{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Digital Slide Archive (DSA) Visualization Tutorial"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Welcome to the Digial Slide Archive (DSA) visualization notebook! \n",
    "\n",
    "Digital Slide Archive (DSA) is a platform where you can manage your pathology images and annotations. A set of CLIs are available to help you convert your pathologist or model-generated annotations and push them to DSA. For more details on the DSA platform, please refer to their [documentation](https://digitalslidearchive.github.io/digital_slide_archive/documentation/).\n",
    "\n",
    "In this notebook, we will use **dsa_viz** and **dsa_upload** CLIs to convert your annotations to a DSA compatible format and to upload them to DSA. We support results from [Qupath/Stardist dectection models](https://github.com/msk-mind/docker/tree/master/qupath), tile scores in a tabular format, and also expert annotations in geojson format. Here are the steps we will review:\n",
    "\n",
    "- Setup DSA\n",
    "- DSA Visuzaliation CLIs\n",
    "- Upload Slidveiewer regional annotations\n",
    "- Upload Qupath regional annotation results\n",
    "- Upload a heatmap generated from tile scores\n",
    "- Upload bitmasks PNGs\n",
    "- Upload Stardist object detection results\n",
    "- Upload Stardist cell detection results\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup DSA"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Before running this notebook, make sure you have your pathology slides organized in DSA under a collection/folder.\n",
    "\n",
    "For one of our examples, we use an SVS image from TCGA. This image file in *tcga* collection, in *slides* folder on the DSA platform.\n",
    "\n",
    "![DSA Organization Screenshot](img/dsa-organization-screenshot.png)\n",
    "\n",
    "The collection name (e.g. tcga) and image file name (e.g. TCGA-GM-A2DB-01Z-00-DX1.9EE36AA6-2594-44C7-B05C-91A0AEC7E511.svs) on DSA will be used while uploading the annotations.\n",
    "\n",
    "Be sure to modify the configuration files based on your DSA setup."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## DSA Visualization CLIs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Luna-pathology offers 2 CLIs to help convert your annotation results to a DSA compatible json format and to upload them to DSA. The conversion and upload is divided in to 2 separate steps, so each step can be parallelized based on your computing capabilities and DSA platform setup. \n",
    "\n",
    "`dsa_viz` CLI takes two inputs, and generates a DSA compatible annotation json.\n",
    "- *source_type* - describes the data source\n",
    "- *data_config* - a file detailing the input, output and visualization details\n",
    "\n",
    "`dsa_upload` CLI takes two inputs, and uploads the DSA compatible annotation json.\n",
    "- *config* - a file with DSA instance information\n",
    "We use a DSA token to push annotations to the platform. Make sure this token is generated via the HistomicsUI API (/api/v1/token/current) for the user with edit permission on the slides. HistomicsUI is the high-magnification viewer part DSA platform.\n",
    "- *data_confi*g - a file specifying the path to the DSA compatible annotation json and the collection/image file name from DSA. \n",
    "\n",
    "Once upload is done, we print the link to HistomicsUI viewer, so you can easily navigate to the uploaded annotation result.\n",
    "\n",
    "*Note: Pushing and rendering a large number of annotation elements can take a long time. Please refer to DSA [documentation](https://digitalslidearchive.github.io/HistomicsTK/examples/tips_for_scalable_annotation_rendering), for user expectations and some tricks for managing annotations.*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Usage: dsa_viz [OPTIONS]\n",
      "\n",
      "  DSA annotation builder\n",
      "\n",
      "Options:\n",
      "  -d, --data_config PATH  path to data config file  [required]\n",
      "  -s, --source_type TEXT  string describing data source that is to be\n",
      "                          transformed into a dsa json.                supports\n",
      "                          stardist-polygon, stardist-cell, regional-polygon,\n",
      "                          qupath-polygon, bitmask-polygon, heatmap  [required]\n",
      "\n",
      "  --help                  Show this message and exit.\n"
     ]
    }
   ],
   "source": [
    "!dsa_viz --help"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Usage: dsa_upload [OPTIONS]\n",
      "\n",
      "  DSA Annotation Upload CLI\n",
      "\n",
      "Options:\n",
      "  -c, --config PATH       json including DSA host, port and token info\n",
      "                          [required]\n",
      "\n",
      "  -d, --data_config PATH  path to data config file  [required]\n",
      "  --help                  Show this message and exit.\n"
     ]
    }
   ],
   "source": [
    "!dsa_upload --help"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Upload Slideviewer regional annotations"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Regional annotations made by expert pathologists are stored in our databases in a GeoJSON format that is compatible with many downstream analysis tools.\n",
    "\n",
    "With **regional-polygon** option, we can convert the GeoJSON annotations to DSA json annotation format, and upload the annotation to the DSA platform."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# Path to regional annotation in GeoJSON format  \n",
      "input: ./input/regional_annotation.json\n",
      "\n",
      "# image file name from DSA\n",
      "image_filename: 2551571.svs\n",
      "  \n",
      "# path to write converted json annotations\n",
      "output_folder: ./dsa_annotations/\n",
      "\n",
      "# annotation name to be shown in DSA  \n",
      "annotation_name: Regional Annotation\n",
      "\n",
      "# line and fill colors in label:rgb/a format\n",
      "line_colors:\n",
      "  lympho_rich_tumor: rgb(0,191,255)\n",
      "  lympho_poor_tumor: rgb(0,255,0)\n",
      "  necrosis: rgb(255,255,0)\n",
      "  lympho_rich_stroma: rgb(255,0,0)\n",
      "  veins: rgb(0,255,255)\n",
      "  adipocytes: rgb(0,0,255)\n",
      "  qc_tissue_fold: rgb(0,0,0)\n",
      "  \n",
      "fill_colors:\n",
      "  lympho_rich_tumor: rgb(0,191,255,100)\n",
      "  lympho_poor_tumor: rgb(0,255,0,100)\n",
      "  necrosis: rgb(255,255,0,100)\n",
      "  lympho_rich_stroma: rgb(255,0,0,100)\n",
      "  veins: rgb(0,255,255,100)\n",
      "  adipocytes: rgb(0,0,255,100)\n",
      "  qc_tissue_fold: rgb(0,0,0,100)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# example data_config\n",
    "!cat configs/dsa_configs/regional_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Building annotation for image: 2551571.svs\n",
      "Time to build annotation 0.0010259151458740234\n",
      "Annotation written to ./dsa_annotations/Regional_Annotation_2551571.json\n"
     ]
    }
   ],
   "source": [
    "# generate DSA annotation\n",
    "!dsa_viz -s regional-polygon -d configs/dsa_configs/regional_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully connected to DSA.\n",
      "collection_id_dict {'_accessLevel': 2, '_id': '60807410150bd39c9df579cf', '_modelType': 'collection', '_textScore': 15.75, 'created': '2021-04-21T18:50:56.730000+00:00', 'description': 'test images', 'meta': {}, 'name': 'test-path', 'public': True, 'publicFlags': [], 'size': 2350018806, 'updated': '2021-04-21T18:50:56.730000+00:00'}\n",
      "Collection test-path found with id: 60807410150bd39c9df579cf\n",
      "Annotation successfully pushed to DSA.\n",
      "Time to push annotation 0.020156383514404297\n",
      "http://localhost:8080/histomics#?image=610aedc9150bd39c9d7adadd\n"
     ]
    }
   ],
   "source": [
    "# push annotation to DSA\n",
    "!dsa_upload -c dsa_configs/dsa_config.yaml -d configs/dsa_configs/regional_upload.yaml"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Upload a heatmap generated from tile scores"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**heatmap** option provides means to visualize your tile scores from your classification model.\n",
    "\n",
    "The input here is a CSV file with a column of (0, 1) range and the tile coordinates. In this example, we visualize the \"otsu_score\" column.\n",
    "\n",
    "We use the color palette \"viridis\" where the output color ranges from purple to yellow, for scores from 0 to 1."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "address,coordinates,otsu_score,purple_score\n",
      "x1_y1_z10,\"(1, 1)\",0.03125,0.03125\n",
      "x1_y2_z10,\"(1, 2)\",0.0,0.0\n",
      "x1_y3_z10,\"(1, 3)\",0.0,0.0546875\n",
      "x1_y4_z10,\"(1, 4)\",0.0,0.0\n"
     ]
    }
   ],
   "source": [
    "# example CSV\n",
    "!head -5 input/tile_scores_and_labels.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# path to CSV containing tile coordinates and tile scores\n",
      "input: input/tile_scores_and_labels.csv\n",
      "\n",
      "# image file name from DSA\n",
      "image_filename: TCGA-GM-A2DB-01Z-00-DX1.9EE36AA6-2594-44C7-B05C-91A0AEC7E511.svs\n",
      "\n",
      "# path to write converted json annotations\n",
      "output_folder: ./dsa_annotations/\n",
      "\n",
      "# column in CSV with value range (0, 1)\n",
      "column: otsu_score\n",
      "\n",
      "# annotation name to be shown in DSA\n",
      "annotation_name: tile-based heatmap\n",
      "\n",
      "# size of the tiles\n",
      "tile_size: 128\n",
      "\n",
      "# scale to match the image on DSA\n",
      "scale_factor: 4\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# example data_config\n",
    "!cat configs/dsa_configs/heatmap_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Building annotation for image: TCGA-GM-A2DB-01Z-00-DX1.9EE36AA6-2594-44C7-B05C-91A0AEC7E511.svs\n",
      "Annotation written to ./dsa_annotations/otsu_score_tile-based_heatmap_TCGA-GM-A2DB-01Z-00-DX1.9EE36AA6-2594-44C7-B05C-91A0AEC7E511.json\n"
     ]
    }
   ],
   "source": [
    "# generate DSA annotation\n",
    "!dsa_viz -s heatmap -d configs/dsa_configs/heatmap_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Usage: dsa_upload [OPTIONS]\n",
      "Try 'dsa_upload --help' for help.\n",
      "\n",
      "Error: Invalid value for '-c' / '--config': Path 'dsa_configs/dsa_config.yaml' does not exist.\n"
     ]
    }
   ],
   "source": [
    "# push annotation to DSA\n",
    "!dsa_upload -c dsa_configs/dsa_config.yaml -d configs/dsa_configs/heatmap_upload.yaml"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Upload bitmasks PNGs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Simple PNG bitmasks can also be visualized in DSA. Use **bitmask-polygon** option and provide pngs with the corresponding labels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# paths to bitmask png images in label:path format\n",
      "input:\n",
      "  Tumor: /gpfs/mskmindhdp_emc/user/shared_data_folder/ov-mind-project/input/Tumor.png\n",
      "  Fat: /gpfs/mskmindhdp_emc/user/shared_data_folder/ov-mind-project/input/Fat.png\n",
      "  Necrosis: /gpfs/mskmindhdp_emc/user/shared_data_folder/ov-mind-project/input/Necrosis.png\n",
      "  Stroma: /gpfs/mskmindhdp_emc/user/shared_data_folder/ov-mind-project/input/Stroma.png\n",
      "\n",
      "# image file name from DSA\n",
      "image_filename: HobI16-670289739721.svs\n",
      "\n",
      "# path to write converted json annotations\n",
      "output_folder: ./dsa_annotations/\n",
      "\n",
      "# annotation name to be shown in DSA\n",
      "annotation_name: Full Res Tile-Based Pixel Classifier Inference,\n",
      "\n",
      "# line and fill colors in label:rgb/a format\n",
      "line_colors:\n",
      "  Stroma: rgb(0,191,255)\n",
      "  Tumor: rgb(0,255,0)\n",
      "  Fat: rgb(255,255,0)\n",
      "  Necrosis: rgb(255,0,0)\n",
      "\n",
      "fill_colors:\n",
      "  Stroma: rgba(0,191,255, 100)\n",
      "  Tumor: rgba(0,255,0, 100)\n",
      "  Fat: rgba(255,255,0, 100)\n",
      "  Necrosis: rgba(255,0,0, 100)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# example data_config\n",
    "!cat configs/dsa_configs/bitmask_polygon_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Building annotation for image: HobI16-670289739721.svs\n",
      "Time to build annotation 138.78823733329773\n",
      "Annotation written to ./dsa_annotations/Full_Res_Tile-Based_Pixel_Classifier_Inference_HobI16-670289739721.json\n"
     ]
    }
   ],
   "source": [
    "# generate DSA annotation\n",
    "!dsa_viz -s bitmask-polygon -d configs/dsa_configs/bitmask_polygon_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully connected to DSA.\n",
      "collection_id_dict {'_accessLevel': 2, '_id': '60807410150bd39c9df579cf', '_modelType': 'collection', '_textScore': 15.75, 'created': '2021-04-21T18:50:56.730000+00:00', 'description': 'test images', 'meta': {}, 'name': 'test-path', 'public': True, 'publicFlags': [], 'size': 936444465, 'updated': '2021-04-21T18:50:56.730000+00:00'}\n",
      "Collection test-path found with id: 60807410150bd39c9df579cf\n",
      "Annotation successfully pushed to DSA.\n",
      "Time to push annotation 0.11921572685241699\n",
      "http://localhost:8080/histomics#?image=60807ad8150bd39c9df579d2\n"
     ]
    }
   ],
   "source": [
    "# push annotation to DSA\n",
    "!dsa_upload -c dsa_configs/dsa_config.yaml -d configs/dsa_configs/bitmask_upload.yaml"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Upload Qupath regional annotation results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Regional annotations generated by [Qupath](https://qupath.github.io/) includes regional polygons from object detection along with nuclear properties.\n",
    "\n",
    "For object and cell detection models in QuPath, please checkout our [Qupath/Stardist docker](https://github.com/msk-mind/docker/tree/master/qupath)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# path to geojson file generated by Qupath\n",
      "input: input/qupath_annotation_results.json\n",
      "\n",
      "# image file name from DSA\n",
      "image_filename: HobI20-681330526186.svs\n",
      "\n",
      "# path to write converted json annotations  \n",
      "output_folder: ./dsa_annotations/\n",
      "  \n",
      "# annotation name to be shown in DSA\n",
      "annotation_name: Qupath Pixel Classifier Polygons\n",
      "\n",
      "# labels to visualize\n",
      "classes_to_include:\n",
      "- Adipocytes\n",
      "- Stroma\n",
      "- Necrosis\n",
      "- Tumor\n",
      "- Other\n",
      "  \n",
      "# line and fill colors in label:rgb/a format\n",
      "line_colors: \n",
      "  Stroma: rgb(0, 191, 255)\n",
      "  Tumor: rgb(0, 255, 0)\n",
      "  Adipocytes: rgb(255, 255, 0)\n",
      "  Necrosis: rgb(255, 0, 0)\n",
      "\n",
      "fill_colors:\n",
      "  Stroma: rgba(0, 191, 255, 100)\n",
      "  Tumor: rgba(0, 255, 0, 100)\n",
      "  Adipocytes: rgba(255, 255, 0, 100)\n",
      "  Necrosis: rgba(255, 0, 0, 100)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# example data_config\n",
    "!cat configs/dsa_configs/qupath_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Building annotation for image: HobI20-681330526186.svs\n",
      "Time to build annotation 0.0030074119567871094\n",
      "Annotation written to ./dsa_annotations/Qupath_Pixel_Classifier_Polygons_HobI20-681330526186.json\n"
     ]
    }
   ],
   "source": [
    "# generate DSA annotation\n",
    "!dsa_viz -s qupath-polygon -d configs/dsa_configs/qupath_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully connected to DSA.\n",
      "collection_id_dict {'_accessLevel': 2, '_id': '60807410150bd39c9df579cf', '_modelType': 'collection', '_textScore': 15.75, 'created': '2021-04-21T18:50:56.730000+00:00', 'description': 'test images', 'meta': {}, 'name': 'test-path', 'public': True, 'publicFlags': [], 'size': 2350018806, 'updated': '2021-04-21T18:50:56.730000+00:00'}\n",
      "Collection test-path found with id: 60807410150bd39c9df579cf\n",
      "Annotation successfully pushed to DSA.\n",
      "Time to push annotation 0.0221097469329834\n",
      "http://localhost:8080/histomics#?image=60807ad8150bd39c9df579d2\n"
     ]
    }
   ],
   "source": [
    "# push annotation to DSA\n",
    "!dsa_upload -c dsa_configs/dsa_config.yaml -d configs/dsa_configs/qupath_upload.yaml"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Upload Stardist object detection results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Stardist is a nuclear segmentation algorithm that is quite capable in detecting and segmenting cells/nuclei in pathology images. **stardist-polygon** option converts Stardist object detection results as polygons capturing different types of cells.\n",
    "\n",
    "*Note: this command can take a few minutes if object detection is run on the whole slide.*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# regional annotation in GeoJSON format generated by Stardist\n",
      "input: input/object_detection_results.geojson\n",
      "\n",
      "# image file name from DSA\n",
      "image_filename: HobI20-681330526186.svs\n",
      "\n",
      "# path to write converted json annotations  \n",
      "output_folder: ./dsa_annotations/\n",
      "  \n",
      "# annotation name to be shown in DSA\n",
      "annotation_name: StarDist Segmentations with Lymphocyte Classifications\n",
      "  \n",
      "# line and fill colors in label:rgb/a format\n",
      "line_colors:\n",
      "  Other: rgb(0, 255, 0)\n",
      "  Lymphocyte: rgb(255, 0, 0)\n",
      "\n",
      "fill_colors:\n",
      "  Other: rgba(0, 255, 0, 100)\n",
      "  Lymphocyte: rgba(255, 0, 0, 100)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# example data_config\n",
    "!cat configs/dsa_configs/stardist_polygon_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Building annotation for image: HobI20-681330526186.svs\n",
      "Time to build annotation 251.02770948410034\n",
      "Annotation written to ./dsa_annotations/StarDist_Segmentations_with_Lymphocyte_Classifications_HobI20-681330526186.json\n"
     ]
    }
   ],
   "source": [
    "# generate DSA annotation\n",
    "!dsa_viz -s stardist-polygon -d configs/dsa_configs/stardist_polygon_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully connected to DSA.\n",
      "collection_id_dict {'_accessLevel': 2, '_id': '60807410150bd39c9df579cf', '_modelType': 'collection', '_textScore': 15.75, 'created': '2021-04-21T18:50:56.730000+00:00', 'description': 'test images', 'meta': {}, 'name': 'test-path', 'public': True, 'publicFlags': [], 'size': 936444465, 'updated': '2021-04-21T18:50:56.730000+00:00'}\n",
      "Collection test-path found with id: 60807410150bd39c9df579cf\n",
      "Annotation successfully pushed to DSA.\n",
      "Time to push annotation 584.9241287708282\n",
      "http://localhost:8080/histomics#?image=60807ad8150bd39c9df579d2\n"
     ]
    }
   ],
   "source": [
    "# push annotation to DSA\n",
    "!dsa_upload -c dsa_configs/dsa_config.yaml -d configs/dsa_configs/stardist_polygon_upload.yaml"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is a screenshot form HistomicsUI, the high-magnification viewer. You can zoom in and view your annotation results with the desired opacity. As specified in `dsa_configs/stardist_polygon_config.yaml`, the red objects are classified as lymphocytes and the green cells are \"other\" cells.\n",
    "\n",
    "![Stardist Polygon Screenshot](img/stardist-polygon-screenshot.png)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Upload Stardist cell detection results\n",
    "\n",
    "Here we use cellular detection results generated from Stardist. The x,y coordinates of the cells in the input TSV file will be visualized as a point, as opposed to a more complex polygon that we saw in the previous step with **stardist-polygon**. You'll notice that the point annotation is faster to upload compared to the polygon represenation of the cells.\n",
    "\n",
    "We also set fill color alpha value to 0 makes annotation upload faster."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# TSV with cell coordinates generated by Stardist  \n",
      "input: input/object_detection_results.tsv\n",
      "  \n",
      "# image file name from DSA\n",
      "image_filename: HobI20-681330526186.svs\n",
      "\n",
      "# path to write converted json annotations\n",
      "annotation_name: Points of Classsified StarDist Cells\n",
      "\n",
      "# annotation name to be shown in DSA  \n",
      "output_folder: ./dsa_annotations/\n",
      "  \n",
      "# line and fill colors in label:rgb/a format\n",
      "line_colors:\n",
      "  Other: rgb(0, 255, 0)\n",
      "  Lymphocyte: rgb(255, 0, 0)\n",
      "\n",
      "fill_colors:\n",
      "  Other: rgba(0, 255, 0, 0)\n",
      "  Lymphocyte: rgba(255, 0, 0, 0)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# example data_config\n",
    "!cat configs/dsa_configs/stardist_cell_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Building annotation for image: HobI20-681330526186.svs\n",
      "Time to build annotation 90.03980946540833\n",
      "Annotation written to ./dsa_annotations/Points_of_Classsified_StarDist_Cells_HobI20-681330526186.json\n"
     ]
    }
   ],
   "source": [
    "# generate DSA annotation\n",
    "!dsa_viz -s stardist-cell -d configs/dsa_configs/stardist_cell_config.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully connected to DSA.\n",
      "collection_id_dict {'_accessLevel': 2, '_id': '60807410150bd39c9df579cf', '_modelType': 'collection', '_textScore': 15.75, 'created': '2021-04-21T18:50:56.730000+00:00', 'description': 'test images', 'meta': {}, 'name': 'test-path', 'public': True, 'publicFlags': [], 'size': 936444465, 'updated': '2021-04-21T18:50:56.730000+00:00'}\n",
      "Collection test-path found with id: 60807410150bd39c9df579cf\n",
      "Annotation successfully pushed to DSA.\n",
      "Time to push annotation 202.15096521377563\n",
      "http://localhost:8080/histomics#?image=60807ad8150bd39c9df579d2\n"
     ]
    }
   ],
   "source": [
    "# push annotation to DSA\n",
    "!dsa_upload -c dsa_configs/dsa_config.yaml -d configs/dsa_configs/stardist_cell_upload.yaml"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Below is another screenshot from HistomicsUI, from the link printed above. The results are the same as **stardist-polygon** visualization. Notice the cells are captured more minimally as circles, and not polygons. For rapid prototyping, **stardist-cell** offers faster annotation upload speed compared to **stardist-polygon**.\n",
    "\n",
    "![Stardist Cell Screenshot](img/stardist-cell-screenshot.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Congratulations! Now you can visualize your annotations and results on DSA platform."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}