{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# AURORA \n",
    "In this Notebook we will demonstrate how to use the AURORA package to perform segmentation on cancer metastasis in brain MRI.\n",
    "\n",
    "---\n",
    "## Getting Started\n",
    "\n",
    "#### This tutorial requires:\n",
    "\n",
    "   - Python 3.10+\n",
    "   \n",
    "#### Optional but recommended:\n",
    "   <!--CUDA 11.4+ (https://developer.nvidia.com/cuda-toolkit)-->\n",
    "   - GPU with CUDA support and at least 8GB of VRAM (*otherwise CPU can be used*) \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Das System kann den angegebenen Pfad nicht finden.\n"
     ]
    }
   ],
   "source": [
    "# Installations\n",
    "!pip install brainles_aurora matplotlib > /dev/null\n",
    "\n",
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you installed the packages and requirments on your own machine, you can skip this section and start from the import section.\n",
    "\n",
    "### Setup Colab environment (optional) \n",
    "Otherwise you can follow and execute the tutorial on your browser.\n",
    "In order to start working on the notebook, click on the following button, this will open this page in the Colab environment and you will be able to execute the code on your own (*Google account required*).\n",
    "\n",
    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/BrainLesion/tutorials/blob/main/AURORA/tutorial.ipynb\">\n",
    "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
    "</a>\n",
    "\n",
    "(EVA VERSION):\n",
    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/evamariie/tutorials/blob/main/AURORA/tutorial.ipynb\">\n",
    "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"\"/>\n",
    "</a>\n",
    "\n",
    "Now that you are visualizing the notebook in Colab, run the next cell to install the packages we will use. There are few things you should follow in order to properly set the notebook up:\n",
    "1. Warning: This notebook was not authored by Google. Click on 'Run anyway'.\n",
    "1. When the installation commands are done, there might be \"Restart runtime\" button at the end of the output. Please, click it."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you run the next cell in a Google Colab environment, it will **clone the 'tutorials' repository** in your google drive. This will create a **new folder** called \"tutorials\" in **your Google Drive**.\n",
    "All generated file will be created/uploaded to your Google Drive respectively.\n",
    "\n",
    "After the first execution of the next cell, you might receive some warnings and notifications, please follow these instructions:\n",
    "   - 'Permit this notebook to access your Google Drive files?' Click on 'Yes', and select your account.\n",
    "   - Google Drive for desktop wants to access your Google Account. Click on 'Allow'.\n",
    "\n",
    "Afterwards the \"tutorials\" folder has been created. You can navigate it through the lefthand panel in Colab. You might also have received an email that informs you about the access on your Google Drive."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "\n",
    "# Check if we are in google colab currently\n",
    "try:\n",
    "    import google.colab\n",
    "\n",
    "    colabFlag = True\n",
    "except ImportError as r:\n",
    "    colabFlag = False\n",
    "\n",
    "# Execute certain steps only if we are in a colab environment\n",
    "if colabFlag:\n",
    "    # Create a folder in your Google Drive\n",
    "    from google.colab import drive\n",
    "\n",
    "    drive.mount(\"/content/drive\")\n",
    "    # clone repository and set path\n",
    "    !git clone https://github.com/BrainLesion/tutorials.git /content/drive/MyDrive/tutorials\n",
    "    COLAB_BASE_PATH = \"/content/drive/MyDrive/tutorials/AURORA/\"\n",
    "    sys.path.insert(0, BASE_PATH)\n",
    "\n",
    "else:  # normal jupyter notebook environment\n",
    "    BASE_PATH = \"./\"  # current working directory would be BraTs-Toolkit anyways if you are not in colab"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from brainles_aurora.inferer import AuroraInferer, AuroraInfererConfig\n",
    "import nibabel as nib\n",
    "import numpy as np\n",
    "import torch\n",
    "import utils  # local file"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data\n",
    "\n",
    "AURORA expects *preprocessed* input data as NIfTI file or NumPy Array (*preprocessed* meaning the files should be co-registerend, skullstripped and in SRI-24 space).\n",
    "\n",
    "In this example we provide sample data from the [ASNR-MICCAI BraTS Brain Metastasis Challenge](https://www.synapse.org/#!Synapse:syn51156910/wiki/622553), which is already preprocessed in the `AURORA/data` folder in the form of 4 modalities of the same brain (T1, T1C, T2, FLAIR). To get an intuition of the data, one example slice of the 3D scans is visualized below.\n",
    "\n",
    "For your own data:\n",
    "If the data is *not* preprocessed yet, consider using our [BrainLes preprocessing](https://github.com/BrainLesion/preprocessing) package (or its predecessor [BraTS-Toolkit](https://github.com/neuronflow/BraTS-Toolkit)).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x720 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "utils.visualize_data(f\"{BASE_PATH}/data\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using AURORA"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Minimal example using default settings and only T1c as input"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | inferer         | L115  ] | 2024-03-14T00:46:43+0100: Initialized AuroraInferer with config: AuroraInfererConfig(log_level=20, device='cpu', cuda_devices='0', tta=False, sliding_window_batch_size=4, workers=0, threshold=0.5, sliding_window_overlap=0.5, crop_size=(192, 192, 32), model_selection=<ModelSelection.BEST: 'best'>)\n",
      "[INFO     | inferer         | L148  ] | 2024-03-14T00:46:43+0100: Set torch device: cpu\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #00ff00; text-decoration-color: #00ff00\">─────────────────────────────────────────── </span>Thank you for using <span style=\"font-weight: bold\">AURORA</span><span style=\"color: #00ff00; text-decoration-color: #00ff00\"> ────────────────────────────────────────────</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[92m─────────────────────────────────────────── \u001b[0mThank you for using \u001b[1mAURORA\u001b[0m\u001b[92m ────────────────────────────────────────────\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">                         Please support our development by citing the papers listed here:                          \n",
       "</pre>\n"
      ],
      "text/plain": [
       "                         Please support our development by citing the papers listed here:                          \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">                           <span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://github.com/BrainLesion/AURORA#citation</span> -- Thank you!                            \n",
       "</pre>\n"
      ],
      "text/plain": [
       "                           \u001b[4;94mhttps://github.com/BrainLesion/AURORA#citation\u001b[0m -- Thank you!                            \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #00ff00; text-decoration-color: #00ff00\">───────────────────────────────────────────────────────────────────────────────────────────────────────────────────</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[92m───────────────────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | inferer         | L191  ] | 2024-03-14T00:46:43+0100: Infer with config: AuroraInfererConfig(log_level=20, device='cpu', cuda_devices='0', tta=False, sliding_window_batch_size=4, workers=0, threshold=0.5, sliding_window_overlap=0.5, crop_size=(192, 192, 32), model_selection=<ModelSelection.BEST: 'best'>) and device: cpu\n",
      "[INFO     | data            | L138  ] | 2024-03-14T00:46:43+0100: Successfully validated input images (received 1). Input mode: NIFTI_FILEPATH\n",
      "[INFO     | data            | L160  ] | 2024-03-14T00:46:43+0100: Received files: T1: False, T1C: True, T2: False, FLAIR: False\n",
      "[INFO     | data            | L169  ] | 2024-03-14T00:46:43+0100: Inference mode: t1c-o\n",
      "[INFO     | model           | L58   ] | 2024-03-14T00:46:43+0100: No loaded compatible model found (Switching from None to t1c-o). Loading Model and weights...\n",
      "[INFO     | model           | L63   ] | 2024-03-14T00:46:43+0100: Successfully loaded model.\n",
      "[INFO     | inferer         | L206  ] | 2024-03-14T00:46:43+0100: Setting up Dataloader\n",
      "[INFO     | inferer         | L216  ] | 2024-03-14T00:46:44+0100: Running inference on device := cpu\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BasicUNet features: (32, 32, 64, 128, 256, 32).\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | model           | L205  ] | 2024-03-14T00:49:23+0100: Post-processing data\n",
      "[INFO     | model           | L209  ] | 2024-03-14T00:49:23+0100: Returning post-processed data as Dict of Numpy arrays\n",
      "[INFO     | inferer         | L218  ] | 2024-03-14T00:49:23+0100: Finished inference\n",
      "[INFO     | inferer         | L222  ] | 2024-03-14T00:49:23+0100: Saving post-processed data as NIfTI files\n",
      "[INFO     | data            | L263  ] | 2024-03-14T00:49:24+0100: Saved segmentation to .//output/t1c_segmentation.nii.gz\n",
      "[INFO     | inferer         | L226  ] | 2024-03-14T00:49:24+0100: ============================ Finished inference run ============================\n"
     ]
    }
   ],
   "source": [
    "# We first need to create an instance of the AuroraInfererConfig class,\n",
    "# which will hold the configuration for the inferer.\n",
    "# We can then create an instance of the AuroraInferer class, which will be used to perform the inference.\n",
    "\n",
    "config = AuroraInfererConfig(\n",
    "    tta=False,\n",
    "    # we disable test time augmentations for a quick demo\n",
    "    # should be set to True for better results\n",
    "    sliding_window_batch_size=4,\n",
    "    # The batch size used for the sliding window inference\n",
    "    # decrease if you run out of memory\n",
    "    # warning: too small batches might lead to unstable results\n",
    "    cuda_devices=\"0\",  # optional, if you have multiple GPUs you can specify which one to use\n",
    "    device=\"cpu\",  # uncomment this line to force-use CPU\n",
    ")\n",
    "\n",
    "\n",
    "# Now that we have the configuration we can create an instance of the AuroraInferer class.\n",
    "# This class will be used to perform the inference. We can then call the infer method to perform the inference.\n",
    "inferer = AuroraInferer(config=config)\n",
    "\n",
    "if torch.cuda.is_available() == False and colabFlag == True:\n",
    "    raise RuntimeWarning(\n",
    "        \"You are not using any GPU in Colab! Go to 'Runtime'->'Change Runtime type' to select GPU usage!\"\n",
    "    )\n",
    "\n",
    "# The infer method takes the path to the T1c MRI file and the path to the output segmentation file as arguments.\n",
    "# The output segmentation file will be created by the infer method and\n",
    "# will contain the segmentation of the input T1c MRI.\n",
    "\n",
    "# The example below shows how to perform the inference using a T1c MRI file:\n",
    "_ = inferer.infer(\n",
    "    t1c=f\"{BASE_PATH}/data/t1c.nii.gz\",\n",
    "    segmentation_file=f\"{BASE_PATH}/output/t1c_segmentation.nii.gz\",\n",
    ")\n",
    "\n",
    "# IMPORTANT: If this cell produces an OutOfMemoryError, you might not have enough VRAM (minimum 8GB).\n",
    "# Try using the CPU instead by setting \"useGPU\" to False above"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualize results\n",
    "\n",
    "The segementation comprise of the\n",
    "- **metastasis label** (in blue), consiting of contrast-enhancing metastasis and necrosis\n",
    "- T2-FLAIR hyperintense **edema label** (in red)  \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "utils.visualize_segmentation(\n",
    "    modality_file=f\"{BASE_PATH}/data/t1c.nii.gz\",\n",
    "    segmentation_file=f\"{BASE_PATH}/output/t1c_segmentation.nii.gz\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Multiple input modalities and other available outputs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "AURORA also supports different combinations of multi-modal MRI files [(see manuscript)](https://www.sciencedirect.com/science/article/pii/S016781402389795X). It will automatically select a suitable model depending on the inputs supplied.\n",
    "\n",
    "- Any of the following combination of sequences can be supplied: \n",
    "    - T1-CE only\n",
    "    - T1 only\n",
    "    - T2-FLAIR only\n",
    "    - T1-CE + T2-FLAIR\n",
    "    - T1-CE + T1\n",
    "    - T1-CE + T1 + T2-FLAIR\n",
    "    - T1-CE + T1 + T2 + T2-FLAIR \n",
    "  \n",
    "- For the last combination (with all 4 sequences), the [(vanilla model)](https://www.sciencedirect.com/science/article/pii/S0167814022045625) can also be used.\n",
    "\n",
    "- Instead of only saving the final output consisting of one file with 2 labels, additional files with labels for the whole lesion (metastasis + edema) or the metastasis only can also be saved.\n",
    "\n",
    "- Test-time augmentation can be enabled (tta parameter in config, default = True). Segmentation with TTA will take around 10 times longer than without TTA.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### The example below shows how to perform the inference using multi-modal inputs.\n",
    "*(This may take a while)*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | inferer         | L115  ] | 2024-03-14T00:49:24+0100: Initialized AuroraInferer with config: AuroraInfererConfig(log_level=20, device=<Device.AUTO: 'auto'>, cuda_devices='0', tta=True, sliding_window_batch_size=1, workers=0, threshold=0.5, sliding_window_overlap=0.5, crop_size=(192, 192, 32), model_selection=<ModelSelection.BEST: 'best'>)\n",
      "[INFO     | inferer         | L148  ] | 2024-03-14T00:49:24+0100: Set torch device: cpu\n",
      "[INFO     | inferer         | L115  ] | 2024-03-14T00:49:24+0100: Initialized AuroraInferer with config: AuroraInfererConfig(log_level=20, device='cpu', cuda_devices='0', tta=False, sliding_window_batch_size=4, workers=0, threshold=0.5, sliding_window_overlap=0.5, crop_size=(192, 192, 32), model_selection=<ModelSelection.BEST: 'best'>)\n",
      "[INFO     | inferer         | L148  ] | 2024-03-14T00:49:24+0100: Set torch device: cpu\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #00ff00; text-decoration-color: #00ff00\">─────────────────────────────────────────── </span>Thank you for using <span style=\"font-weight: bold\">AURORA</span><span style=\"color: #00ff00; text-decoration-color: #00ff00\"> ────────────────────────────────────────────</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[92m─────────────────────────────────────────── \u001b[0mThank you for using \u001b[1mAURORA\u001b[0m\u001b[92m ────────────────────────────────────────────\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">                         Please support our development by citing the papers listed here:                          \n",
       "</pre>\n"
      ],
      "text/plain": [
       "                         Please support our development by citing the papers listed here:                          \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">                           <span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://github.com/BrainLesion/AURORA#citation</span> -- Thank you!                            \n",
       "</pre>\n"
      ],
      "text/plain": [
       "                           \u001b[4;94mhttps://github.com/BrainLesion/AURORA#citation\u001b[0m -- Thank you!                            \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #00ff00; text-decoration-color: #00ff00\">───────────────────────────────────────────────────────────────────────────────────────────────────────────────────</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[92m───────────────────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | inferer         | L191  ] | 2024-03-14T00:49:24+0100: Infer with config: AuroraInfererConfig(log_level=20, device='cpu', cuda_devices='0', tta=False, sliding_window_batch_size=4, workers=0, threshold=0.5, sliding_window_overlap=0.5, crop_size=(192, 192, 32), model_selection=<ModelSelection.BEST: 'best'>) and device: cpu\n",
      "[INFO     | data            | L138  ] | 2024-03-14T00:49:24+0100: Successfully validated input images (received 4). Input mode: NIFTI_FILEPATH\n",
      "[INFO     | data            | L160  ] | 2024-03-14T00:49:24+0100: Received files: T1: True, T1C: True, T2: True, FLAIR: True\n",
      "[INFO     | data            | L169  ] | 2024-03-14T00:49:24+0100: Inference mode: t1-t1c-t2-fla\n",
      "[INFO     | model           | L58   ] | 2024-03-14T00:49:24+0100: No loaded compatible model found (Switching from None to t1-t1c-t2-fla). Loading Model and weights...\n",
      "[INFO     | model           | L63   ] | 2024-03-14T00:49:24+0100: Successfully loaded model.\n",
      "[INFO     | inferer         | L206  ] | 2024-03-14T00:49:24+0100: Setting up Dataloader\n",
      "[INFO     | inferer         | L216  ] | 2024-03-14T00:49:24+0100: Running inference on device := cpu\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BasicUNet features: (32, 32, 64, 128, 256, 32).\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | model           | L205  ] | 2024-03-14T00:52:00+0100: Post-processing data\n",
      "[INFO     | model           | L209  ] | 2024-03-14T00:52:00+0100: Returning post-processed data as Dict of Numpy arrays\n",
      "[INFO     | inferer         | L218  ] | 2024-03-14T00:52:00+0100: Finished inference\n",
      "[INFO     | inferer         | L222  ] | 2024-03-14T00:52:00+0100: Saving post-processed data as NIfTI files\n",
      "[INFO     | data            | L263  ] | 2024-03-14T00:52:00+0100: Saved segmentation to .//output/multi-modal_segmentation.nii.gz\n",
      "[INFO     | data            | L263  ] | 2024-03-14T00:52:00+0100: Saved whole_network to .//output/whole_tumor_unbinarized_floats.nii.gz\n",
      "[INFO     | data            | L263  ] | 2024-03-14T00:52:00+0100: Saved metastasis_network to .//output/metastasis_unbinarized_floats.nii.gz\n",
      "[INFO     | inferer         | L226  ] | 2024-03-14T00:52:00+0100: ============================ Finished inference run ============================\n"
     ]
    }
   ],
   "source": [
    "# Instantiate the AuroraInferer\n",
    "inferer = AuroraInferer()\n",
    "\n",
    "inferer = AuroraInferer(config=config)\n",
    "\n",
    "# Use all four input modalities,we also create other outputs and a custom log file\n",
    "_ = inferer.infer(\n",
    "    t1=f\"{BASE_PATH}/data/t1.nii.gz\",\n",
    "    t1c=f\"{BASE_PATH}/data/t1c.nii.gz\",\n",
    "    t2=f\"{BASE_PATH}/data/t2.nii.gz\",\n",
    "    fla=f\"{BASE_PATH}/data/flair.nii.gz\",\n",
    "    segmentation_file=f\"{BASE_PATH}/output/multi-modal_segmentation.nii.gz\",\n",
    "    # The unbinarized network outputs for the whole tumor channel (edema + enhancing tumor core + necrosis) channel\n",
    "    whole_tumor_unbinarized_floats_file=f\"{BASE_PATH}/output/whole_tumor_unbinarized_floats.nii.gz\",\n",
    "    # The unbinarized network outputs for the metastasis (tumor core) channel\n",
    "    metastasis_unbinarized_floats_file=f\"{BASE_PATH}/output/metastasis_unbinarized_floats.nii.gz\",\n",
    "    log_file=f\"{BASE_PATH}/output/custom_logfile.log\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### In case you have all 4 sequences (t1, t1c, t2, flair) available, you may also use the [(vanilla model)](https://www.sciencedirect.com/science/article/pii/S0167814022045625). \n",
    "\n",
    "\n",
    "<!-- Therefore, run the cell below. \n",
    "\n",
    "#TODO code vanilla model -->"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### NumPy Inputs/ Outputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | inferer         | L115  ] | 2024-03-14T00:52:00+0100: Initialized AuroraInferer with config: AuroraInfererConfig(log_level=20, device=<Device.AUTO: 'auto'>, cuda_devices='0', tta=True, sliding_window_batch_size=1, workers=0, threshold=0.5, sliding_window_overlap=0.5, crop_size=(192, 192, 32), model_selection=<ModelSelection.BEST: 'best'>)\n",
      "[INFO     | inferer         | L148  ] | 2024-03-14T00:52:00+0100: Set torch device: cpu\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #00ff00; text-decoration-color: #00ff00\">─────────────────────────────────────────── </span>Thank you for using <span style=\"font-weight: bold\">AURORA</span><span style=\"color: #00ff00; text-decoration-color: #00ff00\"> ────────────────────────────────────────────</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[92m─────────────────────────────────────────── \u001b[0mThank you for using \u001b[1mAURORA\u001b[0m\u001b[92m ────────────────────────────────────────────\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">                         Please support our development by citing the papers listed here:                          \n",
       "</pre>\n"
      ],
      "text/plain": [
       "                         Please support our development by citing the papers listed here:                          \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">                           <span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://github.com/BrainLesion/AURORA#citation</span> -- Thank you!                            \n",
       "</pre>\n"
      ],
      "text/plain": [
       "                           \u001b[4;94mhttps://github.com/BrainLesion/AURORA#citation\u001b[0m -- Thank you!                            \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #00ff00; text-decoration-color: #00ff00\">───────────────────────────────────────────────────────────────────────────────────────────────────────────────────</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[92m───────────────────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | inferer         | L191  ] | 2024-03-14T00:52:00+0100: Infer with config: AuroraInfererConfig(log_level=20, device=<Device.AUTO: 'auto'>, cuda_devices='0', tta=True, sliding_window_batch_size=1, workers=0, threshold=0.5, sliding_window_overlap=0.5, crop_size=(192, 192, 32), model_selection=<ModelSelection.BEST: 'best'>) and device: cpu\n",
      "[INFO     | data            | L138  ] | 2024-03-14T00:52:00+0100: Successfully validated input images (received 1). Input mode: NP_NDARRAY\n",
      "[INFO     | data            | L160  ] | 2024-03-14T00:52:00+0100: Received files: T1: True, T1C: False, T2: False, FLAIR: False\n",
      "[INFO     | data            | L169  ] | 2024-03-14T00:52:00+0100: Inference mode: t1-o\n",
      "[INFO     | model           | L58   ] | 2024-03-14T00:52:00+0100: No loaded compatible model found (Switching from None to t1-o). Loading Model and weights...\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BasicUNet features: (32, 32, 64, 128, 256, 32).\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO     | model           | L63   ] | 2024-03-14T00:52:01+0100: Successfully loaded model.\n",
      "[INFO     | inferer         | L206  ] | 2024-03-14T00:52:01+0100: Setting up Dataloader\n",
      "[INFO     | inferer         | L216  ] | 2024-03-14T00:52:01+0100: Running inference on device := cpu\n",
      "[INFO     | model           | L201  ] | 2024-03-14T00:54:27+0100: Applying test time augmentations\n",
      "[INFO     | model           | L205  ] | 2024-03-14T01:23:19+0100: Post-processing data\n",
      "[INFO     | model           | L209  ] | 2024-03-14T01:23:19+0100: Returning post-processed data as Dict of Numpy arrays\n",
      "[INFO     | inferer         | L218  ] | 2024-03-14T01:23:19+0100: Finished inference\n",
      "[INFO     | inferer         | L226  ] | 2024-03-14T01:23:19+0100: ============================ Finished inference run ============================\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['segmentation : (240, 240, 155)', 'whole_network : (240, 240, 155)', 'metastasis_network : (240, 240, 155)']\n"
     ]
    }
   ],
   "source": [
    "config = AuroraInfererConfig()\n",
    "\n",
    "# AuroraInferer(config=config)\n",
    "# If you do not have a GPU that supports CUDA use the CPU version (uncomment the line above, comment the GPU inferer)\n",
    "inferer = AuroraInferer(config=config)\n",
    "\n",
    "# we load the nifty data to a numpy array\n",
    "t1_np = nib.load(f\"{BASE_PATH}/data/t1.nii.gz\").get_fdata()\n",
    "\n",
    "# we can now use the inferer to perform the inference and obtain again a numpy array containing the segmentation\n",
    "results = inferer.infer(t1=t1_np)\n",
    "print([f\"{k} : {v.shape}\" for k, v in results.items()])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Example of application"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "metasis volume (including edema) 93711\n"
     ]
    }
   ],
   "source": [
    "# Now we can use the capabilities of numpy without having to re-read a nifti file.\n",
    "# For example we could compute the number of metastasis voxels (the volume of the metastasis) as follows:\n",
    "\n",
    "whole_metastasis_voxels = results[\"segmentation\"] > 0\n",
    "print(\"metasis volume (including edema)\", np.count_nonzero(whole_metastasis_voxels))"
   ]
  },
  {
   "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": "3.10.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}