TissueImageAnalytics · shaneahmed · Mar 5, 2026 · Mar 24, 2023 · Mar 31, 2023 · Mar 31, 2023
diff --git a/docs/images/nucleus_detection_classification.png b/docs/images/nucleus_detection_classification.png
diff --git a/docs/pretrained.rst b/docs/pretrained.rst
@@ -349,11 +349,12 @@ The input output configuration is as follows:
 
    .. code-block:: python
 
-        from tiatoolbox.models import IOPatchPredictorConfig
-        ioconfig = IOPatchPredictorConfig(
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
             patch_input_shape=(31, 31),
+            patch_output_shape=(13, 13),
             stride_shape=(8, 8),
-            input_resolutions=[{"resolution": 0.25, "units": "mpp"}]
+            input_resolutions=[{"resolution": 0.25, "units": "mpp"}],
         )
 
 
@@ -365,11 +366,11 @@ The input output configuration is as follows:
 
    .. code-block:: python
 
-        from tiatoolbox.models import IOPatchPredictorConfig
-        ioconfig = IOPatchPredictorConfig(
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
             patch_input_shape=(252, 252),
             stride_shape=(150, 150),
-            input_resolutions=[{"resolution": 0.25, "units": "mpp"}]
+            input_resolutions=[{"resolution": 0.5, "units": "mpp"}]
         )
 
 
@@ -389,9 +390,10 @@ The input output configuration is as follows:
 
    .. code-block:: python
 
-        from tiatoolbox.models import IOPatchPredictorConfig
-        ioconfig = IOPatchPredictorConfig(
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
             patch_input_shape=(31, 31),
+            patch_output_shape=(13, 13),
             stride_shape=(8, 8),
             input_resolutions=[{"resolution": 0.25, "units": "mpp"}]
         )
@@ -405,18 +407,147 @@ The input output configuration is as follows:
 
    .. code-block:: python
 
-        from tiatoolbox.models import IOPatchPredictorConfig
-        ioconfig = IOPatchPredictorConfig(
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
             patch_input_shape=(252, 252),
             stride_shape=(150, 150),
-            input_resolutions=[{"resolution": 0.25, "units": "mpp"}]
+            input_resolutions=[{"resolution": 0.5, "units": "mpp"}]
         )
 
 
 .. collapse:: Model names
 
     - mapde-conic
 
+.. collapse:: Input Output Configuration Details
+
+   .. code-block:: python
+
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
+            patch_input_shape=(256, 256),
+            stride_shape=(248, 248),
+            input_resolutions=[{"resolution": 0.5, "units": "mpp"}],
+            save_resolution={'units': 'baseline', 'resolution': 1.0}
+        )
+
+
+.. collapse:: Model names
+
+    - KongNet_CoNIC_1
+
+PanNuke Dataset
+--------------
+
+We provide the following models trained using the `PanNuke dataset <https://warwick.ac.uk/fac/cross_fac/tia/data/pannuke>`_.
+All model weights trained on PanNuke are held under the `Creative Commons Attribution-NonCommercial-ShareAlike Version 4 (CC BY-NC-SA 4.0) License <https://creativecommons.org/licenses/by-nc-sa/4.0/>`_.
+The input output configuration is as follows:
+
+.. collapse:: Input Output Configuration Details
+
+   .. code-block:: python
+
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
+            patch_input_shape=(256, 256),
+            stride_shape=(240, 240),
+            input_resolutions=[{"resolution": 0.25, "units": "mpp"}],
+            save_resolution={'units': 'baseline', 'resolution': 1.0}
+        )
+
+
+.. collapse:: Model names
+
+    - KongNet_PanNuke_1
+
+MONKEY Dataset
+--------------
+
+We provide the following models trained using the `MONKEY dataset <https://zenodo.org/records/13794656>`_.
+All model weights trained on MONKEY are held under the `Creative Commons Attribution International Version 4 (CC BY 4.0) License <https://creativecommons.org/licenses/by/4.0/legalcode>`_.
+The input output configuration is as follows:
+
+.. collapse:: Input Output Configuration Details
+
+   .. code-block:: python
+
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
+            patch_input_shape=(256, 256),
+            stride_shape=(224, 224),
+            input_resolutions=[{"resolution": 0.25, "units": "mpp"}],
+            save_resolution={'units': 'baseline', 'resolution': 1.0}
+        )
+
+
+.. collapse:: Model names
+
+    - KongNet_MONKEY_1
+
+PUMA Dataset
+--------------
+
+We provide the following models trained using the `PUMA dataset <https://zenodo.org/records/14869398>`_.
+All model weights trained on PUMA are held under the `Creative Commons Zero v1.0 Universal (CC0 1.0) License <https://creativecommons.org/publicdomain/zero/1.0/legalcode>`_.
+The input output configuration is as follows:
+
+.. collapse:: Input Output Configuration Details
+
+   .. code-block:: python
+
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
+            patch_input_shape=(256, 256),
+            stride_shape=(224, 224),
+            input_resolutions=[{"resolution": 0.25, "units": "mpp"}],
+            save_resolution={'units': 'baseline', 'resolution': 1.0}
+        )
+
+
+.. collapse:: Model names
+
+    - KongNet_PUMA_T1_3
+
+.. collapse:: Input Output Configuration Details
+
+   .. code-block:: python
+
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
+            patch_input_shape=(256, 256),
+            stride_shape=(224, 224),
+            input_resolutions=[{"resolution": 0.25, "units": "mpp"}],
+            save_resolution={'units': 'baseline', 'resolution': 1.0}
+        )
+
+
+.. collapse:: Model names
+
+    - KongNet_PUMA_T2_3
+
+MIDOG 2025
+--------------
+
+We provide the following models trained using the `MIDOG 2025 datasets <https://zenodo.org/records/15077361>`_.
+All model weights trained on MIDOG 2025 datasets are held under the `Creative Commons Attribution International Version 4 (CC BY 4.0) License <https://creativecommons.org/licenses/by/4.0/legalcode>`_.
+The input output configuration is as follows:
+
+.. collapse:: Input Output Configuration Details
+
+   .. code-block:: python
+
+        from tiatoolbox.models.engine.io_config import IOSegmentorConfig
+        ioconfig = IOSegmentorConfig(
+            patch_input_shape=(512, 512),
+            stride_shape=(492, 492),
+            input_resolutions=[{"resolution": 0.5, "units": "mpp"}],
+            save_resolution={'units': 'baseline', 'resolution': 1.0}
+        )
+
+
+.. collapse:: Model names
+
+    - KongNet_Det_MIDOG_1
 
 Multi-Task Segmentation
 ^^^^^^^^^^^^^^^^^^^^^^^

diff --git a/examples/01-wsi-reading.ipynb b/examples/01-wsi-reading.ipynb
diff --git a/examples/02-stain-normalization.ipynb b/examples/02-stain-normalization.ipynb
diff --git a/examples/03-tissue-masking.ipynb b/examples/03-tissue-masking.ipynb
diff --git a/examples/04-patch-extraction.ipynb b/examples/04-patch-extraction.ipynb
@@ -72,7 +72,7 @@
    "outputs": [],
    "source": [
     "%%bash\n",
-    "apt-get -y install libopenjp2-7-dev libopenjp2-tools openslide-tools libpixman-1-dev | tail -n 1\n",
+    "apt-get -y install libopenjp2-7-dev libopenjp2-tools libpixman-1-dev | tail -n 1\n",
     "pip install git+https://github.com/TissueImageAnalytics/tiatoolbox.git@develop | tail -n 1\n",
     "echo \"Installation is done.\""
    ]
@@ -173,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -196,15 +196,15 @@
     "\n",
     "# Downloading sample image from MoNuSeg\n",
     "r = requests.get(\n",
-    "    \"https://tiatoolbox.dcs.warwick.ac.uk/testdata/patchextraction/TCGA-HE-7130-01Z-00-DX1.png\",\n",
+    "    \"https://huggingface.co/datasets/TIACentre/TIAToolBox_Remote_Samples/resolve/main/testdata/patchextraction/TCGA-HE-7130-01Z-00-DX1.png\",\n",
     "    timeout=10,  # 10s\n",
     ")\n",
     "with Path(img_file_name).open(\"wb\") as f:\n",
     "    f.write(r.content)\n",
     "\n",
     "# Downloading points list\n",
     "r = requests.get(\n",
-    "    \"https://tiatoolbox.dcs.warwick.ac.uk/testdata/patchextraction/sample_patch_extraction.csv\",\n",
+    "    \"https://huggingface.co/datasets/TIACentre/TIAToolBox_Remote_Samples/resolve/main/testdata/patchextraction/sample_patch_extraction.csv\",\n",
     "    timeout=10,  # 10s\n",
     ")\n",
     "with Path(csv_file_name).open(\"wb\") as f:\n",
@@ -691,7 +691,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {
     "id": "CZDEPvCy87fL"
    },
@@ -703,7 +703,7 @@
     "\n",
     "wsi_file_name = \"sample_wsi.svs\"\n",
     "wsi_path = download_data(\n",
-    "    \"https://tiatoolbox.dcs.warwick.ac.uk/sample_wsis/TCGA-3L-AA1B-01Z-00-DX1.8923A151-A690-40B7-9E5A-FCBEDFC2394F.svs\",\n",
+    "    \"https://huggingface.co/datasets/TIACentre/TIAToolBox_Remote_Samples/resolve/main/sample_wsis/TCGA-3L-AA1B-01Z-00-DX1.8923A151-A690-40B7-9E5A-FCBEDFC2394F.svs\",\n",
     "    wsi_file_name,\n",
     ")\n",
     "wsi = WSIReader.open(wsi_path)"
@@ -1038,9 +1038,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.18"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 4
 }