Import and use new

02_radiomics_features_extraction/extract_features_radiomics.py

 #%%
 import os
-from radiomics import featureextractor
+from pyradiomics_radler import MyRadiomicsFeaturesExtractor as RadiomicsFeatureExtractor
 import SimpleITK as sitk
 import numpy as np
 import pandas as pd
-import os
 
 from pathlib import Path
 from tqdm import tqdm
@@ -14,6 +13,8 @@ import warnings
 
 warnings.filterwarnings("ignore")
 # %%
+
+# os.chdir('..')
 DATASET = Path('HN_val')
 BBOX = 'bbox_64'
 VOXEL_SPACING = (1.0, 1.0, 1.0)
@@ -25,30 +26,23 @@ PIXEL_SPACING = [1.0, 2.0, 3.0, 4.0, 5.0]
 #%%
 DATADIR = Path('data') / DATASET / 'processed' / 'bbox' / BBOX
 OUTDIR = Path('data') / DATASET / 'processed'
-OUTFILE = f'radiomics_features_{BBOX}.csv'  # output file name
+OUTFILE = f'radiomics_features_{BBOX}_radnew21.csv'  # output file name
+
 clinical = pd.read_csv(Path('data') / DATASET / 'processed' / f'clinical_{DATASET}.csv')
 
 #%%
-params_shape = 'shape.yaml'  # param file to use to create the extractor
-extractor_shape = featureextractor.RadiomicsFeaturesExtractor(params_shape)
+params_shape = '02_radiomics_features_extraction/shape_new.yaml'  # param file to use to create the extractor
+extractor_shape = RadiomicsFeatureExtractor(params_shape)
 
-params_intensity = 'intensity.yaml'  # param file to use to create the extractor
-extractor_intensity = featureextractor.RadiomicsFeaturesExtractor(params_intensity)
+params_intensity = '02_radiomics_features_extraction/intensity.yaml'  # param file to use to create the extractor
+extractor_intensity = RadiomicsFeatureExtractor(params_intensity)
 
-params_texture = 'texture.yaml'  # param file to use to create the extractor
-extractor_texture = featureextractor.RadiomicsFeaturesExtractor(params_texture)
+params_texture = '02_radiomics_features_extraction/texture_new.yaml'  # param file to use to create the extractor
+extractor_texture = RadiomicsFeatureExtractor(params_texture)
 
-filenames = [f for f in os.listdir(DATADIR) if f.endswith('.npy')]
+filenames = [f for f in os.listdir(DATADIR) if f.endswith('.npy')][:2]
 
 exclude_list = []
-#     'HN-CHUM-011',
-#     'HN-HMR-008',
-#     'HN-CHUS-043',
-#     'HN-HMR-002',
-#     'HN-CHUM-010',
-#     'HN-HGJ-044',
-# ]  #'HN-CHUM-020', 'HN-CHUS-093', 'HN-HMR-001', 'HN-HMR-007', 'HN-HMR-017'] # BAD SUV conversion
-
 
 #%%
 def process_file(filename):
@@ -66,12 +60,15 @@ def process_file(filename):
             curr_modality.SetSpacing(VOXEL_SPACING)
             modalities.append(curr_modality)
 
+        # print(data[-1, :, :, :] == data[1, :, :, :])
+        # print(np.max(data[-1, :, :, :]))
         has_label = np.max(data[-1, :, :, :]) > 0
 
         if has_label:
             segmentation = sitk.GetImageFromArray(data[-1, :, :, :].astype(np.uint8))
             segmentation.SetSpacing(VOXEL_SPACING)
             feature = {}
+
             # shape features
             result = extractor_shape.execute(modalities[0], segmentation)
             for key, value in result.items():
@@ -95,28 +92,26 @@ def process_file(filename):
 
                                 # uniform binning
                                 extractor_texture.settings['binMode'] = 'uniform'
-                                try:
-                                    result = extractor_texture.execute(
-                                        modality, segmentation
-                                    )
-                                    for key, value in result.items():
-                                        if not key.startswith("general_"):
-                                            feature[
-                                                f'{key}_{P}_{NB}_uniform_{name}'
-                                            ] = result[key]
-
-                                    # equalized binning
-                                    extractor_texture.settings['binMode'] = 'equal'
-                                    result = extractor_texture.execute(
-                                        modality, segmentation
-                                    )
-                                    for key, value in result.items():
-                                        if not key.startswith("general_"):
-                                            feature[
-                                                f'{key}_{P}_{NB}_equalized_{name}'
-                                            ] = result[key]
-                                except:
-                                    broken = True
+
+                                result = extractor_texture.execute(
+                                    modality, segmentation
+                                )
+                                for key, value in result.items():
+                                    if not key.startswith("general_"):
+                                        feature[
+                                            f'{key}_{P}_{NB}_uniform_{name}'
+                                        ] = result[key]
+
+                                # equalized binning
+                                extractor_texture.settings['binMode'] = 'equal'
+                                result = extractor_texture.execute(
+                                    modality, segmentation
+                                )
+                                for key, value in result.items():
+                                    if not key.startswith("general_"):
+                                        feature[
+                                            f'{key}_{P}_{NB}_equalized_{name}'
+                                        ] = result[key]
 
             if not broken:
                 feature['filename'] = filename
@@ -127,22 +122,32 @@ def process_file(filename):
                 return feature
 
         else:
-            return {}
+            return {'filename': filename, 'patient': patient}
 
 
 #%% MULTIPROCESS
+result = []
+for file in filenames:
+    feat = process_file(file)
+    result.append(feat)
 
-multiproc = ListMultiprocessing(process_file, N_JOBS)
-multiproc.execute(filenames)
-result = multiproc.get_result()
 
-print('done')
+# %%
+
+
+# multiproc = ListMultiprocessing(process_file, N_JOBS)
+# multiproc.execute(filenames)
+# result = multiproc.get_result()
+
+# print('done')
 #%% Save features in a Pandas df
 features = pd.DataFrame(result)
 features.set_index('filename', inplace=True)
 
 print('Number of files: ', features.shape[0])
-print('Number of features: ', features.shape[1])
+print('Number of features: ', features.shape[1] - 1)
 # %%
 features.to_csv(OUTDIR / OUTFILE)
 
+
+# %%