Added example notebook for segmentation with cellpose-SAM

src/tapenade/notebooks/segmentation_notebook_cellpose-sam.ipynb

@@ -0,0 +1,183 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c163bc9a",
+   "metadata": {},
+   "source": [
+    "# Segmentation Notebook using CellPose-SAM"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c0ef5bb6",
+   "metadata": {},
+   "source": [
+    "The algorithm CellPose-SAM is described in the paper:\n",
+    "\n",
+    "Cellpose-SAM: superhuman generalization for cellular segmentation\n",
+    "\n",
+    "Marius Pachitariu, Michael Rariden, Carsen Stringer\n",
+    "\n",
+    "bioRxiv 2025.04.28.651001; doi: https://doi.org/10.1101/2025.04.28.651001"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c127cbbd",
+   "metadata": {},
+   "source": [
+    "### <font color='red'> After clicking on a code cell, press \"Shift+Enter\" to run the code, or click on the \"Run\" button in the toolbar above.<br>\n",
+    "\n",
+    "### Replace \"...\" signs with the appropriate path to your data.\n",
+    "</font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf42aedc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from cellpose import models, core, io, plot\n",
+    "from tapenade import get_path_to_demo_folder\n",
+    "import napari\n",
+    "import tifffile\n",
+    "io.logger_setup() # run this to get printing of progress\n",
+    "if core.use_gpu()==False:\n",
+    "  raise ImportError(\"No GPU access, change your runtime\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "badcf579",
+   "metadata": {},
+   "source": [
+    "Enter the path to the image you want to segment, or use the demo data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d4a2b57f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_data = get_path_to_demo_folder()\n",
+    "data_normalized = tifffile.imread(path_to_data / \"image_isotropized_enhanced.tif\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "83dbd61f",
+   "metadata": {},
+   "source": [
+    "## Quick note about pre-processing\n",
+    "\n",
+    "To prepare your data, we recommend normalizing the image values using `local_contrast_enhancement`, in the case where your image is very deep, as it can improve performance in deeper planes by enhancing the contrast using local statistics. To do so, use the processing notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39918b77",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# the demo data is already processed\n",
+    "\n",
+    "# data_normalized = local_contrast_enhancement(\n",
+    "#     data,\n",
+    "#     mask=mask,\n",
+    "#     box_size=10,\n",
+    "#     perc_low=1, perc_high=99\n",
+    "# )\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d032d50c",
+   "metadata": {},
+   "source": [
+    "## Run the prediction using CellPose-SAM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "548be45c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = models.CellposeModel(gpu=True)\n",
+    "\n",
+    "labels, flows, _ = model.eval(data_normalized, z_axis=0, channel_axis=None,\n",
+    "                                    batch_size=32,\n",
+    "                                    do_3D=True, flow3D_smooth=1)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3e7ab04f",
+   "metadata": {},
+   "source": [
+    "## Check results (napari required)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9d168135",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "viewer=napari.Viewer()\n",
+    "viewer.add_image(data_normalized, name='image')\n",
+    "viewer.add_labels(labels, name='labels')\n",
+    "napari.run()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e4eb3303",
+   "metadata": {},
+   "source": [
+    "## Save results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "231ec9e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tifffile.imwrite(..., labels) # replace ... with the path where you want to save the labels as a tif file"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "cellpose",
+   "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": "3.10.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/tapenade/notebooks/segmentation_notebook.ipynb → src/tapenade/notebooks/segmentation_notebook_stardist.ipynb

@@ -305,7 +305,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "napari-mine",
+   "display_name": "env-tapenade",
    "language": "python",
    "name": "python3"
   },
@@ -319,7 +319,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,