From 1fa6d724374fc0f13b479a5cfc1f2d6676242129 Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Thu, 12 Oct 2023 13:42:57 +0200
Subject: [PATCH 01/15] initial functional implementation of the PICAI baseline
 algorithm model

---
 models/gc_picai_baseline/config/default.yml   | 35 ++++++++++
 .../gc_picai_baseline/config/mha-pipeline.yml | 31 +++++++++
 .../gc_picai_baseline/dockerfiles/Dockerfile  | 51 ++++++++++++++
 .../utils/PicaiBaselineRunner.py              | 68 +++++++++++++++++++
 models/gc_picai_baseline/utils/__init__.py    |  1 +
 5 files changed, 186 insertions(+)
 create mode 100644 models/gc_picai_baseline/config/default.yml
 create mode 100644 models/gc_picai_baseline/config/mha-pipeline.yml
 create mode 100644 models/gc_picai_baseline/dockerfiles/Dockerfile
 create mode 100644 models/gc_picai_baseline/utils/PicaiBaselineRunner.py
 create mode 100644 models/gc_picai_baseline/utils/__init__.py

diff --git a/models/gc_picai_baseline/config/default.yml b/models/gc_picai_baseline/config/default.yml
new file mode 100644
index 00000000..c86566be
--- /dev/null
+++ b/models/gc_picai_baseline/config/default.yml
@@ -0,0 +1,35 @@
+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/images/transverse-adc-prostate-mri@dicom:mod=mradc
+      - $sid/images/transverse-t2-prostate-mri@dicom:mod=mrt2
+      - $sid/images/transverse-hbv-prostate-mri@dicom:mod=mrhbv
+    import_id: sid
+
+  MhaConverter:
+    engine: panimg
+
+  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
diff --git a/models/gc_picai_baseline/config/mha-pipeline.yml b/models/gc_picai_baseline/config/mha-pipeline.yml
new file mode 100644
index 00000000..f70fac4b
--- /dev/null
+++ b/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
diff --git a/models/gc_picai_baseline/dockerfiles/Dockerfile b/models/gc_picai_baseline/dockerfiles/Dockerfile
new file mode 100644
index 00000000..a1bff797
--- /dev/null
+++ b/models/gc_picai_baseline/dockerfiles/Dockerfile
@@ -0,0 +1,51 @@
+# Specify the base image for the environment
+FROM mhubai/base:latest
+
+# Specify/override authors label
+LABEL authors="sil.vandeleemput@radboudumc.nl"
+
+# 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
+
+# FIXME: temporary fix waiting for the latest base image update
+# Clone the main branch of MHubAI/models
+#RUN git stash \
+#    && git fetch https://github.com/MHubAI/models.git main \
+#    && git merge FETCH_HEAD \
+#    && git sparse-checkout set "models/gc_picai_baseline" \
+#    && git fetch https://github.com/MHubAI/models.git main
+
+# 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"]
diff --git a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
new file mode 100644
index 00000000..62b88e30
--- /dev/null
+++ b/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:  sil.vandeleemput@radboudumc.nl
+---------------------------------------------------------
+"""
+
+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=mrt2', the='input T2 weighted prostate MR image')
+    @IO.Input('in_data_adc', 'mha:mod=mradc', the='input ADC prostate MR image')
+    @IO.Input('in_data_hbv', 'mha:mod=mrhbv', 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
diff --git a/models/gc_picai_baseline/utils/__init__.py b/models/gc_picai_baseline/utils/__init__.py
new file mode 100644
index 00000000..a0ec22bc
--- /dev/null
+++ b/models/gc_picai_baseline/utils/__init__.py
@@ -0,0 +1 @@
+from .PicaiBaselineRunner import *

From 954b4a2c0ced7a903a5de29a599164fbdc5ceacc Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Tue, 24 Oct 2023 15:13:10 +0200
Subject: [PATCH 02/15] add meta.json

---
 models/gc_picai_baseline/meta.json | 133 +++++++++++++++++++++++++++++
 1 file changed, 133 insertions(+)
 create mode 100644 models/gc_picai_baseline/meta.json

diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
new file mode 100644
index 00000000..312743c5
--- /dev/null
+++ b/models/gc_picai_baseline/meta.json
@@ -0,0 +1,133 @@
+{
+  "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": [],
+      "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": []
+    }
+  }
+}
\ No newline at end of file

From 47ce41819b87bf6bb0833defbc60505a3d2e243a Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Mon, 6 Nov 2023 13:51:42 +0100
Subject: [PATCH 03/15] changed input structure and added allow_multi_input on
 MHAConverter

---
 models/gc_picai_baseline/config/default.yml           | 5 ++---
 models/gc_picai_baseline/utils/PicaiBaselineRunner.py | 6 +++---
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/models/gc_picai_baseline/config/default.yml b/models/gc_picai_baseline/config/default.yml
index c86566be..fe257f9d 100644
--- a/models/gc_picai_baseline/config/default.yml
+++ b/models/gc_picai_baseline/config/default.yml
@@ -14,13 +14,12 @@ modules:
   FileStructureImporter:
     input_dir: input_data
     structures:
-      - $sid@instance/images/transverse-adc-prostate-mri@dicom:mod=mradc
-      - $sid/images/transverse-t2-prostate-mri@dicom:mod=mrt2
-      - $sid/images/transverse-hbv-prostate-mri@dicom:mod=mrhbv
+      - $sid@instance/$type@dicom:mod=mr
     import_id: sid
 
   MhaConverter:
     engine: panimg
+    allow_multi_input: true
 
   ReportExporter:
     format: compact
diff --git a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
index 62b88e30..d4a122f2 100644
--- a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
+++ b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
@@ -30,9 +30,9 @@ class ProstateCancerProbability(ValueOutput):
 class PicaiBaselineRunner(Module):
 
     @IO.Instance()
-    @IO.Input('in_data_t2', 'mha:mod=mrt2', the='input T2 weighted prostate MR image')
-    @IO.Input('in_data_adc', 'mha:mod=mradc', the='input ADC prostate MR image')
-    @IO.Input('in_data_hbv', 'mha:mod=mrhbv', the='input HBV prostate MR image')
+    @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')

From 0d19c7c5b907b2be6a1ef935fe9e2c01fff8fda8 Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Wed, 15 Nov 2023 13:06:34 +0100
Subject: [PATCH 04/15] add link to baseline algorithm on grand-challenge in
 meta.json

---
 models/gc_picai_baseline/meta.json | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
index 312743c5..59aab4d2 100644
--- a/models/gc_picai_baseline/meta.json
+++ b/models/gc_picai_baseline/meta.json
@@ -73,7 +73,12 @@
     "use": {
       "title": "Intended use",
       "text": "Prediction of the likelihood of harboring clinically significant prostate cancer (csPCa) in prostate biparametric MRI exams.",
-      "references": [],
+      "references": [
+        {
+          "label": "PI-CAI baseline algorithm on grand-challenge",
+          "uri": "https://grand-challenge.org/algorithms/pi-cai-baseline-nnu-net-semi-supervised/"
+        }
+      ],
       "tables": []
     },
     "analyses": {

From 483bf910ad845974d79520b2bf69dd37448f2583 Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Thu, 23 Nov 2023 17:03:05 +0100
Subject: [PATCH 05/15] removed first line comment and added mhub model
 definition import lines

---
 models/gc_picai_baseline/dockerfiles/Dockerfile | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/models/gc_picai_baseline/dockerfiles/Dockerfile b/models/gc_picai_baseline/dockerfiles/Dockerfile
index a1bff797..84a1c607 100644
--- a/models/gc_picai_baseline/dockerfiles/Dockerfile
+++ b/models/gc_picai_baseline/dockerfiles/Dockerfile
@@ -1,4 +1,3 @@
-# Specify the base image for the environment
 FROM mhubai/base:latest
 
 # Specify/override authors label
@@ -35,13 +34,9 @@ RUN SITE_PKG=`pip3 show nnunet | grep "Location:" | awk '{print $2}'` && \
 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
 
-# FIXME: temporary fix waiting for the latest base image update
-# Clone the main branch of MHubAI/models
-#RUN git stash \
-#    && git fetch https://github.com/MHubAI/models.git main \
-#    && git merge FETCH_HEAD \
-#    && git sparse-checkout set "models/gc_picai_baseline" \
-#    && git fetch https://github.com/MHubAI/models.git main
+# 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"

From 4abafd57479aa8d5b562355e2af83f8da8c9f081 Mon Sep 17 00:00:00 2001
From: Miriam Groeneveld <miriam.groeneveld.diag@gmail.com>
Date: Thu, 30 Nov 2023 14:54:05 +0100
Subject: [PATCH 06/15] PR comments on mata.json

---
 models/gc_picai_baseline/config/default.yml   |  4 +-
 .../gc_picai_baseline/config/mha-pipeline.yml |  4 +-
 models/gc_picai_baseline/meta.json            | 83 ++++++++++++++-----
 .../utils/PicaiBaselineRunner.py              | 35 ++++----
 4 files changed, 83 insertions(+), 43 deletions(-)

diff --git a/models/gc_picai_baseline/config/default.yml b/models/gc_picai_baseline/config/default.yml
index fe257f9d..c86cac07 100644
--- a/models/gc_picai_baseline/config/default.yml
+++ b/models/gc_picai_baseline/config/default.yml
@@ -24,8 +24,8 @@ modules:
   ReportExporter:
     format: compact
     includes:
-      - data: prostate_cancer_probability
-        label: prostate_cancer_probability
+      - data: prostate_cancer_likelihood
+        label: prostate_cancer_likelihood
         value: value
 
   DataOrganizer:
diff --git a/models/gc_picai_baseline/config/mha-pipeline.yml b/models/gc_picai_baseline/config/mha-pipeline.yml
index f70fac4b..f20d5abc 100644
--- a/models/gc_picai_baseline/config/mha-pipeline.yml
+++ b/models/gc_picai_baseline/config/mha-pipeline.yml
@@ -21,8 +21,8 @@ modules:
   ReportExporter:
     format: compact
     includes:
-      - data: prostate_cancer_probability
-        label: prostate_cancer_probability
+      - data: prostate_cancer_likelihood
+        label: prostate_cancer_likelihood
         value: value
 
   DataOrganizer:
diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
index 59aab4d2..c83ce46d 100644
--- a/models/gc_picai_baseline/meta.json
+++ b/models/gc_picai_baseline/meta.json
@@ -3,11 +3,31 @@
   "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.",
+    "description": "This algorithm predicts a detection map for the likelihood of clinically significant prostate cancer (csPCa) using biparametric MRI (bpMRI). The algorithm ensembles 5-fold cross-validation models that were trained on the PI-CAI: Public Training and Development Dataset v2.0. The detection map is at the same spatial resolution and physical dimensions as the input axial T2-weighted image.",
     "inputs": [
       {
-        "label": "Prostate biparametric MRI",
-        "description": "Prostate biparametric MRI exam",
+        "label": "Transverse T2-weighted Prostate biparametric MRI",
+        "description": " Transverse T2-weighted Prostate biparametric MRI exam",
+        "format": "DICOM",
+        "modality": "MR",
+        "bodypartexamined": "Prostate",
+        "slicethickness": "",
+        "non-contrast": false,
+        "contrast": false
+      },
+      {
+        "label": "High b-value diffusion-weighted maps",
+        "description": "High b-value diffusion-weighted maps, with b-value of 1400 or 2000, either acquired or vendor-calculated.",
+        "format": "DICOM",
+        "modality": "MR",
+        "bodypartexamined": "Prostate",
+        "slicethickness": "",
+        "non-contrast": false,
+        "contrast": false
+      },
+      {
+        "label": "ADC map",
+        "description": "ADC map",
         "format": "DICOM",
         "modality": "MR",
         "bodypartexamined": "Prostate",
@@ -19,14 +39,14 @@
     "outputs": [
       {
         "type": "Prediction",
-        "valueType": "Probability",
-        "label": "Prostate cancer probability",
+        "valueType": "Likelihood",
+        "label": "Prostate cancer likelihood",
         "description": "Case-level likelihood of harboring clinically significant prostate cancer, in range [0,1]",
         "classes": []
       },
       {
         "type": "Prediction",
-        "valueType": "Probability map",
+        "valueType": "Likelihood 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": []
@@ -34,15 +54,15 @@
     ],
     "model": {
       "architecture": "3d fullres nnUNet",
-      "training": "supervised",
+      "training": "semi-supervised",
       "cmpapproach": "3D"
     },
     "data": {
       "training": {
-        "vol_samples": 1200
+        "vol_samples": 1500
       },
       "evaluation": {
-        "vol_samples": 300
+        "vol_samples": 1000
       },
       "public": false,
       "external": false
@@ -61,9 +81,18 @@
     "cite": "",
     "license": {
       "code": "Apache 2.0",
-      "weights": "Apache 2.0"
+      "weights": "CC-BY-NC-4.0"
     },
-    "publications": [],
+    "publications": [
+      {
+        "uri": "https://doi.org/10.5281/zenodo.6667655",
+        "title": "Artificial Intelligence and Radiologists at Prostate Cancer Detection in MRI: The PI-CAI Challenge (Study Protocol)"
+      },
+      {
+        "uri": "https://pubs.rsna.org/doi/10.1148/ryai.230031",
+        "title": "Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning–based Prostate Cancer Detection Using Biparametric MRI"
+      }
+    ],
     "github": "https://github.com/DIAGNijmegen/picai_nnunet_semi_supervised_gc_algorithm",
     "zenodo": "",
     "colab": "",
@@ -72,7 +101,7 @@
   "info": {
     "use": {
       "title": "Intended use",
-      "text": "Prediction of the likelihood of harboring clinically significant prostate cancer (csPCa) in prostate biparametric MRI exams.",
+      "text": "This algorithm is a deep learning-based detection/diagnosis model, which ensembles 5 independent nnU-Net models (5-fold cross-validation). To predict the likelihood of harboring clinically significant prostate cancer (csPCa), the transversal T2-weighted, apparent diffusion coefficient (ADC) and high b-value diffusion maps are required. The input sequences should be co-registered or aligned reasonably well and the prostate gland should be localized within a volume of 460 cm³ from the centre coordinate. To train these models, a total of 1500 prostate biparametric MRI (bpMRI) scans paired with human-annotated or AI-derived ISUP ≥ 2 delineations were used.",
       "references": [
         {
           "label": "PI-CAI baseline algorithm on grand-challenge",
@@ -83,18 +112,30 @@
     },
     "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",
+      "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.",
       "references": [
         {
           "label": "PI-CAI AI challenge details",
           "uri": "https://pi-cai.grand-challenge.org/AI/"
+        },
+        {
+          "label": "PI-CAI baseline algorithm evaluation results on grand-challenge.",
+          "uri": "https://pi-cai.grand-challenge.org/evaluation/fe187cdb-cb61-4cbb-ab63-2de483a52d60/"
         }
       ],
-      "tables": []
+      "tables": [
+        {
+          "label": "Evaluation results on the PI-CAI testing cohort of 1000 cases.",
+          "entries": {
+              "AUROC": "0.865",
+              "AP": "0.576"
+          }
+        }
+      ]
     },
     "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.",
+      "text": "The PI-CAI Hidden Testing Cohort (1000 cases) includes internal testing data (unseen cases from seen centers) and external testing data (unseen cases from an unseen center).",
       "references": [
         {
           "label": "PI-CAI data section",
@@ -105,19 +146,19 @@
     },
     "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.",
+      "text": "The publicly available PI-CAI training and development dataset of 1500 biparametric MRI exams was used for training [1]. AI-derived annotations were created for cases without manual annotations [2]. This model was trained using a custom preprocessing step followed by the standard nnU-Net pipeline. The default nnU-Net loss-function was changed to Cross-Entropy + Focal loss. [3]",
       "references": [
         {
-          "label": "PI-CAI publicly available training data",
+          "label": "PI-CAI publicly available training and development dataset",
           "uri": "https://zenodo.org/record/6624726"
         },
         {
-          "label": "PI-CAI publicly available training data annotations",
-          "uri": "https://github.com/DIAGNijmegen/picai_labels"
+          "label": "Method to obtain AI-derived annotations",
+          "uri": "https://fastmri.eu/research/bosma22a.html"
         },
         {
-          "label": "ProstateX challenge",
-          "uri": "https://prostatex.grand-challenge.org/"
+          "label": "Detailed description of training method",
+          "uri": "https://github.com/DIAGNijmegen/picai_baseline/blob/main/nnunet_baseline.md"
         }
       ],
       "tables": []
diff --git a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
index d4a122f2..4f1d05ca 100644
--- a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
+++ b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
@@ -18,12 +18,11 @@
 from process import csPCaAlgorithm as PicaiClassifier
 
 
-@ValueOutput.Name('prostate_cancer_probability')
-@ValueOutput.Meta(Meta(key="value"))
-@ValueOutput.Label('ProstateCancerProbability')
+@ValueOutput.Name('prostate_cancer_likelihood')
+@ValueOutput.Label('ProstateCancerLikelihood')
 @ValueOutput.Type(float)
-@ValueOutput.Description('Probability of case-level prostate cancer.')
-class ProstateCancerProbability(ValueOutput):
+@ValueOutput.Description('Likelihood of case-level prostate cancer.')
+class ProstateCancerLikelihood(ValueOutput):
     pass
 
 
@@ -33,10 +32,10 @@ class PicaiBaselineRunner(Module):
     @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:
+    @IO.Output('cancer_likelihood_json', 'cspca-case-level-likelihood.json', "json", bundle='model', the='output JSON file with PICAI baseline prostate cancer likelihood')
+    @IO.Output('cancer_detection_heatmap', 'cspca_detection_map.mha', "mha:mod=hm", bundle='model', the='output heatmap indicating prostate cancer likelihood')
+    @IO.OutputData('cancer_likelihood', ProstateCancerLikelihood, the='PICAI baseline prostate cancer likelihood')
+    def task(self, instance: Instance, in_data_t2: InstanceData, in_data_adc: InstanceData, in_data_hbv: InstanceData, cancer_likelihood_json: InstanceData, cancer_detection_heatmap: InstanceData, cancer_likelihood: ProstateCancerLikelihood) -> None:
         # Initialize classifier object
         classifier = PicaiClassifier()
 
@@ -49,20 +48,20 @@ def task(self, instance: Instance, in_data_t2: InstanceData, in_data_adc: Instan
 
         # Specify output files
         classifier.cspca_detection_map_path = Path(cancer_detection_heatmap.abspath)
-        classifier.case_confidence_path = Path(cancer_probability_json.abspath)
+        classifier.case_confidence_path = Path(cancer_likelihood_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!")
+        # Extract cancer likelihood value from cancer_likelihood_file
+        if not Path(cancer_likelihood_json.abspath).is_file():
+            raise FileNotFoundError(f"Output file {cancer_likelihood_json.abspath} could not be found!")
 
-        with open(cancer_probability_json.abspath, "r") as f:
-            cancer_prob = float(json.load(f))
+        with open(cancer_likelihood_json.abspath, "r") as f:
+            cancer_lh = 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}")
+        if not (isinstance(cancer_lh, (float, int)) and (0.0 <= cancer_lh <= 1.0)):
+            raise ValueError(f"Cancer likelihood value should be between 0 and 1, found: {cancer_lh}")
 
         # Output the predicted values
-        cancer_probability.value = cancer_prob
+        cancer_likelihood.value = cancer_lh

From 8d7a6aa516cf22498aacaa0e55f0792e797f7ebe Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Thu, 30 Nov 2023 16:08:13 +0100
Subject: [PATCH 07/15] Dockerfile - minor cleanup and add sklearn deprecation
 environment flag for nnunet==1.7.0

---
 models/gc_picai_baseline/dockerfiles/Dockerfile | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/models/gc_picai_baseline/dockerfiles/Dockerfile b/models/gc_picai_baseline/dockerfiles/Dockerfile
index 84a1c607..a91146aa 100644
--- a/models/gc_picai_baseline/dockerfiles/Dockerfile
+++ b/models/gc_picai_baseline/dockerfiles/Dockerfile
@@ -7,7 +7,9 @@ LABEL authors="sil.vandeleemput@radboudumc.nl"
 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/*
+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)
@@ -17,6 +19,13 @@ RUN git clone --depth 1 --branch v2.1.1 https://github.com/DIAGNijmegen/picai_nn
     rm -rf /opt/algorithm/test && \
     rm -rf /opt/algorithm/.git
 
+# 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 additional PICAI requirements
 RUN pip3 install --no-cache-dir -r /opt/algorithm/requirements.txt
 

From 3b72e0e31002762da35f6f944debab1b787c80ca Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Thu, 30 Nov 2023 16:12:34 +0100
Subject: [PATCH 08/15] meta.json - add citation to cite field

---
 models/gc_picai_baseline/meta.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
index c83ce46d..b15c65ac 100644
--- a/models/gc_picai_baseline/meta.json
+++ b/models/gc_picai_baseline/meta.json
@@ -78,7 +78,7 @@
       "code": "2022-09-05",
       "pub": ""
     },
-    "cite": "",
+    "cite": "J. S. Bosma, A. Saha, M. Hosseinzadeh, I. Slootweg, M. de Rooij, and H. Huisman, \"Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning–based Prostate Cancer Detection Using Biparametric MRI\", Radiology: Artificial Intelligence, 230031, 2023. DOI: 10.1148/ryai.230031",
     "license": {
       "code": "Apache 2.0",
       "weights": "CC-BY-NC-4.0"

From 66e88c37647a3b59d5bb9cc489ad04d85dd876e0 Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Thu, 30 Nov 2023 16:21:22 +0100
Subject: [PATCH 09/15] meta.json - describe relation to the PI-CAI challenge
 in description

---
 models/gc_picai_baseline/meta.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
index b15c65ac..cfd8697d 100644
--- a/models/gc_picai_baseline/meta.json
+++ b/models/gc_picai_baseline/meta.json
@@ -3,7 +3,7 @@
   "name": "picai_baseline",
   "title": "PI-CAI challenge baseline",
   "summary": {
-    "description": "This algorithm predicts a detection map for the likelihood of clinically significant prostate cancer (csPCa) using biparametric MRI (bpMRI). The algorithm ensembles 5-fold cross-validation models that were trained on the PI-CAI: Public Training and Development Dataset v2.0. The detection map is at the same spatial resolution and physical dimensions as the input axial T2-weighted image.",
+    "description": "This algorithm predicts a detection map for the likelihood of clinically significant prostate cancer (csPCa) using biparametric MRI (bpMRI). The algorithm ensembles 5-fold cross-validation models that were trained on the PI-CAI: Public Training and Development Dataset v2.0. The detection map is at the same spatial resolution and physical dimensions as the input axial T2-weighted image. This model algorithm was used as a baseline for the PI-CAI challenge hosted on Grand Challenge.",
     "inputs": [
       {
         "label": "Transverse T2-weighted Prostate biparametric MRI",

From 39734f9a7151f80d63f836adadb7b56cf3e5f7ab Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Tue, 5 Dec 2023 13:54:52 +0100
Subject: [PATCH 10/15] meta.json - update input/output descriptions, extended
 intended use section

---
 models/gc_picai_baseline/meta.json | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
index cfd8697d..e172b4e1 100644
--- a/models/gc_picai_baseline/meta.json
+++ b/models/gc_picai_baseline/meta.json
@@ -6,32 +6,32 @@
     "description": "This algorithm predicts a detection map for the likelihood of clinically significant prostate cancer (csPCa) using biparametric MRI (bpMRI). The algorithm ensembles 5-fold cross-validation models that were trained on the PI-CAI: Public Training and Development Dataset v2.0. The detection map is at the same spatial resolution and physical dimensions as the input axial T2-weighted image. This model algorithm was used as a baseline for the PI-CAI challenge hosted on Grand Challenge.",
     "inputs": [
       {
-        "label": "Transverse T2-weighted Prostate biparametric MRI",
-        "description": " Transverse T2-weighted Prostate biparametric MRI exam",
+        "label": "Transverse T2-weighted prostate biparametric MRI",
+        "description": "Transverse T2-weighted prostate biparametric MRI exam.",
         "format": "DICOM",
         "modality": "MR",
         "bodypartexamined": "Prostate",
-        "slicethickness": "",
+        "slicethickness": "0.5 x 0.5 x 3.0 mm",
         "non-contrast": false,
         "contrast": false
       },
       {
-        "label": "High b-value diffusion-weighted maps",
-        "description": "High b-value diffusion-weighted maps, with b-value of 1400 or 2000, either acquired or vendor-calculated.",
+        "label": "Transverse high b-value diffusion-weighted maps of the prostate",
+        "description": "Transverse high b-value diffusion-weighted (DWI) maps, with b-value of 1400 or 2000, either acquired or vendor-calculated.",
         "format": "DICOM",
         "modality": "MR",
         "bodypartexamined": "Prostate",
-        "slicethickness": "",
+        "slicethickness": "0.5 x 0.5 x 3.0 mm",
         "non-contrast": false,
         "contrast": false
       },
       {
-        "label": "ADC map",
-        "description": "ADC map",
+        "label": "Transverse apparent diffusion coefficient map of the prostate",
+        "description": "Transverse apparent diffusion coefficient (ADC) prostate MRI map.",
         "format": "DICOM",
         "modality": "MR",
         "bodypartexamined": "Prostate",
-        "slicethickness": "",
+        "slicethickness": "0.5 x 0.5 x 3.0 mm",
         "non-contrast": false,
         "contrast": false
       }
@@ -41,14 +41,14 @@
         "type": "Prediction",
         "valueType": "Likelihood",
         "label": "Prostate cancer likelihood",
-        "description": "Case-level likelihood of harboring clinically significant prostate cancer, in range [0,1]",
+        "description": "Case-level likelihood of harboring clinically significant prostate cancer, in range [0,1].",
         "classes": []
       },
       {
         "type": "Prediction",
         "valueType": "Likelihood 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]",
+        "description": "Detection map of clinically significant prostate cancer lesions in 3D, where each voxel represents a floating point in range [0,1]. This map is at the same spatial resolution and physical dimensions as the input transversal T2-weighted image.",
         "classes": []
       }
     ],
@@ -101,7 +101,7 @@
   "info": {
     "use": {
       "title": "Intended use",
-      "text": "This algorithm is a deep learning-based detection/diagnosis model, which ensembles 5 independent nnU-Net models (5-fold cross-validation). To predict the likelihood of harboring clinically significant prostate cancer (csPCa), the transversal T2-weighted, apparent diffusion coefficient (ADC) and high b-value diffusion maps are required. The input sequences should be co-registered or aligned reasonably well and the prostate gland should be localized within a volume of 460 cm³ from the centre coordinate. To train these models, a total of 1500 prostate biparametric MRI (bpMRI) scans paired with human-annotated or AI-derived ISUP ≥ 2 delineations were used.",
+      "text": "This algorithm is a deep learning-based detection/diagnosis model, which ensembles 5 independent nnU-Net models (5-fold cross-validation). To predict the likelihood of harboring clinically significant prostate cancer (csPCa), the transversal T2-weighted, apparent diffusion coefficient (ADC) and high b-value diffusion weighted maps are required. The input sequences should be co-registered or aligned reasonably well and the prostate gland should be localized within a volume of 460 cm³ from the centre coordinate. The nnU-Net framework will internally resample all input scans to 0.5 x 0.5 x 3.0 mm. Per case the input data should be put into the following folder structure: `case1/adc`, `case1/hbv`, `case1/t2w`, corresponding respectively with the ADC, high b-value DWI, and the T2 weighted MR inputs for a case called `case1`.",
       "references": [
         {
           "label": "PI-CAI baseline algorithm on grand-challenge",
@@ -146,7 +146,7 @@
     },
     "training": {
       "title": "Training data",
-      "text": "The publicly available PI-CAI training and development dataset of 1500 biparametric MRI exams was used for training [1]. AI-derived annotations were created for cases without manual annotations [2]. This model was trained using a custom preprocessing step followed by the standard nnU-Net pipeline. The default nnU-Net loss-function was changed to Cross-Entropy + Focal loss. [3]",
+      "text": "The publicly available PI-CAI training and development dataset of 1500 biparametric MRI exams was used for training [1]. AI-derived annotations were created for cases without manual annotations [2]. This model was trained using a custom preprocessing step followed by the standard nnU-Net pipeline. The default nnU-Net loss-function was changed to Cross-Entropy + Focal loss [3].",
       "references": [
         {
           "label": "PI-CAI publicly available training and development dataset",

From 1f9dd941c0aa9413b342a801257d261ba61d326c Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Thu, 7 Dec 2023 12:56:51 +0100
Subject: [PATCH 11/15] update model/algorithm tag to 2.1.2 for nnunet pipe fix

---
 models/gc_picai_baseline/dockerfiles/Dockerfile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/models/gc_picai_baseline/dockerfiles/Dockerfile b/models/gc_picai_baseline/dockerfiles/Dockerfile
index a91146aa..7c2af162 100644
--- a/models/gc_picai_baseline/dockerfiles/Dockerfile
+++ b/models/gc_picai_baseline/dockerfiles/Dockerfile
@@ -12,10 +12,10 @@ RUN apt update && \
     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)
+#   - Git clone the algorithm repository for v2.1.2 (fixed to v2.1.2 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 && \
+RUN git clone --depth 1 --branch v2.1.2 https://github.com/DIAGNijmegen/picai_nnunet_semi_supervised_gc_algorithm.git /opt/algorithm && \
     rm -rf /opt/algorithm/test && \
     rm -rf /opt/algorithm/.git
 

From f3c73f3282b29c576bd0346c2c9e71c3713e94a8 Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Tue, 12 Dec 2023 10:51:39 +0100
Subject: [PATCH 12/15] add cli and configure runner to use cli

---
 .../utils/PicaiBaselineRunner.py              | 30 +++++------
 models/gc_picai_baseline/utils/cli.py         | 54 +++++++++++++++++++
 2 files changed, 68 insertions(+), 16 deletions(-)
 create mode 100644 models/gc_picai_baseline/utils/cli.py

diff --git a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
index 4f1d05ca..f3958222 100644
--- a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
+++ b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
@@ -10,12 +10,13 @@
 """
 
 import json
+import sys
 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
+
+CLI_PATH = Path(__file__).parent / "cli.py"
 
 
 @ValueOutput.Name('prostate_cancer_likelihood')
@@ -36,22 +37,19 @@ class PicaiBaselineRunner(Module):
     @IO.Output('cancer_detection_heatmap', 'cspca_detection_map.mha', "mha:mod=hm", bundle='model', the='output heatmap indicating prostate cancer likelihood')
     @IO.OutputData('cancer_likelihood', ProstateCancerLikelihood, the='PICAI baseline prostate cancer likelihood')
     def task(self, instance: Instance, in_data_t2: InstanceData, in_data_adc: InstanceData, in_data_hbv: InstanceData, cancer_likelihood_json: InstanceData, cancer_detection_heatmap: InstanceData, cancer_likelihood: ProstateCancerLikelihood) -> 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),
+        # build command (order matters!)
+        cmd = [
+            sys.executable,
+            str(CLI_PATH),
+            in_data_t2.abspath,
+            in_data_adc.abspath,
+            in_data_hbv.abspath,
+            cancer_likelihood_json.abspath,
+            cancer_detection_heatmap.abspath,
         ]
 
-        # Specify output files
-        classifier.cspca_detection_map_path = Path(cancer_detection_heatmap.abspath)
-        classifier.case_confidence_path = Path(cancer_likelihood_json.abspath)
-
-        # Run the classifier on the input images
-        classifier.process()
+        # run the command as subprocess
+        self.subprocess(cmd, text=True)
 
         # Extract cancer likelihood value from cancer_likelihood_file
         if not Path(cancer_likelihood_json.abspath).is_file():
diff --git a/models/gc_picai_baseline/utils/cli.py b/models/gc_picai_baseline/utils/cli.py
new file mode 100644
index 00000000..64d51a73
--- /dev/null
+++ b/models/gc_picai_baseline/utils/cli.py
@@ -0,0 +1,54 @@
+"""
+--------------------------------------------------
+Mhub / DIAG - CLI for the PICAI baseline Algorithm
+--------------------------------------------------
+
+--------------------------------------------------
+Author: Sil van de Leemput
+Email:  sil.vandeleemput@radboudumc.nl
+--------------------------------------------------
+"""
+
+import argparse
+from pathlib import Path
+from process import csPCaAlgorithm as PicaiClassifier
+
+
+def run_classifier(t2: Path, adc: Path, hbv: Path, cancer_likelihood_json: Path, cancer_detection_heatmap: Path):
+    # Initialize classifier object
+    classifier = PicaiClassifier()
+
+    # Specify input files (the order is important!)
+    classifier.scan_paths = [
+        t2,
+        adc,
+        hbv,
+    ]
+
+    # Specify output files
+    classifier.cspca_detection_map_path = cancer_detection_heatmap
+    classifier.case_confidence_path = cancer_likelihood_json
+
+    # Run the classifier on the input images
+    classifier.process()
+
+
+def run_classifier_cli():
+    parser = argparse.ArgumentParser("CLI to run the PICAI baseline classifier")
+    parser.add_argument("input_t2", type=str, help="input T2 weighted prostate MR image (MHA)")
+    parser.add_argument("input_adc", type=str, help="input ADC prostate MR image (MHA")
+    parser.add_argument("input_hbv", type=str, help="input HBV prostate MR image (MHA)")
+    parser.add_argument("output_cancer_likelihood_json", type=str, help="output JSON file with PICAI baseline prostate cancer likelihood (JSON)")
+    parser.add_argument("output_cancer_detection_heatmap", type=str, help="output heatmap indicating prostate cancer likelihood (MHA)")
+    args = parser.parse_args()
+    run_classifier(
+        t2=Path(args.input_t2),
+        adc=Path(args.input_adc),
+        hbv=Path(args.input_hbv),
+        cancer_likelihood_json=Path(args.output_cancer_likelihood_json),
+        cancer_detection_heatmap=Path(args.output_cancer_detection_heatmap),
+    )
+
+
+if __name__ == "__main__":
+    run_classifier_cli()

From 2a8ef5963df1220fd0e35983a7a07d4b2fe654b0 Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Wed, 13 Dec 2023 11:02:10 +0100
Subject: [PATCH 13/15] meta.json - change name into gc_picai_baseline

---
 models/gc_picai_baseline/meta.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
index e172b4e1..7cd3fec4 100644
--- a/models/gc_picai_baseline/meta.json
+++ b/models/gc_picai_baseline/meta.json
@@ -1,6 +1,6 @@
 {
   "id": "c5f886fb-9f54-4555-a954-da02b22d6d3f",
-  "name": "picai_baseline",
+  "name": "gc_picai_baseline",
   "title": "PI-CAI challenge baseline",
   "summary": {
     "description": "This algorithm predicts a detection map for the likelihood of clinically significant prostate cancer (csPCa) using biparametric MRI (bpMRI). The algorithm ensembles 5-fold cross-validation models that were trained on the PI-CAI: Public Training and Development Dataset v2.0. The detection map is at the same spatial resolution and physical dimensions as the input axial T2-weighted image. This model algorithm was used as a baseline for the PI-CAI challenge hosted on Grand Challenge.",

From 7055664293f44dab5b8916d69a1faa911b6d09fe Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Wed, 13 Dec 2023 15:04:11 +0100
Subject: [PATCH 14/15] meta.json - correction for license weights

---
 models/gc_picai_baseline/meta.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/models/gc_picai_baseline/meta.json b/models/gc_picai_baseline/meta.json
index 7cd3fec4..1dbab230 100644
--- a/models/gc_picai_baseline/meta.json
+++ b/models/gc_picai_baseline/meta.json
@@ -81,7 +81,7 @@
     "cite": "J. S. Bosma, A. Saha, M. Hosseinzadeh, I. Slootweg, M. de Rooij, and H. Huisman, \"Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning–based Prostate Cancer Detection Using Biparametric MRI\", Radiology: Artificial Intelligence, 230031, 2023. DOI: 10.1148/ryai.230031",
     "license": {
       "code": "Apache 2.0",
-      "weights": "CC-BY-NC-4.0"
+      "weights": "CC-BY-NC-SA-4.0"
     },
     "publications": [
       {

From ed79ebd134801862eb6e5e2c2810a4a45cb9f6c9 Mon Sep 17 00:00:00 2001
From: silvandeleemput <silvandeleemput@gmail.com>
Date: Thu, 14 Dec 2023 13:17:38 +0100
Subject: [PATCH 15/15] runner & cli - changed heatmap output descriptions to
 detection map and updated descriptions

---
 models/gc_picai_baseline/config/default.yml           | 2 +-
 models/gc_picai_baseline/utils/PicaiBaselineRunner.py | 6 +++---
 models/gc_picai_baseline/utils/cli.py                 | 8 ++++----
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/models/gc_picai_baseline/config/default.yml b/models/gc_picai_baseline/config/default.yml
index c86cac07..bb5d5deb 100644
--- a/models/gc_picai_baseline/config/default.yml
+++ b/models/gc_picai_baseline/config/default.yml
@@ -31,4 +31,4 @@ modules:
   DataOrganizer:
     targets:
       - json:mod=report-->[i:sid]/cspca-case-level-likelihood.json
-      - mha:mod=hm-->[i:sid]/cspca-detection-map.mha
+      - mha:mod=dm-->[i:sid]/cspca-detection-map.mha
diff --git a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
index f3958222..84dc1474 100644
--- a/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
+++ b/models/gc_picai_baseline/utils/PicaiBaselineRunner.py
@@ -34,9 +34,9 @@ class PicaiBaselineRunner(Module):
     @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_likelihood_json', 'cspca-case-level-likelihood.json', "json", bundle='model', the='output JSON file with PICAI baseline prostate cancer likelihood')
-    @IO.Output('cancer_detection_heatmap', 'cspca_detection_map.mha', "mha:mod=hm", bundle='model', the='output heatmap indicating prostate cancer likelihood')
+    @IO.Output('cancer_lesion_detection_map', 'cspca-detection-map.mha', "mha:mod=dm", bundle='model', the='output detection map of clinically significant prostate cancer lesions in 3D, where each voxel represents a floating point in range [0,1]')
     @IO.OutputData('cancer_likelihood', ProstateCancerLikelihood, the='PICAI baseline prostate cancer likelihood')
-    def task(self, instance: Instance, in_data_t2: InstanceData, in_data_adc: InstanceData, in_data_hbv: InstanceData, cancer_likelihood_json: InstanceData, cancer_detection_heatmap: InstanceData, cancer_likelihood: ProstateCancerLikelihood) -> None:
+    def task(self, instance: Instance, in_data_t2: InstanceData, in_data_adc: InstanceData, in_data_hbv: InstanceData, cancer_likelihood_json: InstanceData, cancer_lesion_detection_map: InstanceData, cancer_likelihood: ProstateCancerLikelihood) -> None:
         # build command (order matters!)
         cmd = [
             sys.executable,
@@ -45,7 +45,7 @@ def task(self, instance: Instance, in_data_t2: InstanceData, in_data_adc: Instan
             in_data_adc.abspath,
             in_data_hbv.abspath,
             cancer_likelihood_json.abspath,
-            cancer_detection_heatmap.abspath,
+            cancer_lesion_detection_map.abspath,
         ]
 
         # run the command as subprocess
diff --git a/models/gc_picai_baseline/utils/cli.py b/models/gc_picai_baseline/utils/cli.py
index 64d51a73..deaf9ecf 100644
--- a/models/gc_picai_baseline/utils/cli.py
+++ b/models/gc_picai_baseline/utils/cli.py
@@ -14,7 +14,7 @@
 from process import csPCaAlgorithm as PicaiClassifier
 
 
-def run_classifier(t2: Path, adc: Path, hbv: Path, cancer_likelihood_json: Path, cancer_detection_heatmap: Path):
+def run_classifier(t2: Path, adc: Path, hbv: Path, cancer_likelihood_json: Path, cancer_lesion_detection_map: Path):
     # Initialize classifier object
     classifier = PicaiClassifier()
 
@@ -26,7 +26,7 @@ def run_classifier(t2: Path, adc: Path, hbv: Path, cancer_likelihood_json: Path,
     ]
 
     # Specify output files
-    classifier.cspca_detection_map_path = cancer_detection_heatmap
+    classifier.cspca_detection_map_path = cancer_lesion_detection_map
     classifier.case_confidence_path = cancer_likelihood_json
 
     # Run the classifier on the input images
@@ -39,14 +39,14 @@ def run_classifier_cli():
     parser.add_argument("input_adc", type=str, help="input ADC prostate MR image (MHA")
     parser.add_argument("input_hbv", type=str, help="input HBV prostate MR image (MHA)")
     parser.add_argument("output_cancer_likelihood_json", type=str, help="output JSON file with PICAI baseline prostate cancer likelihood (JSON)")
-    parser.add_argument("output_cancer_detection_heatmap", type=str, help="output heatmap indicating prostate cancer likelihood (MHA)")
+    parser.add_argument("output_cancer_lesion_detection_map", type=str, help="output detection map of clinically significant prostate cancer lesions in 3D (MHA)")
     args = parser.parse_args()
     run_classifier(
         t2=Path(args.input_t2),
         adc=Path(args.input_adc),
         hbv=Path(args.input_hbv),
         cancer_likelihood_json=Path(args.output_cancer_likelihood_json),
-        cancer_detection_heatmap=Path(args.output_cancer_detection_heatmap),
+        cancer_lesion_detection_map=Path(args.output_cancer_lesion_detection_map),
     )