MHub / GC - Add PICAI baseline model/algorithm

models/gc_picai_baseline/config/default.yml

@@ -0,0 +1,34 @@
+general:
+  data_base_dir: /app/data
+  version: 1.0
+  description: Prostate MRI classification default (dicom to json)
+
+execute:
+- FileStructureImporter
+- MhaConverter
+- PicaiBaselineRunner
+- ReportExporter
+- DataOrganizer
+
+modules:
+  FileStructureImporter:
+    input_dir: input_data
+    structures:
+      - $sid@instance/$type@dicom:mod=mr
+    import_id: sid
+
+  MhaConverter:
+    engine: panimg
+    allow_multi_input: true
+
+  ReportExporter:
+    format: compact
+    includes:
+      - data: prostate_cancer_probability
+        label: prostate_cancer_probability
+        value: value
+
+  DataOrganizer:
+    targets:
+      - json:mod=report-->[i:sid]/cspca-case-level-likelihood.json
+      - mha:mod=hm-->[i:sid]/cspca-detection-map.mha

models/gc_picai_baseline/config/mha-pipeline.yml

@@ -0,0 +1,31 @@
+general:
+  data_base_dir: /app/data
+  version: 1.0
+  description: Prostate MRI classification MHA pipeline (mha to json)
+
+execute:
+- FileStructureImporter
+- PicaiBaselineRunner
+- ReportExporter
+- DataOrganizer
+
+modules:
+  FileStructureImporter:
+    input_dir: input_data
+    structures:
+      - $sid@instance/images/transverse-adc-prostate-mri/adc.mha@mha:mod=mradc
+      - $sid/images/transverse-t2-prostate-mri/t2w.mha@mha:mod=mrt2
+      - $sid/images/transverse-hbv-prostate-mri/hbv.mha@mha:mod=mrhbv
+    import_id: sid
+
+  ReportExporter:
+    format: compact
+    includes:
+      - data: prostate_cancer_probability
+        label: prostate_cancer_probability
+        value: value
+
+  DataOrganizer:
+    targets:
+      - json:mod=report-->[i:sid]/cspca-case-level-likelihood.json
+      - mha:mod=hm-->[i:sid]/cspca-detection-map.mha

models/gc_picai_baseline/dockerfiles/Dockerfile

@@ -0,0 +1,46 @@
+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 unpacking model weights)
+RUN apt update && apt install -y --no-install-recommends git-lfs && rm -rf /var/lib/apt/lists/*
+
+# Install PICAI baseline algorithm and model weights
+#   - Git clone the algorithm repository for v2.1.1 (fixed to v2.1.1 tag)
+#   - We remove unnecessary files for a compacter docker layer
+#   - Subsequently we remove the .git directory to procuce a compacter docker layer
+RUN git clone --depth 1 --branch v2.1.1 https://github.com/DIAGNijmegen/picai_nnunet_semi_supervised_gc_algorithm.git /opt/algorithm && \
+    rm -rf /opt/algorithm/test && \
+    rm -rf /opt/algorithm/.git
+
+# Install additional PICAI 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 $2}'` && \
+    mv /opt/algorithm/nnUNetTrainerV2_focalLoss.py "$SITE_PKG/nnunet/training/network_training/nnUNet_variants/loss_function/nnUNetTrainerV2_focalLoss.py"
+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"
+RUN SITE_PKG=`pip3 show nnunet | grep "Location:" | awk '{print $2}'` && \
+    mv /opt/algorithm/nnUNetTrainerV2_Loss_FL_and_CE.py "$SITE_PKG/nnunet/training/network_training/nnUNetTrainerV2_Loss_FL_and_CE.py"
+
+# Two code edits to the __init__ method of the algorithm class in process.py to prevent some of its default behavior
+# 1. Skip forced error caused by using a different input locations than expected (we don't use the GC dirs)
+# 2. Prevent unnecessary folder creation before input directories have been set (we will set the correct directory later)
+RUN sed -i "s|file_paths = list(Path(folder).glob(scan_glob_format))|return|g" /opt/algorithm/process.py && \
+    sed -i "s|self.cspca_detection_map_path.parent.mkdir(exist_ok=True, parents=True)||g" /opt/algorithm/process.py
+
+# Import the MHub model definiton
+ARG MHUB_MODELS_REPO
+RUN buildutils/import_mhub_model.sh gc_picai_baseline ${MHUB_MODELS_REPO}
+
+# Add lobe segmentation code base to python path
+ENV PYTHONPATH="/app:/opt/algorithm"
+
+# Default entrypoint
+ENTRYPOINT ["python3", "-m", "mhubio.run"]
+CMD ["--config", "/app/models/gc_picai_baseline/config/default.yml"]

models/gc_picai_baseline/meta.json

@@ -0,0 +1,138 @@
+{
+  "id": "c5f886fb-9f54-4555-a954-da02b22d6d3f",
+  "name": "picai_baseline",
+  "title": "PI-CAI challenge baseline",
+  "summary": {
+    "description": "The PI-CAI challenge is to validate modern AI algorithms at clinically significant prostate cancer (csPCa) detection and diagnosis. This model algorithm provides the baseline for the challenge.",
+    "inputs": [
+      {
+        "label": "Prostate biparametric MRI",
+        "description": "Prostate biparametric MRI exam",
+        "format": "DICOM",
+        "modality": "MR",
+        "bodypartexamined": "Prostate",
+        "slicethickness": "",
+        "non-contrast": false,
+        "contrast": false
+      }
+    ],
+    "outputs": [
+      {
+        "type": "Prediction",
+        "valueType": "Probability",
+        "label": "Prostate cancer probability",
+        "description": "Case-level likelihood of harboring clinically significant prostate cancer, in range [0,1]",
+        "classes": []
+      },
+      {
+        "type": "Prediction",
+        "valueType": "Probability map",
+        "label": "Transverse cancer detection map",
+        "description": "Detection map of clinically significant prostate cancer lesions in 3D, where each voxel represents a floating point in range [0,1]",
+        "classes": []
+      }
+    ],
+    "model": {
+      "architecture": "3d fullres nnUNet",
+      "training": "supervised",
+      "cmpapproach": "3D"
+    },
+    "data": {
+      "training": {
+        "vol_samples": 1200
+      },
+      "evaluation": {
+        "vol_samples": 300
+      },
+      "public": false,
+      "external": false
+    }
+  },
+  "details": {
+    "name": "PI-CAI challenge baseline",
+    "version": "v2.1.1",
+    "devteam": "Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands",
+    "type": "Prediction",
+    "date": {
+      "weights": "2022-06-22",
+      "code": "2022-09-05",
+      "pub": ""
+    },
+    "cite": "",
+    "license": {
+      "code": "Apache 2.0",
+      "weights": "Apache 2.0"
+    },
+    "publications": [],
+    "github": "https://github.com/DIAGNijmegen/picai_nnunet_semi_supervised_gc_algorithm",
+    "zenodo": "",
+    "colab": "",
+    "slicer": false
+  },
+  "info": {
+    "use": {
+      "title": "Intended use",
+      "text": "Prediction of the likelihood of harboring clinically significant prostate cancer (csPCa) in prostate biparametric MRI exams.",
+      "references": [
+        {
+          "label": "PI-CAI baseline algorithm on grand-challenge",
+          "uri": "https://grand-challenge.org/algorithms/pi-cai-baseline-nnu-net-semi-supervised/"
+        }
+      ],
+      "tables": []
+    },
+    "analyses": {
+      "title": "Evaluation",
+      "text": "Patient-level diagnosis performance is evaluated using the Area Under Receiver Operating Characteristic (AUROC) metric. Lesion-level detection performance is evaluated using the Average Precision (AP) metric. Overall score used to rank each AI algorithm is the average of both task-specific metrics: Overall Ranking Score = (AP + AUROC) / 2",
+      "references": [
+        {
+          "label": "PI-CAI AI challenge details",
+          "uri": "https://pi-cai.grand-challenge.org/AI/"
+        }
+      ],
+      "tables": []
+    },
+    "evaluation": {
+      "title": "Evaluation data",
+      "text": "The test sets are two private cohorts of 100 and 1000 biparametric MRI exams respectively. The first was used to tune the algorithms in a public leaderboard, the second was used to determine the top 5 AI algorithms.",
+      "references": [
+        {
+          "label": "PI-CAI data section",
+          "uri": "https://pi-cai.grand-challenge.org/DATA/"
+        }
+      ],
+      "tables": []
+    },
+    "training": {
+      "title": "Training data",
+      "text": "For the PI-CAI a publicly available training datasets of 1500 biparametric MRI exams including 328 cases from the ProstateX challenge were made available.",
+      "references": [
+        {
+          "label": "PI-CAI publicly available training data",
+          "uri": "https://zenodo.org/record/6624726"
+        },
+        {
+          "label": "PI-CAI publicly available training data annotations",
+          "uri": "https://github.com/DIAGNijmegen/picai_labels"
+        },
+        {
+          "label": "ProstateX challenge",
+          "uri": "https://prostatex.grand-challenge.org/"
+        }
+      ],
+      "tables": []
+    },
+    "ethics": {
+      "title": "",
+      "text": "",
+      "references": [],
+      "tables": []
+    },
+    "limitations": {
+      "title": "Limitations",
+      "text": "This algorithm was developed for research purposes only.",
+      "references": [],
+      "tables": []
+    }
+  }
+}

models/gc_picai_baseline/utils/PicaiBaselineRunner.py

@@ -0,0 +1,68 @@
+"""
+---------------------------------------------------------
+Mhub / DIAG - Run Module for the PICAI baseline Algorithm
+---------------------------------------------------------
+
+---------------------------------------------------------
+Author: Sil van de Leemput
+Email:  [email protected]
+---------------------------------------------------------
+"""
+
+import json
+from pathlib import Path
+
+from mhubio.core import Instance, InstanceData, IO, Module, ValueOutput, ClassOutput, Meta
+
+# Import the PICAI Classifier algorithm class from /opt/algorithm
+from process import csPCaAlgorithm as PicaiClassifier
+
+
+@ValueOutput.Name('prostate_cancer_probability')
+@ValueOutput.Meta(Meta(key="value"))
+@ValueOutput.Label('ProstateCancerProbability')
+@ValueOutput.Type(float)
+@ValueOutput.Description('Probability of case-level prostate cancer.')
+class ProstateCancerProbability(ValueOutput):
+    pass
+
+
+class PicaiBaselineRunner(Module):
+
+    @IO.Instance()
+    @IO.Input('in_data_t2', 'mha:mod=mr:type=t2w', the='input T2 weighted prostate MR image')
+    @IO.Input('in_data_adc', 'mha:mod=mr:type=adc', the='input ADC prostate MR image')
+    @IO.Input('in_data_hbv', 'mha:mod=mr:type=hbv', the='input HBV prostate MR image')
+    @IO.Output('cancer_probability_json', 'cspca-case-level-likelihood.json', "json", bundle='model', the='output JSON file with PICAI baseline prostate cancer probability')
+    @IO.Output('cancer_detection_heatmap', 'cspca_detection_map.mha', "mha:mod=hm", bundle='model', the='output heatmap indicating prostate cancer probability')
+    @IO.OutputData('cancer_probability', ProstateCancerProbability, the='PICAI baseline prostate cancer probability')
+    def task(self, instance: Instance, in_data_t2: InstanceData, in_data_adc: InstanceData, in_data_hbv: InstanceData, cancer_probability_json: InstanceData, cancer_detection_heatmap: InstanceData, cancer_probability: ProstateCancerProbability) -> None:
+        # Initialize classifier object
+        classifier = PicaiClassifier()
+
+        # Specify input files (the order is important!)
+        classifier.scan_paths = [
+            Path(in_data_t2.abspath),
+            Path(in_data_adc.abspath),
+            Path(in_data_hbv.abspath),
+        ]
+
+        # Specify output files
+        classifier.cspca_detection_map_path = Path(cancer_detection_heatmap.abspath)
+        classifier.case_confidence_path = Path(cancer_probability_json.abspath)
+
+        # Run the classifier on the input images
+        classifier.process()
+
+        # Extract cancer probability value from cancer_probability_file
+        if not Path(cancer_probability_json.abspath).is_file():
+            raise FileNotFoundError(f"Output file {cancer_probability_json.abspath} could not be found!")
+
+        with open(cancer_probability_json.abspath, "r") as f:
+            cancer_prob = float(json.load(f))
+
+        if not (isinstance(cancer_prob, (float, int)) and (0.0 <= cancer_prob <= 1.0)):
+            raise ValueError(f"Cancer probability value should be a probability value, found: {cancer_prob}")
+
+        # Output the predicted values
+        cancer_probability.value = cancer_prob

models/gc_picai_baseline/utils/__init__.py

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