MHub / GC - Add GC nnUNet Pancreas model

models/gc_nnunet_pancreas/__init__.py

@@ -0,0 +1 @@
+from .utils import *

models/gc_nnunet_pancreas/config/default.yml

@@ -0,0 +1,35 @@
+general:
+  version: 1.0
+  data_base_dir: /app/data
+  description: base configuration for GC NNUnet Pancreas model (dicom to dicom)
+
+execute:
+- DicomImporter
+- MhaConverter
+- GCNNUnetPancreasRunner
+- DsegConverter
+- DataOrganizer
+
+modules:
+  DicomImporter:
+    source_dir: input_data
+    import_dir: sorted_data
+    sort_data: true
+    meta: 
+      mod: '%Modality'
+
+  MhaConverter:
+    engine: panimg
+    targets: [dicom:mod=ct]
+
+  DsegConverter:
+    model_name: 'GC NNUnet Pancreas'
+    source_segs: ['mha:mod=seg']
+    target_dicom: dicom:mod=ct
+    skip_empty_slices: True
+
+  DataOrganizer:
+    targets:
+    - mha:mod=heatmap-->[i:sid]/nnunet_pancreas_heatmap.mha
+    - mha:mod=seg-->[i:sid]/nnunet_pancreas.seg.mha
+    - dicomseg:mod=seg-->[i:sid]/nnunet_pancreas.seg.dcm

models/gc_nnunet_pancreas/dockerfiles/Dockerfile

@@ -0,0 +1,53 @@
+FROM mhubai/base:latest
+
+# Specify/override authors label
+LABEL authors="[email protected]"
+
+# Install PyTorch 2.0.1 (CUDA enabled)
+RUN pip3 install --no-cache-dir torch==2.0.1+cu118 -f https://download.pytorch.org/whl/torch_stable.html
+
+# Install git-lfs (required for downloading the model weights)
+RUN apt update && \
+    apt install -y --no-install-recommends git-lfs && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install the model weights and the algorithm files
+#  * Pull algorithm from repo into /opt/algorithm (main branch, commit e4f4008c6e18e60a79f693448562a340a9252aa8)
+#  * Remove .git folder to keep docker layer small
+#  * Replace input images path in process.py with an existing folder to avoid errors
+#  * Add specific data types and compression options to output data structures in process.py to reduce generated output footprint
+RUN git clone https://github.com/DIAGNijmegen/CE-CT_PDAC_AutomaticDetection_nnUnet.git /opt/algorithm && \
+    cd /opt/algorithm && \
+    git reset --hard e4f4008c6e18e60a79f693448562a340a9252aa8 && \
+    rm -rf /opt/algorithm/.git && \
+    sed -i 's/Path("\/input\/images\/")/Path("\/app")/g' /opt/algorithm/process.py && \
+    sed -i 's/pred_2_np  = sitk\.GetArrayFromImage(pred_2_nii)/pred_2_np  = sitk\.GetArrayFromImage(pred_2_nii)\.astype(np\.uint8)/g' /opt/algorithm/process.py && \
+    sed -i 's/pm_image = np\.zeros(image_np\.shape)/pm_image = np\.zeros(image_np\.shape, dtype=np\.float32)/g' /opt/algorithm/process.py && \
+    sed -i 's/segmentation_np = np\.zeros(image_np\.shape)/segmentation_np = np\.zeros(image_np\.shape, dtype=np\.uint8)/g' /opt/algorithm/process.py && \
+    sed -i 's/sitk\.WriteImage(segmentation_image, str(self\.segmentation))/sitk\.WriteImage(segmentation_image, str(self\.segmentation), True)/g' /opt/algorithm/process.py && \
+    sed -i 's/sitk\.WriteImage(pred_itk_resampled, str(self\.heatmap))/sitk\.WriteImage(pred_itk_resampled, str(self\.heatmap), True)/g' /opt/algorithm/process.py
+
+# Set this environment variable as a shortcut to avoid nnunet 1.7.0 crashing the build
+# by pulling sklearn instead of scikit-learn
+# N.B. this is a known issue:
+# https://github.com/MIC-DKFZ/nnUNet/issues/1281
+# https://github.com/MIC-DKFZ/nnUNet/pull/1209
+ENV SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL=True
+
+# Install nnUNet 1.7.0 and other requirements
+RUN pip3 install --no-cache-dir -r /opt/algorithm/requirements.txt
+
+# Extend the nnUNet installation with custom trainers
+RUN SITE_PKG=`pip3 show nnunet | grep "Location:" | awk '{print $2}'` && \
+    mv /opt/algorithm/nnUNetTrainerV2_Loss_CE_checkpoints.py "$SITE_PKG/nnunet/training/network_training/nnUNetTrainerV2_Loss_CE_checkpoints.py"
+
+# Import the MHub model definiton
+ARG MHUB_MODELS_REPO
+RUN buildutils/import_mhub_model.sh gc_nnunet_pancreas ${MHUB_MODELS_REPO}
+
+# Add algorithm files to python path
+ENV PYTHONPATH=/opt/algorithm:/app
+
+# Configure main entrypoint
+ENTRYPOINT ["python3", "-m", "mhubio.run"]
+CMD ["--config", "/app/models/gc_nnunet_pancreas/config/default.yml"]

models/gc_nnunet_pancreas/meta.json

@@ -0,0 +1,129 @@
+{
+  "id": "bf7ae4bb-c6f5-4b1e-89aa-a8de246def57",
+  "name": "pdac_detection_in_ct",
+  "title": "Pancreatic Ductal Adenocarcinoma Detection in CT",
+  "summary": {
+    "description": "This algorithm produces a tumor likelihood heatmap for the presence of pancreatic ductal adenocarcinoma (PDAC) in an input venous-phase contrast-enhanced computed tomography scan (CECT). Additionally, the algorithm provides the segmentation of multiple surrounding anatomical structures such as the pancreatic duct, common bile duct, veins and arteries. The heatmap and segmentations are resampled to the same spatial resolution and physical dimensions as the input CECT image for easier visualisation.",
+    "inputs": [
+      {
+        "label": "Venous phase CT scan",
+        "description": "A contrast-enhanced CT scan in the venous phase and axial reconstruction",
+        "format": "DICOM",
+        "modality": "CT",
+        "bodypartexamined": "Abdomen",
+        "slicethickness": "2.5mm",
+        "non-contrast": false,
+        "contrast": false
+      }
+    ],
+    "outputs": [
+      {
+        "type": "Segmentation",
+        "classes": [
+          "veins",
+          "arteries",
+          "pancreas",
+          "pancreatic duct",
+          "bile duct",
+          "cysts",
+          "renal vein"
+        ]
+      },
+      {
+        "type": "Prediction",
+        "valueType": "number",
+        "label": "Pancreatic tumor likelihood",
+        "description": "Pancreatic tumor likelihood map with values between 0 and 1",
+        "classes": []
+      }
+    ],
+    "model": {
+      "architecture": "nnUnet ",
+      "training": "supervised",
+      "cmpapproach": "3D"
+    },
+    "data": {
+      "training": {
+        "vol_samples": 242
+      },
+      "evaluation": {
+        "vol_samples": 361
+      },
+      "public": true,
+      "external": false
+    }
+  },
+  "details": {
+    "name": "Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography",
+    "version": "",
+    "devteam": "DIAGNijmegen (Diagnostic Image Analysis Group, Radboud UMC, The Netherlands)",
+    "type": "The models were developed using nnUnet. All models employed a 3D U-Net as the base architecture and were trained for 250.000 training steps with five-fold cross-validation.",
+    "date": {
+      "weights": "2023-06-28",
+      "code": "2022-07-19",
+      "pub": "2022-01-13"
+    },
+    "cite": "Alves N, Schuurmans M, Litjens G, Bosma JS, Hermans J, Huisman H. Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography. Cancers (Basel). 2022 Jan 13;14(2):376. doi: 10.3390/cancers14020376. PMID: 35053538; PMCID: PMC8774174.",
+    "license": {
+      "code": "Apache 2.0",
+      "weights": "Apache 2.0"
+    },
+    "publications": [
+      {
+        "title": "Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography ",
+        "uri": "https://www.mdpi.com/2072-6694/14/2/376"
+      }
+    ],
+    "github": "https://github.com/DIAGNijmegen/CE-CT_PDAC_AutomaticDetection_nnUnet",
+    "zenodo": "",
+    "colab": "",
+    "slicer": false
+  },
+  "info": {
+    "use": {
+      "title": "Intended Use",
+      "text": "This algorithm is intended to be used only on venous-phase CECT examinations of patients with clinical suspicion of PDAC. This algorithm should not be used in different patient demographics.",
+      "references": [],
+      "tables": []
+    },
+    "analyses": {
+      "title": "Analysis",
+      "text": "The study evaluated a medical model's performance for tumor detection by analyzing receiver operating characteristic (ROC) and free-response receiver operating characteristic (FROC) curves, assessing both tumor presence and lesion localization, and compared three configurations using statistical tests and ensemble modeling.",
+      "references": [],
+      "tables": []
+    },
+    "evaluation": {
+      "title": "Evaluation Data",
+      "text": "This framework was tested in an independent, external cohort consisting of two publicly available datasets.",
+      "references": [
+        {
+          "label": "The Medical Segmentation Decathlon pancreas dataset (training portion) consisting of 281 patients with pancreatic malignancies (including lesions in the head, neck, body, and tail of the pancreas) and voxel-level annotations for the pancreas and lesion.",
+          "uri": "http://medicaldecathlon.com/"
+        },
+        {
+          "label": "The Cancer Imaging Archive dataset from the US National Institutes of Health Clinical Center, containing 80 patients with normal pancreas and respective voxel-level annotations.",
+          "uri": "https://wiki.cancerimagingarchive.net/display/Public/Pancreas-CT"
+        }
+      ],
+      "tables": []
+    },
+    "training": {
+      "title": "Training data",
+      "text": "CE-CT scans in the portal venous phase from 119 patients with pathology-proven PDAC in the pancreatic head (PDAC cohort) and 123 patients with normal pancreas (non-PDAC cohort), acquired between 1 January 2013 and 1 June 2020, were selected for model development.",
+      "references": [],
+      "tables": []
+    },
+    "ethics": {
+      "title": "",
+      "text": "",
+      "references": [],
+      "tables": []
+    },
+    "limitations": {
+      "title": "Before using this model",
+      "text": "Test the model retrospectively and prospectively on a diagnostic cohort that reflects the target population that the model will be used upon to confirm the validity of the model within a local setting.",
+      "references": [],
+      "tables": []
+    }
+  }
+}

models/gc_nnunet_pancreas/utils/GCNNUnetPancreasRunner.py

@@ -0,0 +1,40 @@
+"""
+-----------------------------------------------------------
+GC / MHub - Run Module for the GC NNUnet Pancreas Algorithm
+-----------------------------------------------------------
+
+-----------------------------------------------------------
+Author: Sil van de Leemput
+Email:  [email protected]
+-----------------------------------------------------------
+"""
+
+from mhubio.core import Module, Instance, InstanceData, DataType, Meta, IO
+
+from pathlib import Path
+import SimpleITK
+import numpy as np
+import sys
+
+
+CLI_PATH = Path(__file__).parent / "cli.py"
+
+
+class GCNNUnetPancreasRunner(Module):
+    @IO.Instance()
+    @IO.Input('in_data', 'mha:mod=ct', the="input data")
+    @IO.Output('heatmap', 'heatmap.mha', 'mha:mod=heatmap:model=GCNNUnetPancreas', data="in_data",
+               the="heatmap of the pancreatic tumor likelihood")
+    @IO.Output('segmentation', 'segmentation.mha', 'mha:mod=seg:model=GCNNUnetPancreas:roi=VEIN,ARTERY,PANCREAS,PANCREATIC_DUCT,BILE_DUCT,PANCREAS+CYST,RENAL_VEIN', data="in_data",
+               the="original segmentation of the pancreas, with the following classes: "
+                   "0-background, 1-veins, 2-arteries, 3-pancreas, 4-pancreatic duct, 5-bile duct, 6-cysts, 7-renal vein")
+    def task(self, instance: Instance, in_data: InstanceData, heatmap: InstanceData, segmentation: InstanceData, **kwargs) -> None:
+        # Call the PDAC CLI
+        cmd = [
+            sys.executable,
+            str(CLI_PATH),
+            in_data.abspath,
+            heatmap.abspath,
+            segmentation.abspath
+        ]
+        self.subprocess(cmd, text=True)

models/gc_nnunet_pancreas/utils/__init__.py

@@ -0,0 +1 @@
+from .GCNNUnetPancreasRunner import *

models/gc_nnunet_pancreas/utils/cli.py

@@ -0,0 +1,57 @@
+"""
+----------------------------------------------------
+GC / MHub - CLI for the GC nnUnet Pancreas Algorithm
+----------------------------------------------------
+
+----------------------------------------------------
+Author: Sil van de Leemput
+Email:  [email protected]
+----------------------------------------------------
+"""
+import argparse
+from pathlib import Path
+
+# Import the algorithm pipeline class from the CE-CT_PDAC_AutomaticDetection_nnUnet repository
+from process import PDACDetectionContainer
+
+
+def run_pdac_detection(
+    input_ct_image: Path, output_heatmap: Path, output_segmentation: Path
+):
+    # Configure the algorithm pipeline class and run it
+    algorithm = PDACDetectionContainer()
+    algorithm.ct_image = str(input_ct_image)  # set as str not Path
+    algorithm.heatmap = output_heatmap
+    algorithm.segmentation = output_segmentation
+    algorithm.process()
+
+
+def run_pdac_detection_cli():
+    parser = argparse.ArgumentParser("CLI for the GC nnUNet Pancreas Algorithm")
+    parser.add_argument(
+        "input_ct_image",
+        type=str,
+        help="input CT scan (MHA)"
+    )
+    parser.add_argument(
+        "output_heatmap",
+        type=str,
+        help="heatmap of the pancreatic tumor likelihood (MHA)",
+    )
+    parser.add_argument(
+        "output_segmentation",
+        type=str,
+        help="segmentation map of the pancreas (MHA), with the following classes: "
+        "0-background, 1-veins, 2-arteries, 3-pancreas, 4-pancreatic duct, 5-bile duct, "
+        "6-cysts, 7-renal vein",
+    )
+    args = parser.parse_args()
+    run_pdac_detection(
+        input_ct_image=Path(args.input_ct_image),
+        output_heatmap=Path(args.output_heatmap),
+        output_segmentation=Path(args.output_segmentation),
+    )
+
+
+if __name__ == "__main__":
+    run_pdac_detection_cli()