Vision inference

save_series_pred

 save_series_pred (series_obj, save_dir, val='1234')

Saves series prediction with updated DICOM UIDs.

source

load_system_resources

 load_system_resources (models_path, learner_fn, variables_fn)

Load necessary resources like learner and variables.

source

inference

 inference (learn_inf, reorder, resample,
            fn:(<class'str'>,<class'pathlib.Path'>)='',
            save_path:(<class'str'>,<class'pathlib.Path'>)=None,
            org_img=None, input_img=None, org_size=None)

Predict on new data using exported model.

source

compute_binary_tumor_volume

 compute_binary_tumor_volume (mask_data:torchio.data.image.Image)

Compute the volume of the tumor in milliliters (ml).

Post-processing

source

refine_binary_pred_mask

 refine_binary_pred_mask (pred_mask,
                          remove_size:(<class'int'>,<class'float'>)=None,
                          percentage:float=0.2, verbose:bool=False)

*Removes small objects from the predicted binary mask.

Args: pred_mask: The predicted mask from which small objects are to be removed. remove_size: The size under which objects are considered ‘small’. percentage: The percentage of the remove_size to be used as threshold. Defaults to 0.2. verbose: If True, print the number of components. Defaults to False.

Returns: The processed mask with small objects removed.*

Gradio

source

gradio_image_classifier

 gradio_image_classifier (file_obj, learn, reorder, resample)

Predict on images using exported learner and return the result as a dictionary.