_options.mbm.lsq6.target_type == TargetType.pride_of_models:
second_level_options.mbm.lsq6 = second_level_options.mbm.lsq6.replace(
target_type=TargetType.
target, # target doesn't really matter as no lsq6 here, just used for resolution...
target_file=list(pride_of_models_mapping.values())
[0].registration_standard.path)
# NOTE: running lsq6_nuc_inorm here doesn't work in general (but possibly with rotational minctracc)
# since the native-space initial model is used, but our images are
# already in standard space (as we resampled there after the 1st-level lsq6).
# On the other hand, we might want to run it here (although of course NOT nuc/inorm!) in the future,
# for instance given a 'pride' of models (one for each group).
second_level_results = s.defer(
mbm(imgs=first_level_results.build_model.map(lambda m: m.avg_img),
options=second_level_options,
prefix=os.path.join(
options.application.output_directory,
options.application.pipeline_name + "_second_level")))
# FIXME sadly, `mbm` doesn't return a pd.Series of xfms, so we don't have convenient indexing ...
overall_xfms = [
s.defer(concat_xfmhandlers([xfm_1, xfm_2])) for xfms_1, xfm_2 in
zip([r.xfms.lsq12_nlin_xfm for r in first_level_results.build_model],
second_level_results.xfms.overall_xfm) for xfm_1 in xfms_1
]
resample = np.vectorize(mincresample_new, excluded={"extra_flags"})
defer = np.vectorize(s.defer)
# TODO using the avg_img here is a bit clunky -- maybe better to propagate group indices ...
# only necessary since `mbm` doesn't return DataFrames but namespaces ...
first_level_determinants = pd.concat(list(
first_level_results.build_model.apply(
lambda x: x.determinants.assign(first_level_avg=x.avg_img))),
ignore_index=True)
# first_level_xfms is only necessary because you otherwise have no access to the input file which is necessary
# for merging with the input csv. lsq12_nlin_xfm can be used to merge, and rigid_xfm contains the input file.
# If for some reason we want to output xfms in the future, just don't drop everything.
first_level_xfms = pd.concat(
list(
first_level_results.build_model.apply(
lambda x: x.xfms.assign(first_level_avg=x.avg_img))),
ignore_index=True)[["lsq12_nlin_xfm", "rigid_xfm"]]
if options.mbm.segmentation.run_maget:
maget_df = pd.DataFrame([
{
"label_file": x.labels.path,
"native_file": x.orig_path
} #, "_merge" : basename(x.orig_path)}
for x in pd.concat([
namespace.maget_result
for namespace in first_level_results.build_model
])
])
first_level_xfms = pd.merge(
left=first_level_xfms.assign(native_file=lambda df: df.rigid_xfm.
apply(lambda x: x.source.path)),
right=maget_df,
on="native_file")
first_level_determinants = (pd.merge(left=first_level_determinants,
right=first_level_xfms,
left_on="inv_xfm",
right_on="lsq12_nlin_xfm").drop(
["rigid_xfm", "lsq12_nlin_xfm"],
axis=1))
resampled_determinants = (pd.merge(
left=first_level_determinants,
right=pd.DataFrame({
'group_xfm': second_level_results.xfms.overall_xfm
}).assign(source=lambda df: df.group_xfm.apply(lambda r: r.source)),
left_on="first_level_avg",
right_on="source").assign(
resampled_log_full_det=lambda df: defer(
resample(img=df.log_full_det,
xfm=df.group_xfm.apply(lambda x: x.xfm),
like=second_level_results.avg_img)),
resampled_log_nlin_det=lambda df: defer(
resample(img=df.log_nlin_det,
xfm=df.group_xfm.apply(lambda x: x.xfm),
like=second_level_results.avg_img))))
# TODO only resamples the log determinants, but still a bit ugly ... abstract somehow?
# TODO shouldn't be called resampled_determinants since this is basically the whole (first_level) thing ...
inverted_overall_xfms = [
s.defer(invert_xfmhandler(xfm)) for xfm in overall_xfms
]
overall_determinants = (s.defer(
determinants_at_fwhms(
xfms=inverted_overall_xfms,
inv_xfms=overall_xfms,
blur_fwhms=options.mbm.stats.stats_kernels)).assign(
overall_log_full_det=lambda df: df.log_full_det,
overall_log_nlin_det=lambda df: df.log_nlin_det).drop(
['log_full_det', 'log_nlin_det'], axis=1))
# TODO return some MAGeT stuff from two_level function ??
# FIXME running MAGeT from within the `two_level` function has the same problem as running it from within `mbm`:
# it will now run when this pipeline is called from within another one (e.g., n-level), which will be
# redundant, create filename clashes, etc. -- this should be moved to `two_level_pipeline`.
# TODO do we need a `pride of atlases` for MAGeT in this pipeline ??
# TODO at the moment MAGeT is run within the MBM code, but it could be disabled there and run here
#if options.mbm.segmentation.run_maget:
# maget_options = copy.deepcopy(options)
# maget_options.maget = options.mbm.maget
# fixup_maget_options(maget_options=maget_options.maget,
# lsq12_options=maget_options.mbm.lsq12,
# nlin_options=maget_options.mbm.nlin)
# maget_options.maget.maget.mask = maget_options.maget.maget.mask_only = False # already done above
# del maget_options.mbm
# again using a weird combination of vectorized and loop constructs ...
# s.defer(maget([xfm.resampled for _ix, m in first_level_results.iterrows()
# for xfm in m.build_model.xfms.rigid_xfm],
# options=maget_options,
# prefix="%s_MAGeT" % options.application.pipeline_name,
# output_dir=os.path.join(options.application.output_directory,
# options.application.pipeline_name + "_processed")))
# TODO resampling to database model ...
# TODO there should be one table containing all determinants (first level, overall, resampled first level) for each file
# and another containing some groupwise information (averages and transforms to the common average)
return Result(stages=s,
output=Namespace(
first_level_results=first_level_results,
resampled_determinants=resampled_determinants,
overall_determinants=overall_determinants))
def two_level(grouped_files_df, options : TwoLevelConf):
"""
grouped_files_df - must contain 'group':<any comparable, sortable type> and 'file':MincAtom columns
""" # TODO weird naming since the grouped_files_df isn't a GroupBy object? just files_df?
s = Stages()
if grouped_files_df.isnull().values.any():
raise ValueError("NaN values in input dataframe; can't go")
if options.mbm.lsq6.target_type == TargetType.bootstrap:
# won't work since the second level part tries to get the resolution of *its* "first input file", which
# hasn't been created. We could instead pass in a resolution to the `mbm` function,
# but instead disable for now:
raise ValueError("Bootstrap model building currently doesn't work with this pipeline; "
"just specify an initial target instead")
elif options.mbm.lsq6.target_type == TargetType.pride_of_models:
pride_of_models_mapping = get_pride_of_models_mapping(pride_csv=options.mbm.lsq6.target_file,
output_dir=options.application.output_directory,
pipeline_name=options.application.pipeline_name)
# FIXME this is the same as in the 'tamarack' except for names of arguments/enclosing variables
def group_options(options, group):
options = copy.deepcopy(options)
if options.mbm.lsq6.target_type == TargetType.pride_of_models:
targets = get_closest_model_from_pride_of_models(pride_of_models_dict=pride_of_models_mapping,
time_point=group)
options.mbm.lsq6 = options.mbm.lsq6.replace(target_type=TargetType.initial_model,
target_file=targets.registration_standard.path)
else:
# this will ensure that all groups have the same resolution -- is it necessary?
targets = registration_targets(lsq6_conf=options.mbm.lsq6,
app_conf=options.application,
first_input_file=grouped_files_df.file.iloc[0])
resolution = (options.registration.resolution
or get_resolution_from_file(targets.registration_standard.path))
options.registration = options.registration.replace(resolution=resolution)
# no need to check common space settings here since they're turned off at the parser level
# (a bit strange)
return options
first_level_results = (
grouped_files_df
.groupby('group', as_index=False, sort=False) # the usual annoying pattern to do a aggregate with access
.aggregate({ 'file' : lambda files: list(files) }) # to the groupby object's keys ... TODO: fix
.rename(columns={ 'file' : "files" })
.assign(build_model=lambda df:
df.apply(axis=1,
func=lambda row:
s.defer(mbm(imgs=row.files,
options=group_options(options, row.group),
prefix="%s" % row.group,
output_dir=os.path.join(
options.application.output_directory,
options.application.pipeline_name + "_first_level",
"%s_processed" % row.group)))))
)
# TODO replace .assign(...apply(...)...) with just an apply, producing a series right away?
# FIXME right now the same options set is being used for both levels -- use options.first/second_level
second_level_options = copy.deepcopy(options)
second_level_options.mbm.lsq6 = second_level_options.mbm.lsq6.replace(run_lsq6=False)
second_level_options.mbm.segmentation.run_maget = False
second_level_options.mbm.maget.maget.mask_only = False
second_level_options.mbm.maget.maget.mask = False
# FIXME this is probably a hack -- instead add a --second-level-init-model option to specify which timepoint should be used
# as the initial model in the second level ??? (at this point it doesn't matter due to lack of lsq6 ...)
if second_level_options.mbm.lsq6.target_type == TargetType.pride_of_models:
second_level_options.mbm.lsq6 = second_level_options.mbm.lsq6.replace(
target_type=TargetType.target, # target doesn't really matter as no lsq6 here, just used for resolution...
target_file=list(pride_of_models_mapping.values())[0].registration_standard.path)
# NOTE: running lsq6_nuc_inorm here doesn't work in general (but possibly with rotational minctracc)
# since the native-space initial model is used, but our images are
# already in standard space (as we resampled there after the 1st-level lsq6).
# On the other hand, we might want to run it here (although of course NOT nuc/inorm!) in the future,
# for instance given a 'pride' of models (one for each group).
second_level_results = s.defer(mbm(imgs=first_level_results.build_model.map(lambda m: m.avg_img),
options=second_level_options,
prefix=os.path.join(options.application.output_directory,
options.application.pipeline_name + "_second_level")))
# FIXME sadly, `mbm` doesn't return a pd.Series of xfms, so we don't have convenient indexing ...
overall_xfms = [s.defer(concat_xfmhandlers([xfm_1, xfm_2]))
for xfms_1, xfm_2 in zip([r.xfms.lsq12_nlin_xfm for r in first_level_results.build_model],
second_level_results.xfms.overall_xfm)
for xfm_1 in xfms_1]
resample = np.vectorize(mincresample_new, excluded={"extra_flags"})
defer = np.vectorize(s.defer)
# TODO using the avg_img here is a bit clunky -- maybe better to propagate group indices ...
# only necessary since `mbm` doesn't return DataFrames but namespaces ...
first_level_determinants = pd.concat(list(first_level_results.build_model.apply(
lambda x: x.determinants.assign(first_level_avg=x.avg_img))),
ignore_index=True)
resampled_determinants = (pd.merge(
left=first_level_determinants,
right=pd.DataFrame({'group_xfm' : second_level_results.xfms.overall_xfm})
.assign(source=lambda df: df.group_xfm.apply(lambda r: r.source)),
left_on="first_level_avg",
right_on="source")
.assign(resampled_log_full_det=lambda df: defer(resample(img=df.log_full_det,
xfm=df.group_xfm.apply(lambda x: x.xfm),
like=second_level_results.avg_img)),
resampled_log_nlin_det=lambda df: defer(resample(img=df.log_nlin_det,
xfm=df.group_xfm.apply(lambda x: x.xfm),
like=second_level_results.avg_img))))
# TODO only resamples the log determinants, but still a bit ugly ... abstract somehow?
# TODO shouldn't be called resampled_determinants since this is basically the whole (first_level) thing ...
inverted_overall_xfms = [s.defer(invert_xfmhandler(xfm)) for xfm in overall_xfms]
overall_determinants = (s.defer(determinants_at_fwhms(
xfms=inverted_overall_xfms,
inv_xfms=overall_xfms,
blur_fwhms=options.mbm.stats.stats_kernels))
.assign(overall_log_full_det=lambda df: df.log_full_det,
overall_log_nlin_det=lambda df: df.log_nlin_det)
.drop(['log_full_det', 'log_nlin_det'], axis=1))
# TODO return some MAGeT stuff from two_level function ??
# FIXME running MAGeT from within the `two_level` function has the same problem as running it from within `mbm`:
# it will now run when this pipeline is called from within another one (e.g., n-level), which will be
# redundant, create filename clashes, etc. -- this should be moved to `two_level_pipeline`.
# TODO do we need a `pride of atlases` for MAGeT in this pipeline ??
# TODO at the moment MAGeT is run within the MBM code, but it could be disabled there and run here
#if options.mbm.segmentation.run_maget:
# maget_options = copy.deepcopy(options)
# maget_options.maget = options.mbm.maget
# fixup_maget_options(maget_options=maget_options.maget,
# lsq12_options=maget_options.mbm.lsq12,
# nlin_options=maget_options.mbm.nlin)
# maget_options.maget.maget.mask = maget_options.maget.maget.mask_only = False # already done above
# del maget_options.mbm
# again using a weird combination of vectorized and loop constructs ...
# s.defer(maget([xfm.resampled for _ix, m in first_level_results.iterrows()
# for xfm in m.build_model.xfms.rigid_xfm],
# options=maget_options,
# prefix="%s_MAGeT" % options.application.pipeline_name,
# output_dir=os.path.join(options.application.output_directory,
# options.application.pipeline_name + "_processed")))
# TODO resampling to database model ...
# TODO there should be one table containing all determinants (first level, overall, resampled first level) for each file
# and another containing some groupwise information (averages and transforms to the common average)
return Result(stages=s, output=Namespace(first_level_results=first_level_results,
resampled_determinants=resampled_determinants,
overall_determinants=overall_determinants))
def chain(options):
"""Create a registration chain pipeline from the given options."""
# TODO:
# one overall question for this entire piece of code is how
# we are going to make sure that we can concatenate/add all
# the transformations together. Many of the sub-registrations
# that are performed (inter-subject registration, lsq6 using
# multiple initial models) are applied to subsets of the entire
# data, making it harder to keep the mapping simple/straightforward
chain_opts = options.chain # type : ChainConf
s = Stages()
with open(options.chain.csv_file, 'r') as f:
subject_info = parse_csv(rows=f, common_time_pt=options.chain.common_time_point)
output_dir = options.application.output_directory
pipeline_name = options.application.pipeline_name
pipeline_processed_dir = os.path.join(output_dir, pipeline_name + "_processed")
pipeline_lsq12_common_dir = os.path.join(output_dir, pipeline_name + "_lsq12_" + options.chain.common_time_point_name)
pipeline_nlin_common_dir = os.path.join(output_dir, pipeline_name + "_nlin_" + options.chain.common_time_point_name)
pipeline_montage_dir = os.path.join(output_dir, pipeline_name + "_montage")
pipeline_subject_info = map_over_time_pt_dict_in_Subject(
lambda subj_str: MincAtom(name=subj_str, pipeline_sub_dir=pipeline_processed_dir),
subject_info) # type: Dict[str, Subject[MincAtom]]
# verify that in input files are proper MINC files, and that there
# are no duplicates in the filenames
all_Minc_atoms = [] # type: List[MincAtom]
for s_id, subj in pipeline_subject_info.items():
for subj_time_pt, subj_filename in subj.time_pt_dict.items():
all_Minc_atoms.append(subj_filename)
# check_MINC_input_files takes strings, so pass along those instead of the actual MincAtoms
check_MINC_input_files([minc_atom.path for minc_atom in all_Minc_atoms])
if options.registration.input_space == InputSpace.lsq6 or \
options.registration.input_space == InputSpace.lsq12:
# the input files are not going through the lsq6 alignment. This is the place
# where they will all be resampled using a single like file, and get the same
# image dimensions/lengths/resolution. So in order for the subsequent stages to
# finish (mincaverage stages for instance), all files need to have the same
# image parameters:
check_MINC_files_have_equal_dimensions_and_resolution([minc_atom.path for minc_atom in all_Minc_atoms],
additional_msg="Given that the input images are "
"already in " + str(options.registration.input_space) +
" space, all input files need to have "
"the same dimensions/starts/step sizes.")
if options.registration.input_space not in InputSpace.__members__.values():
raise ValueError('unrecognized input space: %s; choices: %s' %
(options.registration.input_space, ','.join(InputSpace.__members__)))
if options.registration.input_space == InputSpace.native:
if options.lsq6.target_type == TargetType.bootstrap:
raise ValueError("\nA bootstrap model is ill-defined for the registration chain. "
"(Which file is the 'first' input file?). Please use the --lsq6-target "
"flag to specify a target for the lsq6 stage, or use an initial model.")
if options.lsq6.target_type == TargetType.pride_of_models:
pride_of_models_dict = get_pride_of_models_mapping(pride_csv=options.lsq6.target_file,
output_dir=options.application.output_directory,
pipeline_name=options.application.pipeline_name)
subj_id_to_subj_with_lsq6_xfm_dict = map_with_index_over_time_pt_dict_in_Subject(
lambda subj_atom, time_point:
s.defer(lsq6_nuc_inorm([subj_atom],
registration_targets=get_closest_model_from_pride_of_models(
pride_of_models_dict, time_point),
resolution=options.registration.resolution,
lsq6_options=options.lsq6,
lsq6_dir=None, # never used since no average
# (could call this "average_dir" with None -> no avg ?)
subject_matter=options.registration.subject_matter,
create_qc_images=False,
create_average=False))[0],
pipeline_subject_info) # type: Dict[str, Subject[XfmHandler]]
else:
# if we are not dealing with a pride of models, we can retrieve a fixed
# registration target for all input files:
targets = registration_targets(lsq6_conf=options.lsq6,
app_conf=options.application)
# we want to store the xfm handlers in the same shape as pipeline_subject_info,
# as such we will call lsq6_nuc_inorm for each file individually and simply extract
# the first (and only) element from the resulting list via s.defer(...)[0].
subj_id_to_subj_with_lsq6_xfm_dict = map_over_time_pt_dict_in_Subject(
lambda subj_atom:
s.defer(lsq6_nuc_inorm([subj_atom],
registration_targets=targets,
resolution=options.registration.resolution,
lsq6_options=options.lsq6,
lsq6_dir=None, # no average will be create, is just one file...
create_qc_images=False,
create_average=False,
subject_matter=options.registration.subject_matter)
)[0],
pipeline_subject_info) # type: Dict[str, Subject[XfmHandler]]
# create verification images to show the 6 parameter alignment
montageLSQ6 = pipeline_montage_dir + "/quality_control_montage_lsq6.png"
# TODO, base scaling factor on resolution of initial model or target
filesToCreateImagesFrom = []
for subj_id, subj in subj_id_to_subj_with_lsq6_xfm_dict.items():
for time_pt, subj_time_pt_xfm in subj.time_pt_dict.items():
filesToCreateImagesFrom.append(subj_time_pt_xfm.resampled)
# TODO it's strange that create_quality_control_images gets the montage directory twice
# TODO (in montages=output=montageLSQ6 and in montage_dir), suggesting a weirdness in create_q_c_images
lsq6VerificationImages = s.defer(create_quality_control_images(filesToCreateImagesFrom,
montage_output=montageLSQ6,
montage_dir=pipeline_montage_dir,
message=" the input images after the lsq6 alignment"))
# NB currently LSQ6 expects an array of files, but we have a map.
# possibilities:
# - note that pairwise is enough (except for efficiency -- redundant blurring, etc.)
# and just use the map fn above with an LSQ6 fn taking only a single source
# - rewrite LSQ6 to use such a (nested) map
# - write conversion which creates a tagged array from the map, performs LSQ6,
# and converts back
# - write 'over' which takes a registration, a data structure, and 'get/set' fns ...?
# Intersubject registration: LSQ12/NLIN registration of common-timepoint images
# The assumption here is that all these files are roughly aligned. Here is a toy
# schematic of what happens. In this example, the common timepoint is set timepoint 2:
#
# ------------
# subject A A_time_1 -> | A_time_2 | -> A_time_3
# subject B B_time_1 -> | B_time_2 | -> B_time_3
# subject C C_time_1 -> | C_time_2 | -> C_time_3
# ------------
# |
# group_wise registration on time point 2
#
# dictionary that holds the transformations from the intersubject images
# to the final common space average
intersubj_img_to_xfm_to_common_avg_dict = {} # type: Dict[MincAtom, XfmHandler]
if options.registration.input_space in (InputSpace.lsq6, InputSpace.lsq12):
# no registrations have been performed yet, so we can point to the input files
s_id_to_intersubj_img_dict = { s_id : subj.intersubject_registration_image
for s_id, subj in pipeline_subject_info.items() }
else:
# lsq6 aligned images
# When we ran the lsq6 alignment, we stored the XfmHandlers in the Subject dictionary. So when we call
# xfmhandler.intersubject_registration_image, this returns an XfmHandler. From which
# we want to extract the resampled file (in order to continue the registration with)
s_id_to_intersubj_img_dict = { s_id : subj_with_xfmhandler.intersubject_registration_image.resampled
for s_id, subj_with_xfmhandler in subj_id_to_subj_with_lsq6_xfm_dict.items() }
if options.application.verbose:
print("\nImages that are used for the inter-subject registration:")
print("ID\timage")
for subject in s_id_to_intersubj_img_dict:
print(subject + '\t' + s_id_to_intersubj_img_dict[subject].path)
# determine what configuration to use for the non linear registration
nonlinear_configuration = get_nonlinear_configuration_from_options(options.nlin.nlin_protocol,
options.nlin.reg_method,
options.registration.resolution)
if options.registration.input_space in [InputSpace.lsq6, InputSpace.native]:
intersubj_xfms = s.defer(lsq12_nlin_build_model(imgs=list(s_id_to_intersubj_img_dict.values()),
lsq12_conf=options.lsq12,
nlin_conf=nonlinear_configuration,
resolution=options.registration.resolution,
lsq12_dir=pipeline_lsq12_common_dir,
nlin_dir=pipeline_nlin_common_dir,
nlin_prefix="common"))
#, like={atlas_from_init_model_at_this_tp}
elif options.registration.input_space == InputSpace.lsq12:
#TODO: write reader that creates a mincANTS configuration out of an input protocol
# if we're starting with files that are already aligned with an affine transformation
# (overall scaling is also dealt with), then the target for the non linear registration
# should be the averge of the current input files.
first_nlin_target = s.defer(mincaverage(imgs=list(s_id_to_intersubj_img_dict.values()),
name_wo_ext="avg_of_input_files",
output_dir=pipeline_nlin_common_dir))
intersubj_xfms = s.defer(mincANTS_NLIN_build_model(imgs=list(s_id_to_intersubj_img_dict.values()),
initial_target=first_nlin_target,
nlin_dir=pipeline_nlin_common_dir,
conf=nonlinear_configuration))
intersubj_img_to_xfm_to_common_avg_dict = { xfm.source : xfm for xfm in intersubj_xfms.output }
# create one more convenience data structure: a mapping from subject_ID to the xfm_handler
# that contains the transformation from the subject at the common time point to the
# common time point average.
subj_ID_to_xfm_handler_to_common_avg = {}
for s_id, subj_at_common_tp in s_id_to_intersubj_img_dict.items():
subj_ID_to_xfm_handler_to_common_avg[s_id] = intersubj_img_to_xfm_to_common_avg_dict[subj_at_common_tp]
# create verification images to show the inter-subject alignment
montage_inter_subject = pipeline_montage_dir + "/quality_control_montage_inter_subject_registration.png"
avg_and_inter_subject_images = []
avg_and_inter_subject_images.append(intersubj_xfms.avg_img)
for xfmh in intersubj_xfms.output:
avg_and_inter_subject_images.append(xfmh.resampled)
inter_subject_verification_images = s.defer(create_quality_control_images(
imgs=avg_and_inter_subject_images,
montage_output=montage_inter_subject,
montage_dir=pipeline_montage_dir,
message=" the result of the inter-subject alignment"))
if options.application.verbose:
print("\nTransformations for intersubject images to final nlin common space:")
print("MincAtom\ttransformation")
for subj_atom, xfm_handler in intersubj_img_to_xfm_to_common_avg_dict.items():
print(subj_atom.path + '\t' + xfm_handler.xfm.path)
## within-subject registration
# In the toy scenario below:
# subject A A_time_1 -> A_time_2 -> A_time_3
# subject B B_time_1 -> B_time_2 -> B_time_3
# subject C C_time_1 -> C_time_2 -> C_time_3
#
# The following registrations are run:
# 1) A_time_1 -> A_time_2
# 2) A_time_2 -> A_time_3
#
# 3) B_time_1 -> B_time_2
# 4) B_time_2 -> B_time_3
#
# 5) C_time_1 -> C_time_2
# 6) C_time_2 -> C_time_3
subj_id_to_Subjec_for_within_dict = pipeline_subject_info
if options.registration.input_space == InputSpace.native:
# we started with input images that were not aligned whatsoever
# in this case we should use the images that were rigidly
# aligned files to continue the within-subject registration with
# # type: Dict[str, Subject[XfmHandler]]
subj_id_to_Subjec_for_within_dict = map_over_time_pt_dict_in_Subject(lambda x: x.resampled,
subj_id_to_subj_with_lsq6_xfm_dict)
if options.application.verbose:
print("\n\nWithin subject registrations:")
for s_id, subj in subj_id_to_Subjec_for_within_dict.items():
print("ID: ", s_id)
for time_pt, subj_img in subj.time_pt_dict.items():
print(time_pt, " ", subj_img.path)
print("\n")
# dictionary that maps subject IDs to a list containing:
# ( [(time_pt_n, time_pt_n+1, XfmHandler_from_n_to_n+1), ..., (,,,)],
# index_of_common_time_pt)
chain_xfms = { s_id : s.defer(intrasubject_registrations(
subj=subj,
linear_conf=default_lsq12_multilevel_minctracc,
nlin_conf=mincANTS_default_conf.replace(
file_resolution=options.registration.resolution,
iterations="100x100x100x50")))
for s_id, subj in subj_id_to_Subjec_for_within_dict.items() }
# create a montage image for each pair of time points
for s_id, output_from_intra in chain_xfms.items():
for time_pt_n, time_pt_n_plus_1, transform in output_from_intra[0]:
montage_chain = pipeline_montage_dir + "/quality_control_chain_ID_" + s_id + \
"_timepoint_" + str(time_pt_n) + "_to_" + str(time_pt_n_plus_1) + ".png"
chain_images = [transform.resampled, transform.target]
chain_verification_images = s.defer(create_quality_control_images(chain_images,
montage_output=montage_chain,
montage_dir=pipeline_montage_dir,
message="the alignment between ID " + s_id + " time point " +
str(time_pt_n) + " and " + str(time_pt_n_plus_1)))
if options.application.verbose:
print("\n\nTransformations gotten from the intrasubject registrations:")
for s_id, output_from_intra in chain_xfms.items():
print("ID: ", s_id)
for time_pt_n, time_pt_n_plus_1, transform in output_from_intra[0]:
print("Time point: ", time_pt_n, " to ", time_pt_n_plus_1, " trans: ", transform.xfm.path)
print("\n")
## stats
#
# The statistic files we want to create are the following:
# 1) subject <----- subject_common_time_point (resampled to common average)
# 2) subject <----- subject_common_time_point <- common_time_point_average (incorporates inter subject differences)
# 3) subject_time_point_n <----- subject_time_point_n+1 (resampled to common average)
# create transformation from each subject to the final common time point average,
# and from each subject to the subject's common time point
(non_rigid_xfms_to_common_avg, non_rigid_xfms_to_common_subj) = s.defer(get_chain_transforms_for_stats(subj_id_to_Subjec_for_within_dict,
intersubj_img_to_xfm_to_common_avg_dict,
chain_xfms))
# Ad 1) provide transformations from the subject's common time point to each subject
# These are temporary, because they still need to be resampled into the
# average common time point space
determinants_from_subject_common_to_subject = map_over_time_pt_dict_in_Subject(
lambda xfm: s.defer(determinants_at_fwhms(xfms=[s.defer(invert_xfmhandler(xfm))],
inv_xfms=[xfm], # determinants_at_fwhms now vectorized-unhelpful here
blur_fwhms=options.stats.stats_kernels)),
non_rigid_xfms_to_common_subj)
# the content of determinants_from_subject_common_to_subject is:
#
# {subject_ID : Subject(inter_subject_time_pt, time_pt_dict)
#
# where time_pt_dict contains:
#
# {time_point : Tuple(List[Tuple(float, Tuple(MincAtom, MincAtom))],
# List[Tuple(float, Tuple(MincAtom, MincAtom))])
#
# And to be a bit more verbose:
#
# {time_point : Tuple(relative_stat_files,
# absolute_stat_files)
#
# where either the relative_stat_files or the absolute_stat_files look like:
#
# [blur_kernel_1, (determinant_file_1, log_of_determinant_file_1),
# ...,
# blur_kernel_n, (determinant_file_n, log_of_determinant_file_n)]
#
# Now the only thing we really want to do, is to resample the actual log
# determinants that were generated into the space of the common average.
# To make that a little easier, I'll create a mapping that will contain:
#
# {subject_ID: Subject(intersubject_timepoint, {time_pt_1: [stat_file_1, ..., stat_file_n],
# ...,
# time_pt_n: [stat_file_1, ..., stat_file_n]}
# }
for s_id, subject_with_determinants in determinants_from_subject_common_to_subject.items():
transform_from_common_subj_to_common_avg = subj_ID_to_xfm_handler_to_common_avg[s_id].xfm
for time_pt, determinant_info in subject_with_determinants.time_pt_dict.items():
# here, each determinant_info is a DataFrame where each row contains
# 'abs_det', 'nlin_det', 'log_nlin_det', 'log_abs_det', 'fwhm' fields
# of the log-determinants, blurred at various fwhms (corresponding to different rows)
for _ix, row in determinant_info.iterrows():
for log_det_file_to_resample in (row.log_full_det, row.log_nlin_det):
# TODO the MincAtoms corresponding to the resampled files are never returned
new_name_wo_ext = log_det_file_to_resample.filename_wo_ext + "_resampled_to_common"
s.defer(mincresample(img=log_det_file_to_resample,
xfm=transform_from_common_subj_to_common_avg,
like=log_det_file_to_resample,
new_name_wo_ext=new_name_wo_ext,
subdir="stats-volumes"))
# Ad 2) provide transformations from the common avg to each subject. That's the
# inverse of what was provided by get_chain_transforms_for_stats()
determinants_from_common_avg_to_subject = map_over_time_pt_dict_in_Subject(
lambda xfm: s.defer(determinants_at_fwhms(xfms=[s.defer(invert_xfmhandler(xfm))],
inv_xfms=[xfm], # determinants_at_fwhms now vectorized-unhelpful here
blur_fwhms=options.stats.stats_kernels)),
non_rigid_xfms_to_common_avg)
# TODO don't just return an (unnamed-)tuple here
return Result(stages=s, output=Namespace(non_rigid_xfms_to_common=non_rigid_xfms_to_common_avg,
determinants_from_common_avg_to_subject=determinants_from_common_avg_to_subject,
determinants_from_subject_common_to_subject=determinants_from_subject_common_to_subject))
stats_parser,
chain_parser])
# TODO could abstract and then parametrize by prefix/ns ??
options = parse(p, sys.argv[1:])
# TODO: the registration resolution should be set somewhat outside
# of any actual function? Maybe the right time to set this, is here
# when options are gathered?
if not options.registration.resolution:
# if the target for the registration_chain comes from the pride_of_models
# we can not use the registration_targets() function. The pride_of_models
# works in a fairly different way, so we will separate out that option.
if options.lsq6.target_type == TargetType.pride_of_models:
pride_of_models_mapping = get_pride_of_models_mapping(options.lsq6.target_file,
options.application.output_directory,
options.application.pipeline_name)
# all initial models that are part of the pride of models must have
# the same resolution (it's currently a requirement). So we can get the
# resolution from any of the RegistrationTargets:
random_key = list(pride_of_models_mapping)[0]
file_for_resolution = pride_of_models_mapping[random_key].registration_standard.path
else:
file_for_resolution = registration_targets(lsq6_conf=options.lsq6,
app_conf=options.application).registration_standard.path
options.registration = options.registration.replace(
resolution=get_resolution_from_file(file_for_resolution))
# *** *** *** *** *** *** *** *** ***
chain_result = chain(options)