{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bead segmentation and measurements\n",
    "This notebook shows how to detect hot spots / local maxima / beads in an image and how to measure their FWHM. To make the algorithm work, the beads should be sufficiently sparse."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<GeForce RTX 2080 Ti on Platform: NVIDIA CUDA (1 refs)>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pyclesperanto_prototype as cle\n",
    "\n",
    "cle.get_device()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's start by making an image showing local maxima."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "from skimage.io import imshow\n",
    "\n",
    "random_image = np.random.random([512,512])\n",
    "binary_image = random_image > 0.9995\n",
    "\n",
    "# push to GPU\n",
    "input_image = cle.push(binary_image * random_image)\n",
    "\n",
    "# blur the image\n",
    "sigma = 3\n",
    "starting_point = cle.gaussian_blur(input_image, sigma_x=sigma, sigma_y=sigma)\n",
    "\n",
    "# show input image\n",
    "cle.imshow(starting_point)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Local maxima detection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "maxima = cle.detect_maxima_box(starting_point)\n",
    "\n",
    "cle.imshow(maxima)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Local threshold determination"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0.         0.01768377 0.01768208 0.01768224 0.0176772  0.0181608\n",
      "  0.01815818 0.01768057 0.01768325 0.01767664 0.01767906 0.01767709\n",
      "  0.01768016 0.01768034 0.01774181 0.01774283 0.01768184 0.01767717\n",
      "  0.0178369  0.01767897 0.01768419 0.01767986 0.01783899 0.01767691\n",
      "  0.01768328 0.01768697 0.03254582 0.01767773 0.0176841  0.01768155\n",
      "  0.01769111 0.01768344 0.02928126 0.01786935 0.01768215 0.01768069\n",
      "  0.01768353 0.01770177 0.01768265 0.01767997 0.01768172 0.01770184\n",
      "  0.01767969 0.01767693 0.01767922 0.01768182 0.01768393 0.01768284\n",
      "  0.01768168 0.01768519 0.01768195 0.01768152 0.0176794  0.01767927\n",
      "  0.01768468 0.01767826 0.01768431 0.01768175 0.01767642 0.01768046\n",
      "  0.02197522 0.01768482 0.02831593 0.01767953 0.01768435 0.01768049\n",
      "  0.01768227 0.01768274 0.01768204 0.01775198 0.01767821 0.01768308\n",
      "  0.01774705 0.01767809 0.0308786  0.01768096 0.01767744 0.017677\n",
      "  0.01767849 0.01768358 0.01768395 0.01768166 0.01767815 0.01768243\n",
      "  0.01767886 0.01767834 0.01768392 0.01776545 0.01767989 0.01776191\n",
      "  0.01767842 0.01767735 0.01767821 0.01767953 0.01768415 0.01768159\n",
      "  0.01767878 0.01768069 0.01768275 0.01768378 0.01768449 0.01768373\n",
      "  0.01767703 0.01767811 0.01768177 0.01775915 0.01767675 0.01768197\n",
      "  0.01873644 0.01866633 0.01768056 0.01768161 0.01768002 0.01768094\n",
      "  0.01767907 0.01786366 0.01768381 0.01787041 0.0176813  0.01768215\n",
      "  0.01768482 0.01767716 0.01767839]]\n"
     ]
    }
   ],
   "source": [
    "# Label maxima\n",
    "labeled_maxima = cle.label_spots(maxima)\n",
    "\n",
    "# read out intensities at the maxima\n",
    "max_intensities = cle.read_intensities_from_map(labeled_maxima, starting_point)\n",
    "print(max_intensities)\n",
    "\n",
    "# calculate thresholds\n",
    "thresholds = cle.multiply_image_and_scalar(max_intensities, scalar=0.5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Make a local threshold image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Extend labeled maxima until they touch\n",
    "voronoi_label_image = cle.extend_labeling_via_voronoi(labeled_maxima)\n",
    "cle.imshow(voronoi_label_image, labels=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Replace labels with thresholds\n",
    "threshold_image = cle.replace_intensities(voronoi_label_image, thresholds)\n",
    "\n",
    "cle.imshow(threshold_image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Apply threshold\n",
    "binary_segmented = cle.greater(starting_point, threshold_image)\n",
    "\n",
    "cle.imshow(binary_segmented)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Measure bounding boxes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Label objects\n",
    "labels = cle.connected_components_labeling_box(binary_segmented)\n",
    "\n",
    "cle.imshow(labels, labels=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Bounding box widths [ 7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.\n",
      "  7.  7. 16.  7.  7. 10.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.\n",
      "  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.\n",
      "  7.  7.  7.  7.  9.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.\n",
      "  7.  7.  7.  7.  7.  7.  7.  7.  7. 18.  7.  7.  7.  9. 16.  7.  7.  7.\n",
      "  7. 15.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7. 17.  7.  7.  8.\n",
      "  7.  7.  7.  8.  7.  7.  7.]\n",
      "Bounding box heights [ 8.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.\n",
      "  7.  7.  8.  7.  7. 12.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.\n",
      "  7.  7.  7.  7.  7.  7.  7.  7.  7.  5.  7.  7.  7.  8.  7.  7.  7.  7.\n",
      "  7.  5.  7.  7.  7.  7.  7.  7.  7.  7.  8.  8.  7.  7.  7.  7.  7.  7.\n",
      "  7.  7.  7.  7.  7.  7.  7.  7.  7. 20.  7.  7.  7. 16. 11.  7.  7.  7.\n",
      "  7.  8.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  7.  8.  7.  7.  7.\n",
      "  7.  7.  7.  7.  7.  7.  7.]\n"
     ]
    }
   ],
   "source": [
    "# Derive statistics\n",
    "stats = cle.statistics_of_labelled_pixels(label_image=labels)\n",
    "\n",
    "print('Bounding box widths', stats['bbox_width'])\n",
    "print('Bounding box heights', stats['bbox_height'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The bounding box width and height should be approximately twice as large as the sigma used for bluring the image at the very beginning."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sigma 3\n"
     ]
    }
   ],
   "source": [
    "print(\"Sigma\", sigma)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}