Updated the liver tumor example

Signed-off-by: M Q <mingmelvinq@nvidia.com>

Author: MMelQin

examples/apps/ai_livertumor_seg_app/app.py

@@ -13,9 +13,7 @@
 from pathlib import Path
 
 from livertumor_seg_operator import LiverTumorSegOperator
-
-# Required for setting SegmentDescription attributes. Direct import as this is not part of App SDK package.
-from pydicom.sr.codedict import codes
+from pydicom.sr.codedict import codes  # Required for setting SegmentDescription attributes.
 
 from monai.deploy.conditions import CountCondition
 from monai.deploy.core import AppContext, Application
@@ -26,33 +24,12 @@
 from monai.deploy.operators.dicom_series_to_volume_operator import DICOMSeriesToVolumeOperator
 from monai.deploy.operators.stl_conversion_operator import STLConversionOperator
 
-# from monai.deploy.operators.publisher_operator import PublisherOperator
-
-# This is a sample series selection rule in JSON, simply selecting CT series.
-# If the study has more than 1 CT series, then all of them will be selected.
-# Please see more detail in DICOMSeriesSelectorOperator.
-# For list of string values, e.g. "ImageType": ["PRIMARY", "ORIGINAL"], it is a match if all elements
-# are all in the multi-value attribute of the DICOM series.
-
-Sample_Rules_Text = """
-{
-    "selections": [
-        {
-            "name": "CT Series",
-            "conditions": {
-                "Modality": "(?i)CT",
-                "ImageType": ["PRIMARY", "ORIGINAL"],
-                "PhotometricInterpretation": "MONOCHROME2"
-            }
-        }
-    ]
-}
-"""
+# This sample example completes the processing of a DICOM series with around 600 instances within 45 seconds,
+# and time reduces to about 23 seconds if the STL generation is disabled,
+# on a desktop with Ubuntu 20.04, 32GB of RAM, and a Nvidia GPU GV100 with 32GB of memory.
 
 
 # @resource(cpu=1, gpu=1, memory="7Gi")
-# pip_packages can be a string that is a path(str) to requirements.txt file or a list of packages.
-# The MONAI pkg is not required by this class, instead by the included operators.
 class AILiverTumorApp(Application):
     def __init__(self, *args, **kwargs):
         """Creates an application instance."""
@@ -62,9 +39,9 @@ def __init__(self, *args, **kwargs):
 
     def run(self, *args, **kwargs):
         # This method calls the base class to run. Can be omitted if simply calling through.
-        self._logger.debug(f"Begin {self.run.__name__}")
+        self._logger.info(f"Begin {self.run.__name__}")
         super().run(*args, **kwargs)
-        self._logger.debug(f"End {self.run.__name__}")
+        self._logger.info(f"End {self.run.__name__}")
 
     def compose(self):
         """Creates the app specific operators and chain them up in the processing DAG."""
@@ -88,7 +65,7 @@ def compose(self):
         #     self, model_path=model_path, output_folder=app_output_path, name="seg_op"
         # )
 
-        # Create the publisher operator
+        # Create the surface mesh STL conversion operator
         stl_op = STLConversionOperator(self, output_file=app_output_path.joinpath("stl/mesh.stl"), name="stl_op")
 
         # Create DICOM Seg writer providing the required segment description for each segment with
@@ -144,6 +121,27 @@ def compose(self):
         self._logger.info(f"End {self.compose.__name__}")
 
 
+# This is a sample series selection rule in JSON, simply selecting CT series.
+# If the study has more than 1 CT series, then all of them will be selected.
+# Please see more detail in DICOMSeriesSelectorOperator.
+# For list of string values, e.g. "ImageType": ["PRIMARY", "ORIGINAL"], it is a match if all elements
+# are all in the multi-value attribute of the DICOM series.
+
+Sample_Rules_Text = """
+{
+    "selections": [
+        {
+            "name": "CT Series",
+            "conditions": {
+                "Modality": "(?i)CT",
+                "ImageType": ["PRIMARY", "ORIGINAL"],
+                "PhotometricInterpretation": "MONOCHROME2"
+            }
+        }
+    ]
+}
+"""
+
 if __name__ == "__main__":
     # Creates the app and test it standalone. When running is this mode, please note the following:
     #     -m <model file>, for model file path

examples/apps/ai_livertumor_seg_app/livertumor_seg_operator.py

@@ -90,11 +90,12 @@ def compute(self, op_input, op_output, context):
         # This operator gets an in-memory Image object, so a specialized ImageReader is needed.
         _reader = InMemImageReader(input_image)
 
-        # In this example, the input image, once loaded at the beginning of the pre-transforms, is
-        # saved on disk, so is the segmentation prediction image at the end of the post-transform.
+        # In this example, the input image, once loaded at the beginning of the pre-transforms, can
+        # be saved on disk, so can the segmentation prediction image at the end of the post-transform.
         # They are both saved in the same subfolder of the application output folder, with names
-        # distinguished by postfix. They can also be save in different subfolder if need be.
+        # distinguished by the postfix. They can also be saved in different subfolder if need be.
         # These images files can then be packaged for rendering.
+        # In the code below, saving of the image files are disabled to save 10 seconds if nii, and 20 if nii.gz
         pre_transforms = self.pre_process(_reader, str(self.output_folder))
         post_transforms = self.post_process(pre_transforms, str(self.output_folder))
 
@@ -131,13 +132,15 @@ def pre_process(self, img_reader, out_dir: str = "./input_images") -> Compose:
             [
                 LoadImaged(keys=my_key, reader=img_reader),
                 EnsureChannelFirstd(keys=my_key),
-                SaveImaged(
-                    keys=my_key,
-                    output_dir=out_dir,
-                    output_postfix="",
-                    resample=False,
-                    output_ext=".nii",  # favor speed over size
-                ),
+                # The SaveImaged transform can be commented out to save 5 seconds.
+                # Uncompress NIfTI file, nii, is used favoring speed over size, but can be changed to nii.gz
+                # SaveImaged(
+                #     keys=my_key,
+                #     output_dir=out_dir,
+                #     output_postfix="",
+                #     resample=False,
+                #     output_ext=".nii",
+                # ),
                 Spacingd(keys=my_key, pixdim=(1.0, 1.0, 1.0), mode=("bilinear"), align_corners=True),
                 ScaleIntensityRanged(my_key, a_min=-21, a_max=189, b_min=0.0, b_max=1.0, clip=True),
                 CropForegroundd(my_key, source_key=my_key),
@@ -157,13 +160,15 @@ def post_process(self, pre_transforms: Compose, out_dir: str = "./prediction_out
                 Invertd(
                     keys=pred_key, transform=pre_transforms, orig_keys=self._input_dataset_key, nearest_interp=True
                 ),
-                SaveImaged(
-                    keys=pred_key,
-                    output_dir=out_dir,
-                    output_postfix="seg",
-                    output_dtype=uint8,
-                    resample=False,
-                    output_ext=".nii",  # favor speed over size
-                ),
+                # The SaveImaged transform can be commented out to save 5 seconds.
+                # Uncompress NIfTI file, nii, is used favoring speed over size, but can be changed to nii.gz
+                # SaveImaged(
+                #     keys=pred_key,
+                #     output_dir=out_dir,
+                #     output_postfix="seg",
+                #     output_dtype=uint8,
+                #     resample=False,
+                #     output_ext=".nii",
+                # ),
             ]
         )

setup.cfg

@@ -98,8 +98,8 @@ show_column_numbers = True
 show_error_codes = True
 # Use visually nicer output in error messages: use soft word wrap, show source code snippets, and show error location markers.
 pretty = False
-# Exclude certail files/folders
-exclude = (dist|notebooks)/$
+# Exclude certain files/folders
+exclude = (dist|notebooks|platforms)/$
 
 [mypy-versioneer]
 # Ignores all non-fatal errors.