fix path in readme and preprocessing (#927)

Signed-off-by: Can Zhao <canz@nvidia.com>

Signed-off-by: Can Zhao <canz@nvidia.com>

Author: Can-Zhao

multimodal/openi_multilabel_classification_transchex/README.md

@@ -14,10 +14,8 @@ completed, the dataset can be readily used for the tutorial.
 
 ### Preprocessing Steps
 1) Create a new folder named 'monai_data' for downloading the raw data and preprocessing.
-2) Download the chest X-ray images in PNG format from this [link](https://openi.nlm.nih.gov/imgs/collections/NLMCXR_png.tgz). Copy the downloaded file (NLMCXR_png.tgz)
-to 'monai_data' directory and extract it.
-3) Download the reports in XML format from this [link](https://openi.nlm.nih.gov/imgs/collections/NLMCXR_reports.tgz). Copy the downloaded file (NLMCXR_reports.tgz)
-to 'monai_data' directory and extract it.
+2) Download the chest X-ray images in PNG format from this [link](https://openi.nlm.nih.gov/imgs/collections/NLMCXR_png.tgz). Copy the downloaded file (NLMCXR_png.tgz) to 'monai_data' directory and extract it to 'monai_data/dataset_orig/NLMCXR_png/'.
+3) Download the reports in XML format from this [link](https://openi.nlm.nih.gov/imgs/collections/NLMCXR_reports.tgz). Copy the downloaded file (NLMCXR_reports.tgz) to 'monai_data' directory and extract it to 'monai_data/dataset_orig/NLMCXR_reports/'.
 4) Download the splits of train, validation and test datasets from this [link](https://drive.google.com/u/1/uc?id=1jvT0jVl9mgtWy4cS7LYbF43bQE4mrXAY&export=download). Copy the downloaded file (TransChex_openi.zip)
-to 'monai_data' directory and extract it.
+to 'monai_data' directory and extract it here.
 5) Run 'preprocess_openi.py' to process the images and reports.

multimodal/openi_multilabel_classification_transchex/preprocess_openi.py

@@ -28,6 +28,8 @@ def create_report(img_names_list_, report_list_, gt_list_, save_add):
 
 report_file_add= './monai_data/dataset_orig/NLMCXR_reports/ecgen-radiology'
 img_file_add= './monai_data/dataset_orig/NLMCXR_png'
+npy_add= './monai_data/TransChex_openi/'
+
 img_save_add = './monai_data/dataset_proc/images'
 report_train_save_add = './monai_data/dataset_proc/train.csv'
 report_val_save_add = './monai_data/dataset_proc/validation.csv'
@@ -37,15 +39,15 @@ def create_report(img_names_list_, report_list_, gt_list_, save_add):
     os.makedirs(img_save_add)
 report_files = [f for f in listdir(report_file_add) if isfile(join(report_file_add, f))]
 
-train_data = np.load('./train.npy', allow_pickle=True).item()
+train_data = np.load(npy_add+'train.npy', allow_pickle=True).item()
 train_data_id = train_data['id_GT']
 train_data_gt = train_data['label_GT']
 
-val_data = np.load('./validation.npy', allow_pickle=True).item()
+val_data = np.load(npy_add+'validation.npy', allow_pickle=True).item()
 val_data_id = val_data['id_GT']
 val_data_gt = val_data['label_GT']
 
-test_data = np.load('./test.npy', allow_pickle=True).item()
+test_data = np.load(npy_add+'test.npy', allow_pickle=True).item()
 test_data_id = test_data['id_GT']
 test_data_gt = test_data['label_GT']