antspymm 1.4.5__tar.gz → 1.4.8__tar.gz

{antspymm-1.4.5/antspymm.egg-info → antspymm-1.4.8}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: antspymm
-Version: 1.4.5
+Version: 1.4.8
 Summary: multi-channel/time-series medical image processing with antspyx
 Author-email: "Avants, Gosselin, Tustison, Reardon" <stnava@gmail.com>
 License: Apache 2.0
@@ -19,9 +19,12 @@ Requires-Dist: nibabel
 Requires-Dist: scipy
 Requires-Dist: siq
 Requires-Dist: scikit-learn
+Dynamic: license-file
 
 # ANTsPyMM
 
+[![DOI](https://zenodo.org/badge/423404500.svg)](https://doi.org/10.5281/zenodo.15131653)
+
 [![CircleCI](https://dl.circleci.com/status-badge/img/gh/ANTsX/ANTsPyMM/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/ANTsX/ANTsPyMM/tree/main)
 
 ![mapping](https://i.imgur.com/qKqYjU9.jpeg)

{antspymm-1.4.5 → antspymm-1.4.8}/README.md

@@ -1,5 +1,7 @@
 # ANTsPyMM
 
+[![DOI](https://zenodo.org/badge/423404500.svg)](https://doi.org/10.5281/zenodo.15131653)
+
 [![CircleCI](https://dl.circleci.com/status-badge/img/gh/ANTsX/ANTsPyMM/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/ANTsX/ANTsPyMM/tree/main)
 
 ![mapping](https://i.imgur.com/qKqYjU9.jpeg)

{antspymm-1.4.5 → antspymm-1.4.8}/antspymm/mm.py

@@ -3882,9 +3882,13 @@ def joint_dti_recon(
         print("recon after distortion correction", flush=True)
 
     if impute:
+        print("impute begin", flush=True)
         img_LRdwp=impute_dwi( img_LRdwp, verbose=True )
+        print("impute done", flush=True)
     elif censor:
+        print("censor begin", flush=True)
         img_LRdwp, reg_LR['bvals'], reg_LR['bvecs'] = censor_dwi( img_LRdwp, reg_LR['bvals'], reg_LR['bvecs'], verbose=True )
+        print("censor done", flush=True)
     if impute and img_RL is not None:
         img_RLdwp=impute_dwi( img_RLdwp, verbose=True )
     elif censor and img_RL is not None:
@@ -5355,6 +5359,7 @@ def PerAF( x, mask, globalmean=True ):
     return outimg
 
 
+
 def resting_state_fmri_networks( fmri, fmri_template, t1, t1segmentation,
     f=[0.03, 0.08],
     FD_threshold=5.0,
@@ -7281,8 +7286,8 @@ def mm(
                 img_RL=dw_image[1],
                 bval_RL=bvals[1],
                 bvec_RL=bvecs[1],
-                motion_correct='SyN', # set to False if using input from qsiprep
-                denoise=True,
+                motion_correct=dti_motion_correct, # set to False if using input from qsiprep
+                denoise=dti_denoise,
                 verbose = verbose)
         mydti = output_dict['DTI']
         # summarize dwi with T1 outputs
@@ -10601,9 +10606,9 @@ def censor_dwi( dwi, bval, bvec, threshold = 0.20, imputeb0=False, mask=None, ve
     list1 = segment_timeseries_by_meanvalue( dwi )['highermeans']
     if imputeb0:
         dwib = impute_timeseries( dwi, list1 ) # focus on the dwi - not the b0
-        looped, list2 = loop_timeseries_censoring( dwib, threshold, mask )
+        looped, list2 = loop_timeseries_censoring( dwib, threshold, mask, verbose=verbose)
     else:
-        looped, list2 = loop_timeseries_censoring( dwi, threshold, mask )
+        looped, list2 = loop_timeseries_censoring( dwi, threshold, mask, verbose=verbose )
     if verbose:
         print( list1 )
         print( list2 )
@@ -10626,18 +10631,21 @@ def flatten_time_series(time_series):
     n_volumes = time_series.shape[3]
     return time_series.reshape(-1, n_volumes).T
 
-def calculate_loop_scores(flattened_series, n_neighbors=20):
+def calculate_loop_scores_full(flattened_series, n_neighbors=20, verbose=True ):
     """
     Calculate Local Outlier Probabilities for each volume.
     
     :param flattened_series: A 2D numpy array from flatten_time_series.
     :param n_neighbors: Number of neighbors to use for calculating LOF scores.
+    :param verbose: boolean
     :return: An array of LoOP scores.
     """
     from PyNomaly import loop
     from sklearn.neighbors import NearestNeighbors
     from sklearn.preprocessing import StandardScaler
     # replace nans with zero
+    if verbose:
+        print("loop: nan_to_num")
     flattened_series=np.nan_to_num(flattened_series, nan=0)
     scaler = StandardScaler()
     scaler.fit(flattened_series)
@@ -10645,12 +10653,109 @@ def calculate_loop_scores(flattened_series, n_neighbors=20):
     data=np.nan_to_num(data, nan=0)
     if n_neighbors > int(flattened_series.shape[0]/2.0):
         n_neighbors = int(flattened_series.shape[0]/2.0)
+    if verbose:
+        print("loop: nearest neighbors init")
     neigh = NearestNeighbors(n_neighbors=n_neighbors, metric='minkowski')
+    if verbose:
+        print("loop: nearest neighbors fit")
     neigh.fit(data)
     d, idx = neigh.kneighbors(data, return_distance=True)
+    if verbose:
+        print("loop: probability")
     m = loop.LocalOutlierProbability(distance_matrix=d, neighbor_matrix=idx, n_neighbors=n_neighbors).fit()
     return m.local_outlier_probabilities[:]
 
+
+def calculate_loop_scores(flattened_series, n_neighbors=20, 
+                                           n_features_sample=10000, seed=42, verbose=True):
+    """
+    Approximate LoOP scores using a random subset of features to reduce memory usage.
+
+    Parameters:
+        flattened_series (np.ndarray): 2D array of shape (n_samples, n_features)
+        n_neighbors (int): Number of neighbors for LOF/LoOP computation
+        n_features_sample (int): Number of features to sample for approximation
+        seed (int): Random seed for reproducible feature sampling
+        verbose (bool): If True, print detailed progress and dimensions
+
+    Returns:
+        np.ndarray: 1D array of local outlier probabilities (length n_samples)
+    """
+    import numpy as np
+    from sklearn.preprocessing import StandardScaler
+    from sklearn.neighbors import NearestNeighbors
+    from PyNomaly import loop
+
+    # -------------------------------
+    # Step 1: Input stats and cleanup
+    # -------------------------------
+    X = np.nan_to_num(flattened_series, nan=0).astype(np.float32)
+    n_samples, n_features = X.shape
+
+    if verbose:
+        print("\n[LoOP Approximation - Verbose Mode]")
+        print(f"- Original input shape: {X.shape} (samples x features)")
+        print(f"- Requested sampled features: {n_features_sample}")
+    
+    if n_features_sample > n_features:
+        n_features_sample = n_features
+        if verbose:
+            print(f"- Requested n_features_sample exceeds available features. Using all {n_features} features.")
+
+    # -------------------------------
+    # Step 2: Feature sampling
+    # -------------------------------
+    rng = np.random.default_rng(seed)
+    sampled_indices = rng.choice(n_features, n_features_sample, replace=False)
+    X_sampled = X[:, sampled_indices]
+
+    if verbose:
+        print(f"- Sampled feature shape: {X_sampled.shape} (samples x sampled_features)")
+        print(f"- Random seed for reproducibility: {seed}")
+
+    # -------------------------------
+    # Step 3: Standardization
+    # -------------------------------
+    scaler = StandardScaler(copy=False)
+    X_sampled = scaler.fit_transform(X_sampled)
+    X_sampled = np.nan_to_num(X_sampled, nan=0)
+
+    # -------------------------------
+    # Step 4: KNN setup for LoOP
+    # -------------------------------
+    if n_neighbors >= n_samples:
+        n_neighbors = max(1, n_samples // 2)
+        if verbose:
+            print(f"- Adjusted n_neighbors to {n_neighbors} (was too large for available samples).")
+
+    if verbose:
+        print(f"- Performing KNN using Minkowski distance (default p=2, Euclidean)")
+        print(f"- Each point will use its {n_neighbors} nearest neighbors for local density estimation")
+
+    neigh = NearestNeighbors(n_neighbors=n_neighbors)
+    neigh.fit(X_sampled)
+    dists, indices = neigh.kneighbors(X_sampled, return_distance=True)
+
+    # -------------------------------
+    # Step 5: LoOP probability calculation
+    # -------------------------------
+    if verbose:
+        print(f"- Distance matrix shape: {dists.shape} (samples x n_neighbors)")
+        print(f"- Neighbor index matrix shape: {indices.shape}")
+        print("- Estimating Local Outlier Probabilities (LoOP)...")
+
+    model = loop.LocalOutlierProbability(
+        distance_matrix=dists,
+        neighbor_matrix=indices,
+        n_neighbors=n_neighbors
+    ).fit()
+
+    if verbose:
+        print("- LoOP scoring complete.\n")
+
+    return model.local_outlier_probabilities[:]
+
+
 def score_fmri_censoring(cbfts, csf_seg, gm_seg, wm_seg ):
     """
     Process CBF time series to remove high-leverage points.
@@ -10718,7 +10823,7 @@ def score_fmri_censoring(cbfts, csf_seg, gm_seg, wm_seg ):
     cbfts_recon_ants = ants.copy_image_info(cbfts, cbfts_recon_ants)
     return cbfts_recon_ants, indx
 
-def loop_timeseries_censoring(x, threshold=0.5, mask=None, verbose=False):
+def loop_timeseries_censoring(x, threshold=0.5, mask=None, n_features_sample=10000, verbose=True):
     """
     Censor high leverage volumes from a time series using Local Outlier Probabilities (LoOP).
 
@@ -10726,6 +10831,7 @@ def loop_timeseries_censoring(x, threshold=0.5, mask=None, verbose=False):
     x (ANTsImage): A 4D time series image.
     threshold (float): Threshold for determining high leverage volumes based on LoOP scores.
     mask (antsImage): restricts to a ROI
+    n_features_sample (int): feature sample size default 5000
     verbose (bool)
 
     Returns:
@@ -10739,10 +10845,12 @@ def loop_timeseries_censoring(x, threshold=0.5, mask=None, verbose=False):
         flattened_series = flatten_time_series(x.numpy())
     else:
         flattened_series = ants.timeseries_to_matrix( x, mask )
-    loop_scores = calculate_loop_scores(flattened_series)
+    if verbose:
+        print("loop_timeseries_censoring: flattened")
+    loop_scores = calculate_loop_scores(flattened_series, n_features_sample=n_features_sample, verbose=verbose )
     high_leverage_volumes = np.where(loop_scores > threshold)[0]
     if verbose:
-        print("LOOP High Leverage Volumes:", high_leverage_volumes)
+        print("loop_timeseries_censoring: High Leverage Volumes:", high_leverage_volumes)
     new_asl = remove_volumes_from_timeseries(x, high_leverage_volumes)
     return new_asl, high_leverage_volumes
 

{antspymm-1.4.5 → antspymm-1.4.8/antspymm.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: antspymm
-Version: 1.4.5
+Version: 1.4.8
 Summary: multi-channel/time-series medical image processing with antspyx
 Author-email: "Avants, Gosselin, Tustison, Reardon" <stnava@gmail.com>
 License: Apache 2.0
@@ -19,9 +19,12 @@ Requires-Dist: nibabel
 Requires-Dist: scipy
 Requires-Dist: siq
 Requires-Dist: scikit-learn
+Dynamic: license-file
 
 # ANTsPyMM
 
+[![DOI](https://zenodo.org/badge/423404500.svg)](https://doi.org/10.5281/zenodo.15131653)
+
 [![CircleCI](https://dl.circleci.com/status-badge/img/gh/ANTsX/ANTsPyMM/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/ANTsX/ANTsPyMM/tree/main)
 
 ![mapping](https://i.imgur.com/qKqYjU9.jpeg)

{antspymm-1.4.5 → antspymm-1.4.8}/antspymm.egg-info/SOURCES.txt

@@ -18,6 +18,7 @@ docs/blind_qc.Rmd
 docs/blind_qc.html
 docs/convert_adni_dti_to_nrg.R
 docs/deepnbm.jpg
+docs/describe_mm_data.R
 docs/example_antspymm_output.csv
 docs/example_run_from_directory.py
 docs/make_dict_table.Rmd
@@ -30,6 +31,7 @@ docs/step1_blind_qc.py
 docs/step2_outlierness.py
 docs/step3_mm_nrg_csv.py
 docs/step4_aggregate.py
+docs/template_overlays.py
 docs/ukbb_to_nrg_processing.py
 docs/ukbb_to_nrg_processing2.py
 tests/bids_2_nrg.py
@@ -50,10 +52,12 @@ tests/outlierness.py
 tests/parallel_study_aggregation_example.py
 tests/perfusion_ptbp.py
 tests/perfusion_run.py
+tests/perfusion_run_nnl.py
 tests/rsfmri_run.py
 tests/rsfmri_run_minimal.py
 tests/test_loop.py
 tests/test_reference_run.py
+tests/test_rsfmri_run_minimal_ptbp.py
 tests/testsr.py
 tests/ukbb_rsfmri.py
 tests/visualize_tractogram.py

antspymm-1.4.8/docs/describe_mm_data.R

@@ -0,0 +1,144 @@
+# powers points 10.1016/j.conb.2012.12.009
+powers=read.csv("~/.antspymm/powers_mni_itk.csv")
+# 10.1016/j.neuroimage.2008.07.009
+# https://doi.org/10.1016/j.neuroimage.2007.07.053
+jhu=read.csv("~/.antspyt1w/FA_JHU_labels_edited.csv")
+# doi: 10.3389/fnins.2012.00171
+# http://dx.doi.org/10.1016/j.neuroimage.2006.01.021
+dktcsv=read.csv("~/.antspyt1w/dkt.csv")
+dktcsv=dktcsv[dktcsv$Label>0,]
+# hipp https://doi.org/10.1101/2023.01.17.23284693
+hipp=read.csv("~/.antspyt1w/mtl_description.csv")
+hipp$Anatomy=hipp$Description
+hipp$Anatomy=gsub("alEC"," antero-lateral entorhinal cortex",hipp$Anatomy)
+hipp$Anatomy=gsub("pMEC"," postero-medial entorhinal cortex",hipp$Anatomy)
+hipp$Anatomy=gsub("DG"," dentate gyrus",hipp$Anatomy)
+hipp$Anatomy=gsub("CA"," cornu ammonis", hipp$Anatomy)
+
+# https://doi.org/10.1101/211201
+cit=read.csv("~/.antspyt1w/CIT168_Reinf_Learn_v1_label_descriptions_pad.csv")
+cit$Anatomy=NA
+cit$Anatomy[  grep("STR_Ca", cit$Description )] = 'caudate'
+cit$Anatomy[  grep("STR_Pu", cit$Description )] = 'putamen'
+cit$Anatomy[  grep("STR_NAC", cit$Description )] = 'Nucleus Accumbens'
+cit$Anatomy[  grep("VTA", cit$Description )] = 'Ventral Tegmental Area'
+cit$Anatomy[  grep("PBP", cit$Description )] = 'Parabrachial Pigmented Nucleus'
+cit$Anatomy[  grep("SNc", cit$Description )] = 'Substantia Nigra pars compacta'
+cit$Anatomy[  grep("SNr", cit$Description )] = 'Substantia Nigra pars reticulated'
+cit$Anatomy[  grep("GPe", cit$Description )] = 'globus pallidus externa'
+cit$Anatomy[  grep("GPi", cit$Description )] = 'globus pallidus interna'
+cit$Anatomy[  grep("RN", cit$Description )] = 'red nucleus'
+cit$Anatomy[  grep("STH", cit$Description )] = 'Subthalamic Nucleus'
+cit$Anatomy[  grep("HTH", cit$Description )] = 'Hypothalamus'
+cit$Anatomy[  grep("HN", cit$Description )] = 'Habenular Nuclei'
+cit$Anatomy[  grep("EXA", cit$Description )] = 'extended amygdala'
+cit$Anatomy[  grep("BNST", cit$Description )] = 'bed nuclei of the stria terminali'
+cit$Anatomy[  grep("MN", cit$Description )] = 'mammillary nucleus'
+cit$Anatomy[  grep("SLEA", cit$Description )] = 'sublenticular extended amygdala'
+cit$Anatomy[  grep("VeP", cit$Description )] = 'ventral pallidum'
+
+interpretcnx<-function( x ) {
+    breaker=gsub("DTI_cnxcount","",x)
+    temp = unlist(strsplit(breaker,"_"))
+    ind=temp[1]
+    anat=paste( temp[-1],collapse='_')
+    return( paste( anat, "to", dktcsv[as.integer(ind),'Description'] ) )
+}
+interpretcnx2<-function( x ) {
+    breaker=gsub("DTI_cnxcount","",x)
+    temp = unlist(strsplit(breaker,"_"))
+    ind=temp[1]
+    anat=paste( temp[-1],collapse='_')
+    return( dktcsv[as.integer(ind),'Description'] )
+}
+# dd=read.csv("joined_mm_or2.csv")
+zz=data.frame( Label=colnames(dd))
+qcrows=min(grep("RandBasis",zz$Label)):grep("resnetGrade", zz$Label)
+zz$Modality='Other'
+zz[ grep("T1Hier", zz$Label), 'Modality']='T1 hierarchical processing'
+zz[ grep("T1w", zz$Label), 'Modality']='T1 DiReCT thickness processing'
+zz[ grep("DTI", zz$Label), 'Modality']='DTI'
+zz[ grep("NM2DMT", zz$Label), 'Modality']='Neuromelanin'
+zz[ grep("rsfMRI", zz$Label), 'Modality']='restingStatefMRI'
+zz[ grep("lair", zz$Label), 'Modality']='Flair'
+zz[ grep("left", zz$Label), 'side']='left'
+zz[ grep("right", zz$Label), 'side']='right'
+zz$Atlas='ANTs'
+zz[ grep("dkt", zz$Label), 'Atlas']='desikan-killiany-tourville'
+zz[ grep("cnxcou", zz$Label), 'Atlas']='desikan-killiany-tourville'
+zz[ grep("jhu", zz$Label), 'Atlas']='johns hopkins white matter'
+zz[ grep("cit", zz$Label), 'Atlas']='CIT168'
+zz[ grep("nbm", zz$Label), 'Atlas']='BF'
+zz[ grep("ch13", zz$Label), 'Atlas']='BF'
+zz[ grep("mtl", zz$Label), 'Atlas']='MTL'
+zz[ grep("rsfMRI", zz$Label),'Atlas']='power peterson fMRI meta-analyses'
+zz[qcrows,'Atlas']='quality control metrics'
+zz[qcrows,'Measurement']='QC'
+zz$Measurement[  grep("FD", zz$Label)]='motion statistic on framewise displacement'
+zz$Measurement[  grep("thk", zz$Label)]='geometry/thickness'
+zz$Measurement[  grep("area", zz$Label)]='geometry/area'
+zz$Measurement[  grep("vol", zz$Label)]='geometry/volume'
+zz$Measurement[  grep("mean_md", zz$Label)]='mean diffusion'
+zz$Measurement[  grep("mean_fa", zz$Label)]='fractional anisotropy'
+zz$Measurement[  grep("cnx", zz$Label)]='tractography-based connectivity'
+zz$Anatomy = zz$Label
+zz$Anatomy = gsub("_thk_","", zz$Anatomy)
+zz$Anatomy = gsub("_area_","", zz$Anatomy)
+zz$Anatomy = gsub("_volume_","", zz$Anatomy)
+zz$Anatomy = gsub("DTI_cnxcount","", zz$Anatomy)
+zz$Anatomy = gsub("DTI_mean_md","", zz$Anatomy)
+zz$Anatomy = gsub("DTI_mean_fa","", zz$Anatomy)
+zz$Anatomy = gsub("T1Hier_","", zz$Anatomy)
+zz$Anatomy = gsub("T1Hier","", zz$Anatomy)
+# fix dkt
+dktlabs=dktcsv$Description
+dktlabs=gsub("right ","",dktlabs)
+dktlabs=gsub("left ","",dktlabs)
+dktlabs2=gsub(" ","_",dktlabs)
+for ( k in 1:length(dktlabs) ) {
+    gg=grep( dktlabs[k], zz$Label)
+    zz[ gg, "Atlas"]="desikan-killiany-tourville"
+    zz[ gg, "Anatomy"]=dktlabs[k]
+    gg=grep( dktlabs2[k], zz$Label)
+    zz[ gg, "Atlas"]="desikan-killiany-tourville"
+    zz[ gg, "Anatomy"]=dktlabs[k]
+}
+
+# fix cit
+citlabs=tolower( cit$Description)
+for ( k in 1:length(citlabs) ) {
+    gg=grep( citlabs[k], zz$Label)
+    zz[ gg, "Atlas"]="CIT168"
+    zz[ gg, "Anatomy"]=cit$Anatomy[k]
+}
+zz$Anatomy = gsub("DTIfa","", zz$Anatomy)
+zz$Anatomy = gsub("DTImd","", zz$Anatomy)
+zz$Anatomy = gsub("dktregions","", zz$Anatomy)
+zz$Anatomy = gsub("dktcortex"," cortex only ", zz$Anatomy)
+zz$Anatomy = gsub("_right_","", zz$Anatomy)
+zz$Anatomy = gsub("_left_","", zz$Anatomy)
+zz$Anatomy = gsub("right","", zz$Anatomy)
+zz$Anatomy = gsub("left","", zz$Anatomy)
+zz$Anatomy = gsub("jhu_icbm_labels_1mm","", zz$Anatomy)
+zz[ grep("u_hier_id", zz$Label), -1 ]='unique id'
+cnxrows=grep("DTI_cnxcount",zz$Label)
+for ( k in cnxrows )
+    zz$Anatomy[k]=interpretcnx( zz[k,'Label'] )
+
+zz[ multigrep( c("rsfMRI","R"), zz$Label, intersect=TRUE), 'side'  ]='right'
+zz[ multigrep( c("rsfMRI","L"), zz$Label, intersect=TRUE), 'side'  ]='left'
+zz$Measurement[ multigrep( c("rsfMRI","_2_"), zz$Label, intersect=TRUE) ]='network correlation'
+zz$Measurement[ multigrep(c("rsfMRI","_alff"), zz$Label, intersect=TRUE) ]='amplitude of low frequency fluctuations ALFF'
+zz$Measurement[ multigrep( c("rsfMRI","_falff"), zz$Label, intersect=TRUE) ]='fractional amplitude of low frequency fluctuations fALFF'
+zz$Anatomy = gsub("rsfMRI_", "", zz$Anatomy )
+zz$Anatomy = gsub("falffPoint", "", zz$Anatomy )
+zz$Anatomy = gsub("alffPoint", "", zz$Anatomy )
+noncnx=1:1888
+for ( k in sample(noncnx, 3) ) print( zz[k,c("Label","Atlas","Anatomy")] )
+
+zz[ zz$Label == 'Flair', 'Measurement' ]='white matter hyper-intensity'
+zz[ zz$Label == 'T2Flair_flair_wmh_prior', 'Measurement' ]='prior-constrained white matter hyper-intensity'
+
+zz[ multigrep( c("NM2DMT", "q0pt"),  zz$Label, intersect=TRUE), "Measurement"  ]='neuromelanin intensity quantile'
+
+write.csv( zz, "~/code/ANTsPyMM/antspymm_data_dictionary.csv", row.names=FALSE)

antspymm-1.4.8/docs/template_overlays.py

@@ -0,0 +1,17 @@
+
+######## template figures ########
+import ants
+import antspymm
+import pandas as pd
+# Example Usage
+scalar_label_df = pd.DataFrame({'label': range(33), 'scalar_value': range(33)})
+prefix = '../PPMI_template0_'
+print("begin")
+for t in ['mtl','bf','jhuwm','cerebellum','cit168']:
+    print( t )
+    proimgs=antspymm.template_figure_with_overlay(scalar_label_df, prefix, template=t, outputfilename='/tmp/py_viz_'+t+'.png' )
+t='ctx'
+scalar_label_df = pd.DataFrame({'label': range(1001,1200), 'scalar_value': range(1001,1200)})
+proimgs=antspymm.template_figure_with_overlay(scalar_label_df, prefix, template=t, mask_dilation=0, outputfilename='/tmp/py_viz_'+t+'.png')
+
+

{antspymm-1.4.5 → antspymm-1.4.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "antspymm"
-version = "1.4.5"
+version = "1.4.8"
 description = "multi-channel/time-series medical image processing with antspyx"
 readme = "README.md"
 requires-python = ">=3.8"

antspymm-1.4.8/tests/perfusion_run_nnl.py

@@ -0,0 +1,46 @@
+import sys, os
+import unittest
+
+os.environ["TF_NUM_INTEROP_THREADS"] = "8"
+os.environ["TF_NUM_INTRAOP_THREADS"] = "8"
+os.environ["ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS"] = "8"
+
+import tempfile
+import shutil
+import tensorflow as tf
+import antspymm
+import antspyt1w
+import antspynet
+import ants
+import numpy as np
+from scipy.stats import median_abs_deviation
+import math
+
+islocal = False
+t1fn = '/Users/stnava/code/NNL/data/sub-1001-0462_run-001_t1.nii.gz'
+ffn='/Users/stnava/code/NNL/data/sub-1001-0462_run-001_perf.nii.gz'
+fmri = ants.image_read( ffn )
+#dkt
+if not 'dkt' in globals():
+  t1head = ants.image_read( t1fn ).n3_bias_field_correction( 8 ).n3_bias_field_correction( 4 )
+  t1bxt = antspynet.brain_extraction( t1head, 't1' ).threshold_image( 0.3, 1.0 )
+  t1 = t1bxt * t1head
+  t1seg = antspynet.deep_atropos( t1head )
+  t1segmentation = t1seg['segmentation_image']
+  dkt = antspynet.desikan_killiany_tourville_labeling( t1head )
+#################
+
+#################
+type_of_transform='Rigid'
+tc='alternating'
+fmri_template, hlinds = antspymm.loop_timeseries_censoring( fmri, 0.1 )
+fmri_template = ants.get_average_of_timeseries( fmri_template )
+print("do perf")
+olthresh=0.2
+perf = antspymm.bold_perfusion( fmri, fmri_template, t1head, t1, 
+  t1segmentation, dkt, nc=4, type_of_transform=type_of_transform,
+  spa=(0.,0.,0.,0.),
+  outlier_threshold=olthresh, add_FD_to_nuisance=False, verbose=True )
+ants.image_write( ants.iMath( perf['perfusion'], "Normalize" ), '/tmp/temp.nii.gz' )
+ants.image_write( perf['motion_corrected'], '/tmp/temp2.nii.gz' )
+ants.plot( ants.iMath( perf['perfusion'], "Normalize" ), axis=2, crop=True )

{antspymm-1.4.5 → antspymm-1.4.8}/tests/test_loop.py

@@ -15,6 +15,5 @@ import math
 testingClass = unittest.TestCase( )
 islocal = False
 idp = "LS2001_3T_rfMRI_REST1_LR_gdc"
-# fmri = ants.image_read( antspymm.get_data( idp, target_extension=".nii.gz") )
-# fmri = ants.resample_image( fmri, [20,20,20,20], use_voxels=True )
-# fmri_template, hlinds = antspymm.loop_timeseries_censoring( fmri, 0.1 )
+fmri = ants.image_read( antspymm.get_data( idp, target_extension=".nii.gz") )
+fmri_template, hlinds = antspymm.loop_timeseries_censoring( fmri, 0.1 )

antspymm-1.4.8/tests/test_rsfmri_run_minimal_ptbp.py

@@ -0,0 +1,53 @@
+import sys, os
+import unittest
+
+os.environ["TF_NUM_INTEROP_THREADS"] = "8"
+os.environ["TF_NUM_INTRAOP_THREADS"] = "8"
+os.environ["ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS"] = "8"
+
+import tempfile
+import shutil
+import tensorflow as tf
+import antspymm
+import antspyt1w
+import antspynet
+import ants
+import numpy as np
+import math
+import glob
+
+testingClass = unittest.TestCase( )
+id = 'PEDS131'; dt = '20130816' # high motion - bad volumes
+id = "PEDS074"; dt = "20110803" # high motion - bad volumes
+# id = 'PEDS144'; dt = '20131212' # not so bad
+# id = "PEDS107"; dt = "20130118" # challenging
+prefix = "/Users/stnava/data/PTBP/images/" + id + "/" + dt 
+bold = glob.glob( prefix + '/BOLD/' + id + "_" + dt + "*bold*nii.gz" )
+t1w = glob.glob( prefix + '/Anatomy/' + id + "_" + dt + "*t1.nii.gz" )
+rsfn = bold[0]
+print( rsfn )
+t1fn = t1w[0]
+import pandas as pd
+print("do t1")
+if not "t1" in globals():
+    t1 = ants.image_read( t1fn ).n3_bias_field_correction( 8 ).n3_bias_field_correction( 4 )
+    t1bxt = antspynet.brain_extraction( t1, 't1' ).threshold_image( 0.3, 1.0 )
+    t1seg = antspynet.deep_atropos( t1 )
+    t1segmentation = t1seg['segmentation_image']
+
+if not 'rsfpro' in globals():
+  print("do rsf: default")
+  img1 = ants.image_read( rsfn )
+  fmri_template, hlinds = antspymm.loop_timeseries_censoring( img1, 0.1 )
+  fmri_template = antspymm.get_average_rsf( fmri_template )
+#  img1 = antspymm.remove_volumes_from_timeseries(img1, list(range(55,4000)))
+  rsfpro = antspymm.resting_state_fmri_networks(
+    img1,
+    fmri_template, t1 * t1bxt, t1segmentation,
+    verbose=True )
+  mm = { 'rsf': rsfpro }
+  antspymm.write_mm( '/tmp/RSF', mm )  
+  ants.plot( rsfpro['fmri_template'], rsfpro[ rsfpro['dfnname']], crop=True, axis=2 )
+  ants.plot( rsfpro['fmri_template'], rsfpro['alff'], crop=True, axis=2 )
+  ants.plot( rsfpro['fmri_template'], rsfpro['falff'], crop=True, axis=2 )
+  ants.plot( rsfpro['fmri_template'], rsfpro['PerAF'], crop=True, axis=2 )