Select only available patients on filesystem and preprocess HN_BZ dataset

preprocessing/prepare_dataset.py

@@ -30,7 +30,7 @@ import shutil
 from tqdm import tqdm
 
 # %%
-DATASET_NAME = 'HN_val'
+DATASET_NAME = 'HN_BZ'
 PROJECT_DATA_PATH = Path('data') / DATASET_NAME
 RAW_DATA_PATH = PROJECT_DATA_PATH / 'raw'
 PROCESSED_DATA_PATH = PROJECT_DATA_PATH / 'processed'
@@ -40,12 +40,15 @@ os.makedirs(PROCESSED_DCM_PATH, exist_ok=False)
 
 
 if DATASET_NAME == 'HN_val':
-    # TODO: read path from path_original_data.csv and not from summary.csv
 
     DATASET_DESCRIPTION_FILE = 'path_original_data.csv'
 
     dataset_description = pd.read_csv(PROCESSED_DATA_PATH / DATASET_DESCRIPTION_FILE)
 
+    available_patients = patients = [
+        f for f in os.listdir(DCM_DIR) if os.path.isdir(DCM_DIR / f)
+    ]
+
     for i, row in tqdm(dataset_description.iterrows()):
         patient = row['Subject ID']
         old_files_dir = RAW_DATA_PATH / row['dicom_folder']
@@ -65,5 +68,19 @@ if DATASET_NAME == 'HN_val':
 
         shutil.copytree(old_files_dir, new_files_dir)
 
+elif DATASET_NAME == 'HN_BZ':
+
+    patients = [
+        f for f in os.listdir(RAW_DATA_PATH) if os.path.isdir(RAW_DATA_PATH / f)
+    ]
+
+    for patient in tqdm(patients):
+        old_files_dir = RAW_DATA_PATH / patient
+        new_files_dir = PROCESSED_DCM_PATH / patient
+
+        shutil.copytree(old_files_dir, new_files_dir)
+
+        os.rename(new_files_dir / 'RS', new_files_dir / 'RTSTRUCT')
+        os.rename(new_files_dir / 'PET', new_files_dir / 'PT')
 
 # %%