Update the multi-AI app. Tested working

Signed-off-by: M Q <[email protected]>

Author: MMelQin

examples/apps/ai_multi_ai_app/app.py

@@ -11,15 +11,22 @@
 
 import logging
 
-from monai.deploy.core import Application, env, resource
+# Required for setting SegmentDescription attributes. Direct import as this is not part of App SDK package.
+from pydicom.sr.codedict import codes
+
+import monai.deploy.core as md
+from monai.deploy.core import Application, resource
 from monai.deploy.core.domain import Image
 from monai.deploy.core.io_type import IOType
 from monai.deploy.operators.dicom_data_loader_operator import DICOMDataLoaderOperator
-from monai.deploy.operators.dicom_seg_writer_operator import DICOMSegmentationWriterOperator
+from monai.deploy.operators.dicom_seg_writer_operator import DICOMSegmentationWriterOperator, SegmentDescription
 from monai.deploy.operators.dicom_series_selector_operator import DICOMSeriesSelectorOperator
 from monai.deploy.operators.dicom_series_to_volume_operator import DICOMSeriesToVolumeOperator
-from monai.deploy.operators.monai_bundle_inference_operator import IOMapping, MonaiBundleInferenceOperator
-from monai.deploy.operators.stl_conversion_operator import STLConversionOperator  # import as needed.
+from monai.deploy.operators.monai_bundle_inference_operator import (
+    BundleConfigNames,
+    IOMapping,
+    MonaiBundleInferenceOperator,
+)
 
 
 @resource(cpu=1, gpu=1, memory="7Gi")
@@ -28,7 +35,7 @@
 # The Bundle Inference Operator as of now only requires torch>=1.10.2, and does not yet dynamically
 # parse the MONAI bundle to get the required pip package or ver on initialization, hence it does not set
 # its own @env decorator accordingly when the app is being packaged into a MONAI Package.
-@env(pip_packages=["torch>=1.12.0"])
+@md.env(pip_packages=["torch>=1.12.0"])
 # 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 App(Application):
@@ -50,7 +57,7 @@ class App(Application):
         <parent_fodler>
         ├── pancreas_ct_dints
         │   └── model.ts
-        └── spleen_model
+        └── spleen_ct
             └── model.ts
 
     Note:
@@ -91,20 +98,71 @@ def compose(self):
         # for it to install the packages in the MAP docker image.
         # Setting output IOType to DISK only works only for leaf operators, not the case in this example.
         # When multiple models/bundles are supported, create an inference operator for each.
+        #
+        # Pertinent MONAI Bundle:
+        #   https://github.com/Project-MONAI/model-zoo/tree/dev/models/spleen_ct_segmentation, v0.3.2
+        #   https://github.com/Project-MONAI/model-zoo/tree/dev/models/pancreas_ct_dints_segmentation, v0.3
+
+        config_names = BundleConfigNames(config_names=["inference"])  # Same as the default
+
+        # This is the inference operator for the spleen_model bundle. Note the model name.
         bundle_spleen_seg_op = MonaiBundleInferenceOperator(
             input_mapping=[IOMapping("image", Image, IOType.IN_MEMORY)],
             output_mapping=[IOMapping("pred", Image, IOType.IN_MEMORY)],
-            model_name="spleen_model",
+            bundle_config_names=config_names,
+            model_name="spleen_ct",
         )
 
-        bundle_pancrea_seg_op = MonaiBundleInferenceOperator(
+        # This is the inference operator for the pancreas_ct_dints bundle. Note the model name.
+        bundle_pancreas_seg_op = MonaiBundleInferenceOperator(
             input_mapping=[IOMapping("image", Image, IOType.IN_MEMORY)],
             output_mapping=[IOMapping("pred", Image, IOType.IN_MEMORY)],
             model_name="pancreas_ct_dints",
         )
 
-        # Create DICOM Seg writer with segment label name in a string list
-        dicom_seg_writer = DICOMSegmentationWriterOperator(seg_labels=["Spleen"])
+        # Create DICOM Seg writer providing the required segment description for each segment with
+        # the actual algorithm and the pertinent organ/tissue. The segment_label, algorithm_name,
+        # and algorithm_version are of DICOM VR LO type, limited to 64 chars.
+        # https://dicom.nema.org/medical/dicom/current/output/chtml/part05/sect_6.2.html
+        #
+        # NOTE: Each generated DICOM Seg will be a dcm file with the name based on the SOP instance UID.
+
+        # Description for the Spleen seg, and the seg writer obj
+        seg_descriptions_spleen = [
+            SegmentDescription(
+                segment_label="Spleen",
+                segmented_property_category=codes.SCT.Organ,
+                segmented_property_type=codes.SCT.Spleen,
+                algorithm_name="volumetric (3D) segmentation of the spleen from CT image",
+                algorithm_family=codes.DCM.ArtificialIntelligence,
+                algorithm_version="0.3.2",
+            )
+        ]
+
+        custom_tags_spleen = {"SeriesDescription": "AI Spleen Seg for research use only. Not for clinical use."}
+        dicom_seg_writer_spleen = DICOMSegmentationWriterOperator(
+            segment_descriptions=seg_descriptions_spleen, custom_tags=custom_tags_spleen
+        )
+
+        # Description for the Pancreas seg, and the seg writer obj
+        seg_descriptions_pancreas = [
+            SegmentDescription(
+                segment_label="Pancreas",
+                segmented_property_category=codes.SCT.Organ,
+                segmented_property_type=codes.SCT.Pancreas,
+                algorithm_name="volumetric (3D) segmentation of the pancreas from CT image",
+                algorithm_family=codes.DCM.ArtificialIntelligence,
+                algorithm_version="0.3.0",
+            )
+        ]
+        custom_tags_pancreas = {"SeriesDescription": "AI Pancreas Seg for research use only. Not for clinical use."}
+
+        dicom_seg_writer_pancreas = DICOMSegmentationWriterOperator(
+            segment_descriptions=seg_descriptions_pancreas, custom_tags=custom_tags_pancreas
+        )
+
+        # NOTE: Sharp eyed readers can alreay see that the above instantiation of object can be simply parameterized.
+        #       Very true, but leaving them as if for easy reading. In fact the whole app can be parameterized for general use.
 
         # Create the processing pipeline, by specifying the upstream and downstream operators, and
         # ensuring the output from the former matches the input of the latter, in both name and type.
@@ -116,21 +174,21 @@ def compose(self):
         # Feed the input image to all inference operators
         self.add_flow(series_to_vol_op, bundle_spleen_seg_op, {"image": "image"})
         # The Pancreas CT Seg bundle requires PyTorch 1.12.0 to avoid failure to load.
-        self.add_flow(series_to_vol_op, bundle_pancrea_seg_op, {"image": "image"})
+        self.add_flow(series_to_vol_op, bundle_pancreas_seg_op, {"image": "image"})
 
         # Create DICOM Seg for one of the inference output
         # Note below the dicom_seg_writer requires two inputs, each coming from a upstream operator.
         self.add_flow(
-            series_selector_op, dicom_seg_writer, {"study_selected_series_list": "study_selected_series_list"}
+            series_selector_op, dicom_seg_writer_spleen, {"study_selected_series_list": "study_selected_series_list"}
         )
-        self.add_flow(bundle_spleen_seg_op, dicom_seg_writer, {"pred": "seg_image"})
+        self.add_flow(bundle_spleen_seg_op, dicom_seg_writer_spleen, {"pred": "seg_image"})
 
-        # Create the surface mesh STL conversion operator and add it to the app execution flow, if needed, by
-        # uncommenting the following lines.
-        stl_conversion_op = STLConversionOperator(
-            output_file="stl/pancreas_tumor.stl",
+        # Create DICOM Seg for one of the inference output
+        # Note below the dicom_seg_writer requires two inputs, each coming from a upstream operator.
+        self.add_flow(
+            series_selector_op, dicom_seg_writer_pancreas, {"study_selected_series_list": "study_selected_series_list"}
         )
-        self.add_flow(bundle_pancrea_seg_op, stl_conversion_op, {"pred": "image"})
+        self.add_flow(bundle_pancreas_seg_op, dicom_seg_writer_pancreas, {"pred": "seg_image"})
 
         logging.info(f"End {self.compose.__name__}")
 

examples/apps/ai_pancrea_seg_app/app.py

@@ -14,6 +14,7 @@
 # Required for setting SegmentDescription attributes. Direct import as this is not part of App SDK package.
 from pydicom.sr.codedict import codes
 
+import monai.deploy.core as md
 from monai.deploy.core import Application, resource
 from monai.deploy.core.domain import Image
 from monai.deploy.core.io_type import IOType
@@ -31,6 +32,7 @@
 
 
 @resource(cpu=1, gpu=1, memory="7Gi")
+@md.env(pip_packages=["torch>=1.12.0"])
 # 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 AIPancreasSegApp(Application):

examples/apps/ai_spleen_seg_app/app.py

@@ -27,8 +27,6 @@
     MonaiBundleInferenceOperator,
 )
 
-# from monai.deploy.operators.stl_conversion_operator import STLConversionOperator  # import as needed.
-
 
 @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.