analyzin pixel spacings and pickled dict with pixel spaces and pids a…

…s key

analyze_dsb_pixel_spacings.py

@@ -0,0 +1,45 @@
+import cPickle as pickle
+import string
+import sys
+import time
+from itertools import izip
+import numpy as np
+from datetime import datetime, timedelta
+import utils
+import utils_lung
+import logger
+import buffering
+import pathfinder
+import data_iterators
+
+
+candidates_config = 'dsb_c3_s5_p8a1'
+predictions_dir = utils.get_dir_path('model-predictions', pathfinder.METADATA_PATH)
+candidates_path = predictions_dir + '/%s' % candidates_config
+id2candidates_path = utils_lung.get_candidates_paths(candidates_path)
+
+train_valid_ids = utils.load_pkl(pathfinder.VALIDATION_SPLIT_PATH)
+train_pids, valid_pids, test_pids = train_valid_ids['training'], train_valid_ids['validation'], train_valid_ids['test']
+all_pids = train_pids + valid_pids + test_pids
+
+data_iterator = data_iterators.DSBPixelSpacingsGenerator(pathfinder.DATA_PATH, id2candidates_path, all_pids)
+
+
+z = []
+y = []
+x = []
+pixel_spacings = {}
+
+# use buffering.buffered_gen_threaded()
+for idx, (pid, pixel_spacing) in enumerate(data_iterator.generate()):
+    print idx, pid, pixel_spacing
+    z.append(pixel_spacing[0])
+    y.append(pixel_spacing[1])
+    x.append(pixel_spacing[2])
+    pixel_spacings[pid] = pixel_spacing
+
+
+utils.save_pkl(pixel_spacings, 'pixel_spacings_dsb.pkl')
+print 'z', min(z), max(z)
+print 'y', min(y), max(y)
+print 'x', min(x), max(x)

data_iterators.py

@@ -1679,6 +1679,35 @@ def generate(self):
             yield x_batch, y_batch, pid
 
 
+
+
+class DSBPixelSpacingsGenerator(object):
+    def __init__(self, data_path, id2candidates_path, patient_ids):
+
+        self.id2candidates_path = id2candidates_path
+        self.patient_paths = []
+        if patient_ids is not None:
+            for pid in patient_ids:
+                if pid in self.id2candidates_path:  # TODO: this should be redundant if fpr and segemntation are correctly generated
+                    self.patient_paths.append(data_path + '/' + pid)
+        else:
+            raise ValueError('provide patient ids')
+
+        self.nsamples = len(self.patient_paths)
+        self.data_path = data_path
+
+    def generate(self):
+
+        for idx in xrange(self.nsamples):
+
+            patient_path = self.patient_paths[idx]
+            pid = utils_lung.extract_pid_dir(patient_path)
+
+            img, pixel_spacing = utils_lung.read_dicom_scan(patient_path)
+
+            yield  pid, pixel_spacing
+
+
 class DSBPatientsDataGenerator_only_heatmap(object):
     def __init__(self, data_path, batch_size, transform_params, id2candidates_path, data_prep_fun, 
                  n_candidates_per_patient, rng, random, infinite, candidates_prep_fun, return_patch_locs=False, shuffle_top_n=False, patient_ids=None):