Unable to generate masks from .xml built through custom annotated WSI

[MalviyaR]

Hello,

I am using ASAP 1.9 to generate customized annotations and save them as .xml files. Thus generated .xml file is fine, but when I use AnnotationtoMask.py to generate masks I am getting a blank image for the custom annotations I have done. However, the same code generates the masks for the annotations (.xml files) given with the dataset.

Please help me with this.
Thanks

Following is the code:

import os 
import multiresolutionimageinterface as mir

reader = mir.MultiResolutionImageReader()
train_dataset_path = "F:\\CAMELYON17\\OriginalImagesGivenAnnotations"

anno_path = "F:\\CAMELYON17\\Training\\annotation\\" # path to annotation file
xml_files = os.listdir(anno_path)


for entry in os.listdir(anno_path):
    print(entry)

    annofile_lc = entry if len(entry) == 25 else None
    img_path = train_dataset_path

    # Looping
    for item in os.listdir(img_path):
        print(item)
        if item.startswith(entry[0:-7]):
            item = item
            print(item)
            wsi_path = train_dataset_path + '/' + item
            print(wsi_path)
            mr_image = reader.open(wsi_path)
            try:
                annotation_list = mir.AnnotationList()
                xml_repository = mir.XmlRepository(annotation_list)
                xml_repository.setSource(anno_path + annofile_lc)
                xml_repository.load()
                annotation_mask = mir.AnnotationToMask()
                camelyon17_type_mask = True
                label_map = {'metastases': 1, 'normal': 2} if camelyon17_type_mask else {'_0': 1, '_1': 1, '_2': 0}
                conversion_order = ['metastases', 'normal'] if camelyon17_type_mask else ['_0', '_1', '_2']
                output_path = ('G:\\DataPrep\\LocalContext\\WSI50Masks\\' + entry[0:-4] + 'try_mask.tif')
                annotation_mask.convert(annotation_list, output_path, mr_image.getDimensions(), mr_image.getSpacing(), label_map, conversion_order)
            except:
                mr_image is None