diff --git a/notebooks/e09-Cellpose_pipeline.ipynb b/notebooks/e09-Cellpose_pipeline.ipynb
index e9c63a78da498e97dd5b27504aa11db77f59995c..02a58fd481bf17f350e4673d4078370d41360d15 100644
--- a/notebooks/e09-Cellpose_pipeline.ipynb
+++ b/notebooks/e09-Cellpose_pipeline.ipynb
@@ -4,15 +4,18 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# 9. Segment images using cellpose"
+    "# 9. Segment images using cellpose\n",
+    "\n",
+    "In this notebook we'll be applying the Cellpose algorithm to segment the cells in the images. Cellpose is a deep learning algorithm that can be used to segment cells in images."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
+    "import os\n",
     "import skimage\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
@@ -23,74 +26,134 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "- define a function that reads an image and bins it by 4.\n",
-    "- define a function that segments the image using cellpose\n",
-    "- define a function that measures the area of the cells\n",
-    "- loop over the images and save the results"
+    "This is a function to rea the third channel of an image and downscale it. Use the function to read one of the tif images in the 'images' folder and display it. \n",
+    "\n",
+    "```python\n",
+    "def read_and_scale_image(image_path):\n",
+    "    image = skimage.io.imread(image_path)\n",
+    "    image = image[:, :, 2]\n",
+    "    image = image[::4, :: 4]\n",
+    "    return image\n",
+    "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/cellpose/resnet_torch.py:275: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
-      "  state_dict = torch.load(filename, map_location=torch.device(\"cpu\"))\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "model = models.Cellpose(model_type='cyto')"
+    "Use the following function to segment the nuclei in the image.\n",
+    "\n",
+    "Display the segmentation masks using `stackview.curtain(image, masks)`\n",
+    "\n",
+    "```python\n",
+    "def segment_image(image):\n",
+    "    model = models.Cellpose(gpu=False, model_type='nuclei')\n",
+    "    masks, flows, styles, diams = model.eval(image, diameter=150, channels=[0, 0])\n",
+    "    return masks\n",
+    "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "image = skimage.io.imread('images/19838_1252_F8_1.tif')\n",
-    "image = image[::4, :: 4, :]"
+    "How could you improve the segmentation output? Hint: Look at the diameter."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "channels=[[1,3]]\n",
-    "masks, flows, styles, diams = model.eval(image, diameter=None, channels=channels)"
+    "Use the following code to create a list of all the images in the 'images' folder and print the list.\n",
+    "\n",
+    "```python\n",
+    "image_path_list = [p for p in os.listdir('images') if p.endswith('.tif')]\n",
+    "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "11c36e6036824acb9157c7f779378251",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "HBox(children=(VBox(children=(VBox(children=(HBox(children=(VBox(children=(ImageWidget(height=512, width=512),…"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Restrict the list to only the first 2 images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Write a loop that for each image file path:\n",
+    "- reads the image\n",
+    "- segments the nuclei\n",
+    "- displays the segmentation masks.\n",
+    "\n",
+    "Display the masks using the following command\n",
+    "`plt.figure(); plt.imshow(masks)`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a folder \"segmentations\" into which you will write the nuclei segmentations (you can do this outside of jupyter).\n",
+    "\n",
+    "For each image, remove the imshow command and instead add a line that saves the segmentation masks into the previously created folder. Use the command `skimage.io.imsave(output_path, masks)` for this."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "import stackview\n",
-    "stackview.curtain(image, masks)"
+    "Check the segmentations folder and open the files in Fiji to check everything is okay."
    ]
   }
  ],
diff --git a/notebooks/e09-Cellpose_pipeline_solution.ipynb b/notebooks/e09-Cellpose_pipeline_solution.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..62389ee086aa1f8d1c77887d0e53ccde6080dca8
--- /dev/null
+++ b/notebooks/e09-Cellpose_pipeline_solution.ipynb
@@ -0,0 +1,379 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 9. Segment images using cellpose\n",
+    "\n",
+    "In this notebook we'll be applying the Cellpose algorithm to segment the cells in the images. Cellpose is a deep learning algorithm that can be used to segment cells in images."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import skimage\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from cellpose import models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is a function to rea the third channel of an image and downscale it. Use the function to read one of the tif images in the 'images' folder and display it. \n",
+    "\n",
+    "```python\n",
+    "def read_and_scale_image(image_path):\n",
+    "    image = skimage.io.imread(image_path)\n",
+    "    image = image[:, :, 2]\n",
+    "    image = image[::4, :: 4]\n",
+    "    return image\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x146abed10>"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "def read_and_scale_image(image_path):\n",
+    "    image = skimage.io.imread(image_path)\n",
+    "    image = image[:, :, 2]\n",
+    "    image = image[::4, :: 4]\n",
+    "    return image\n",
+    "\n",
+    "image = read_and_scale_image('images/46658_784_B12_1.tif')\n",
+    "plt.imshow(image, cmap='gray')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Use the following function to segment the nuclei in the image.\n",
+    "\n",
+    "Display the segmentation masks using `stackview.curtain(image, masks)`\n",
+    "\n",
+    "```python\n",
+    "def segment_image(image):\n",
+    "    model = models.Cellpose(gpu=False, model_type='nuclei')\n",
+    "    masks, flows, styles, diams = model.eval(image, diameter=150, channels=[0, 0])\n",
+    "    return masks\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/cellpose/resnet_torch.py:275: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
+      "  state_dict = torch.load(filename, map_location=torch.device(\"cpu\"))\n"
+     ]
+    }
+   ],
+   "source": [
+    "def segment_image(image):\n",
+    "    model = models.Cellpose(gpu=False, model_type='nuclei')\n",
+    "    masks, flows, styles, diams = model.eval(image, diameter=150, channels=[0, 0])\n",
+    "    return masks\n",
+    "\n",
+    "masks = segment_image(image)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "329a0c2a88da4da9be98f1d9c6249f5f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(VBox(children=(VBox(children=(HBox(children=(VBox(children=(ImageWidget(height=512, width=512),…"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import stackview\n",
+    "\n",
+    "stackview.curtain(image, masks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "How could you improve the segmentation output? Hint: Look at the diameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "51c2380c1a1843fcb16a2196584602e7",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(VBox(children=(VBox(children=(HBox(children=(VBox(children=(ImageWidget(height=512, width=512),…"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def segment_image(image):\n",
+    "    model = models.Cellpose(gpu=False, model_type='nuclei')\n",
+    "    masks, flows, styles, diams = model.eval(image, diameter=50, channels=[0, 0])\n",
+    "    return masks\n",
+    "\n",
+    "masks = segment_image(image)\n",
+    "stackview.curtain(image, masks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Use the following code to create a list of all the images in the 'images' folder and print the list.\n",
+    "\n",
+    "```python\n",
+    "image_path_list = [p for p in os.listdir('images') if p.endswith('.tif')]\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['27985_284_E10_2.tif',\n",
+       " '24138_196_F7_2.tif',\n",
+       " '50546_727_A8_2.tif',\n",
+       " '67703_1283_D7_3.tif',\n",
+       " '47549_736_E7_1.tif',\n",
+       " '19838_1252_F8_1.tif',\n",
+       " '8346_22_C1_1.tif',\n",
+       " '47032_977_G4_4.tif',\n",
+       " '37367_517_E4_2.tif',\n",
+       " '36268_407_B8_1.tif',\n",
+       " '64554_1164_A6_2.tif',\n",
+       " '60398_1596_E1_1.tif',\n",
+       " '46658_784_B12_1.tif',\n",
+       " '27897_273_C8_2.tif',\n",
+       " '36268_404_B8_2.tif']"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "image_path_list = [p for p in os.listdir('images') if p.endswith('.tif')]\n",
+    "image_path_list"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Restrict the list to only the first 2 images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "image_path_list = image_path_list[:2]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Write a loop that for each image file path:\n",
+    "- reads the image\n",
+    "- segments the nuclei\n",
+    "- displays the segmentation masks.\n",
+    "\n",
+    "Display the masks using the following command\n",
+    "`plt.figure(); plt.imshow(masks)`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/cellpose/resnet_torch.py:275: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
+      "  state_dict = torch.load(filename, map_location=torch.device(\"cpu\"))\n",
+      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/cellpose/resnet_torch.py:275: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
+      "  state_dict = torch.load(filename, map_location=torch.device(\"cpu\"))\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# import stackview\n",
+    "for image_path in image_path_list:\n",
+    "    image = read_and_scale_image('images/' + image_path)\n",
+    "    masks = segment_image(image)\n",
+    "    plt.figure()\n",
+    "    plt.imshow(masks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a folder \"segmentations\" into which you will write the nuclei segmentations (you can do this outside of jupyter).\n",
+    "\n",
+    "For each image, remove the imshow command and instead add a line that saves the segmentation masks into the previously created folder. Use the command `skimage.io.imsave(output_path, masks)` for this."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/cellpose/resnet_torch.py:275: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
+      "  state_dict = torch.load(filename, map_location=torch.device(\"cpu\"))\n",
+      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/skimage/_shared/utils.py:328: UserWarning: segmentations/27985_284_E10_2.tif is a low contrast image\n",
+      "  return func(*args, **kwargs)\n",
+      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/cellpose/resnet_torch.py:275: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
+      "  state_dict = torch.load(filename, map_location=torch.device(\"cpu\"))\n",
+      "/Users/malbert/miniconda3/envs/pyimagecourse/lib/python3.10/site-packages/skimage/_shared/utils.py:328: UserWarning: segmentations/24138_196_F7_2.tif is a low contrast image\n",
+      "  return func(*args, **kwargs)\n"
+     ]
+    }
+   ],
+   "source": [
+    "for image_path in image_path_list:\n",
+    "    image = read_and_scale_image('images/' + image_path)\n",
+    "    masks = segment_image(image)\n",
+    "    skimage.io.imsave('segmentations/' + image_path, masks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Check the segmentations folder and open the files in Fiji to check everything is okay."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.16"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": false,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": true
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}