rsna-lumbar-keyfunctions.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d7646028",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-07-12T23:51:25.707575Z",
     "iopub.status.busy": "2024-07-12T23:51:25.706527Z",
     "iopub.status.idle": "2024-07-12T23:51:26.878767Z",
     "shell.execute_reply": "2024-07-12T23:51:26.877695Z"
    },
    "papermill": {
     "duration": 1.18035,
     "end_time": "2024-07-12T23:51:26.881240",
     "exception": false,
     "start_time": "2024-07-12T23:51:25.700890",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import cv2\n",
    "import os\n",
    "from tqdm import tqdm\n",
    "\n",
    "import pydicom\n",
    "import numpy as np\n",
    "import glob"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae747d92",
   "metadata": {
    "papermill": {
     "duration": 0.00321,
     "end_time": "2024-07-12T23:51:26.888405",
     "exception": false,
     "start_time": "2024-07-12T23:51:26.885195",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# 1. Metadata object (highest level) (run once)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "af8f57a4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-07-12T23:51:26.897239Z",
     "iopub.status.busy": "2024-07-12T23:51:26.896736Z",
     "iopub.status.idle": "2024-07-12T23:51:35.690211Z",
     "shell.execute_reply": "2024-07-12T23:51:35.689121Z"
    },
    "papermill": {
     "duration": 8.800707,
     "end_time": "2024-07-12T23:51:35.692511",
     "exception": false,
     "start_time": "2024-07-12T23:51:26.891804",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 1975/1975 [00:08<00:00, 227.60it/s]\n"
     ]
    }
   ],
   "source": [
    "df_train_series_descriptions = pd.read_csv(\"/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_series_descriptions.csv\")\n",
    "folder_train_images = os.listdir(\"/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_images\")\n",
    "# exclude .DS_store files\n",
    "folder_train_images = list(filter(lambda x: x.find('.DS') == -1, folder_train_images))\n",
    "\n",
    "def get_metadata_object(folder_images, df_series_descriptions):\n",
    "    '''\n",
    "    for intially the train_images folder and train_series_descriptions.csv,\n",
    "    later for the test_images folder and test_series_description.csv\n",
    "    '''\n",
    "    \n",
    "    # a list of tuples like (study_id, study_id's path location)\n",
    "    images_study_id_dirs = [(int(study_id),    # integer the study_id\n",
    "                                   f\"/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_images/{study_id}\") \n",
    "                                  for study_id in folder_images]\n",
    "\n",
    "    # convert the list of tuples into dictionary/metadata\n",
    "    metadata_object = {study_id: {'study_id_folder_path': path, \n",
    "                                    'SeriesInstanceUIDs': [],\n",
    "                                    'SeriesDescriptions': []\n",
    "                                 }\n",
    "                       for study_id, path in images_study_id_dirs\n",
    "                      }\n",
    "\n",
    "    # remove all the .DS files/folders (MacOS) from SeriesInstanceUIDs or series_ids folders\n",
    "    # then put the names for series_ids as well as the corresponding description to metadata\n",
    "    for study_id in tqdm(metadata_object):\n",
    "\n",
    "        # SERIES_ID\n",
    "        # get all series directories/folders inside each study_id directory\n",
    "        series_ids_dirs = os.listdir(metadata_object[study_id]['study_id_folder_path'])\n",
    "        filtered_series_ids_dirs = [int(x) for x in series_ids_dirs if x.find('.DS') == -1]   # integer(series_id)\n",
    "        # put to metadata_object\n",
    "        metadata_object[study_id]['SeriesInstanceUIDs'] = filtered_series_ids_dirs\n",
    "\n",
    "        # SERIES_DESCRIPTIONS\n",
    "        series_desc_df = df_series_descriptions[df_series_descriptions.study_id==study_id][[\"series_id\", \"series_description\"]]\n",
    "        for series_id in metadata_object[study_id]['SeriesInstanceUIDs']:\n",
    "\n",
    "            series_desc_list = series_desc_df[series_desc_df.series_id==series_id].series_description.values\n",
    "\n",
    "            if len(series_desc_list) == 0:\n",
    "                metadata_object[study_id]['SeriesDescriptions'].append(\"\")\n",
    "            else:\n",
    "                metadata_object[study_id]['SeriesDescriptions'].append(series_desc_list[0])\n",
    "                \n",
    "    return metadata_object\n",
    "\n",
    "metadata_object_train = get_metadata_object(folder_train_images, df_train_series_descriptions)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17220f57",
   "metadata": {
    "papermill": {
     "duration": 0.008548,
     "end_time": "2024-07-12T23:51:35.710085",
     "exception": false,
     "start_time": "2024-07-12T23:51:35.701537",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# 2. Metadata object for series for each study_id\n",
    "\n",
    "### remember: each image instance has its own metadata for id and dicom\n",
    "\n",
    "<br>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "9c42a16a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-07-12T23:51:35.729450Z",
     "iopub.status.busy": "2024-07-12T23:51:35.729060Z",
     "iopub.status.idle": "2024-07-12T23:51:35.738295Z",
     "shell.execute_reply": "2024-07-12T23:51:35.737212Z"
    },
    "papermill": {
     "duration": 0.021537,
     "end_time": "2024-07-12T23:51:35.740438",
     "exception": false,
     "start_time": "2024-07-12T23:51:35.718901",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "def get_series_metadata_object_given_study_id(metadata_object, study_id):\n",
    "    \"\"\"\n",
    "    one study_id can have many series => this func gets all series metadata for this \n",
    "    particular study_id\n",
    "    \"\"\"\n",
    "    \n",
    "    metadata_for_study_id = metadata_object[study_id]\n",
    "    \n",
    "    series_metadata_object_given_study_id = {}\n",
    "\n",
    "    for idx, series_id in enumerate(metadata_for_study_id[\"SeriesInstanceUIDs\"]):\n",
    "\n",
    "        # create bases for the series_images_metadata: each series contains desc and images files\n",
    "        series_metadata_object_given_study_id[series_id] = {'image_series_description': metadata_for_study_id[\"SeriesDescriptions\"][idx], \n",
    "                                                            'image_files': []\n",
    "                                                            }\n",
    "\n",
    "        # glob for patten matching as we want to get image files ending with .dcm\n",
    "        folder_path_study_id = metadata_for_study_id[\"study_id_folder_path\"]\n",
    "        # rmb: \"SeriesInstancesUIDs\" is just a list of images and series_id is the actual series-id\n",
    "        image_files = glob.glob(f\"{folder_path_study_id}/{series_id}/*.dcm\")\n",
    "\n",
    "\n",
    "        # inside image_files, create a metadata for id_image and corresponding dicom readable image file\n",
    "        sorted_image_files = sorted(image_files, key = lambda x: int(x.split('/')[-1].replace('.dcm', '')))\n",
    "\n",
    "        \n",
    "        # iterate through all image files (sorting to make sense, not very necessarily)\n",
    "        for image_file in sorted_image_files:\n",
    "            \n",
    "            dicom_image_id = image_file.split('/')[-1].replace(\".dcm\", '')\n",
    "            dicom_image_read = pydicom.dcmread(image_file)\n",
    "            \n",
    "            # metadata for one image instance\n",
    "            one_image_metadata = {\"SOPInstanceUID\": dicom_image_id,      # id of the dicom image instance file\n",
    "                                  \"dicom_image_file\": dicom_image_read}  # actual read of the dcm instance file\n",
    "\n",
    "            # append this image_metadata to list of image_files\n",
    "            series_metadata_object_given_study_id[series_id][\"image_files\"].append(one_image_metadata)\n",
    "\n",
    "    return series_metadata_object_given_study_id\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8f8b1457",
   "metadata": {
    "papermill": {
     "duration": 0.008806,
     "end_time": "2024-07-12T23:51:35.758376",
     "exception": false,
     "start_time": "2024-07-12T23:51:35.749570",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# 3. Display normal images for one study_id"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6592ca39",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-07-12T23:51:35.777858Z",
     "iopub.status.busy": "2024-07-12T23:51:35.777272Z",
     "iopub.status.idle": "2024-07-12T23:51:35.787526Z",
     "shell.execute_reply": "2024-07-12T23:51:35.786356Z"
    },
    "papermill": {
     "duration": 0.022422,
     "end_time": "2024-07-12T23:51:35.789649",
     "exception": false,
     "start_time": "2024-07-12T23:51:35.767227",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    " def display_images_given_study_id(metadata_object, study_id): \n",
    "    '''\n",
    "    inside there is another function specifically for this function\n",
    "    '''\n",
    "    \n",
    "    # view images for this study_id = 4003253 for a particular series_description\n",
    "    def display_images(image_files, series_description, max_images_per_row=5):\n",
    "\n",
    "        # grid for display\n",
    "        num_images = len(image_files)\n",
    "        num_rows = (num_images + max_images_per_row - 1) // max_images_per_row  # ceiling division (ignore the remainder, extra)\n",
    "\n",
    "        # subplot grid\n",
    "        fig, axes = plt.subplots(nrows=num_rows, ncols=max_images_per_row)\n",
    "\n",
    "        # flatten axes for easy looping if there are multiple rows\n",
    "        if num_rows > 1:\n",
    "            axes = axes.flatten()\n",
    "        else:\n",
    "            axes = [axes] # iterable for consistency\n",
    "\n",
    "        # plot each image\n",
    "        for idx, image_file in enumerate(image_files):\n",
    "            ax = axes[idx]\n",
    "            ax.imshow(image_file, cmap='gray') # Assuming grayscale for simplicity, change cmap as needed\n",
    "            ax.axis('off')\n",
    "\n",
    "        # turn off unused subplots\n",
    "        for idx in range(num_images, len(axes)):\n",
    "            axes[idx].axis(\"off\")\n",
    "\n",
    "        fig.suptitle(series_description, fontsize=12)\n",
    "        plt.show()\n",
    "        \n",
    "        \n",
    "        \n",
    "    series_metadata_object = get_series_metadata_object_given_study_id(metadata_object, study_id)\n",
    "    \n",
    "    for series_id in series_metadata_object:\n",
    "\n",
    "        series_description = series_metadata_object[series_id][\"image_series_description\"]\n",
    "\n",
    "        # get the image_files for this particular series_id\n",
    "        image_files = series_metadata_object[series_id][\"image_files\"]\n",
    "\n",
    "        # get the dicom files to a list\n",
    "        dicom_images = []\n",
    "        for image_metadata in image_files:\n",
    "            dicom_image = image_metadata['dicom_image_file'].pixel_array\n",
    "            dicom_images.append(dicom_image)\n",
    "\n",
    "        # display images for each series\n",
    "        display_images(dicom_images, series_description)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc930f3a",
   "metadata": {
    "papermill": {
     "duration": 0.008612,
     "end_time": "2024-07-12T23:51:35.807404",
     "exception": false,
     "start_time": "2024-07-12T23:51:35.798792",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Display images with coordinated pathologies for one study_id"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7c811d12",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-07-12T23:51:35.827853Z",
     "iopub.status.busy": "2024-07-12T23:51:35.827430Z",
     "iopub.status.idle": "2024-07-12T23:51:36.493259Z",
     "shell.execute_reply": "2024-07-12T23:51:36.492133Z"
    },
    "papermill": {
     "duration": 0.679602,
     "end_time": "2024-07-12T23:51:36.495806",
     "exception": false,
     "start_time": "2024-07-12T23:51:35.816204",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "coord_df = pd.read_csv('/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_label_coordinates.csv')\n",
    "# add the columns in coordinates regarding condition+level to match with train_df\n",
    "\n",
    "cols = ['condition', 'level']\n",
    "coord_df['m_condition'] = coord_df[cols].apply(lambda row: ' '.join(row.values.astype(str)).lower(), axis=1)\n",
    "coord_df['m_condition'] = coord_df['m_condition'].str.replace(r'[ /]', '_', regex=True)\n",
    "\n",
    "train_df = pd.read_csv('/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train.csv')\n",
    "\n",
    "\n",
    "\n",
    "def display_images_with_coord(metadata_object, study_id):\n",
    "    '''\n",
    "    again, there is an inner function to display imges\n",
    "    '''\n",
    "    \n",
    "    # this function is for one coord, one image, and one title/description/condition/level)\n",
    "    def display_image_with_coord(center_coord, image_instance_dicom, title):\n",
    "        '''\n",
    "        coord_entry is a particular coord for a particular image \n",
    "        image_meta is the image that specifically in the series, containing SOPInstanceUID and dicom_image_file, i.e. \n",
    "        {2448190387: {'image_series_description': 'Axial T2',\n",
    "                      'image_files': [{'SOPInstanceUID': '1',\n",
    "                                        'dicom_image_file': Dataset.file_meta -------------------------------\n",
    "                                        (0002, 0001) File Meta Informa\n",
    "        '''\n",
    "        radius = 10\n",
    "        color = (255, 0, 0)\n",
    "        thickness = 2\n",
    "\n",
    "        # for what?\n",
    "        image_normalized = cv2.normalize(image_instance_dicom, None, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8U)\n",
    "        # circling\n",
    "        image_circle = cv2.circle(image_normalized.copy(), center_coord, radius, color, thickness)\n",
    "\n",
    "        # convert image from BGR to RGB for correct color display in matplotlib\n",
    "        image_circle = cv2.cvtColor(image_circle, cv2.COLOR_BAYER_BG2BGR)\n",
    "\n",
    "        # display\n",
    "        plt.imshow(image_circle)\n",
    "        plt.axis('off')\n",
    "        plt.title(title)\n",
    "        plt.show()\n",
    "    \n",
    "    \n",
    "    \n",
    "    # example_study_id = 4003253\n",
    "    series_meta =  get_series_metadata_object_given_study_id(metadata_object, study_id) # series_meta all based on given study_id\n",
    "    example_train_df = train_df[train_df.study_id==study_id]\n",
    "    example_coord_entries_df = coord_df[coord_df.study_id==study_id]\n",
    "\n",
    "    for d, coord_entry in example_coord_entries_df.iterrows():\n",
    "\n",
    "        center_coord = (int(coord_entry['x']), int(coord_entry['y']))\n",
    "\n",
    "        # search for the image available for coord in all imgs in series\n",
    "        image_meta_instances_list = series_meta[coord_entry.series_id][\"image_files\"]\n",
    "        # check matching\n",
    "        image_instance_id = coord_entry.instance_number\n",
    "\n",
    "        for image_instance in image_meta_instances_list:\n",
    "\n",
    "            if int(image_instance[\"SOPInstanceUID\"]) == int(image_instance_id):\n",
    "\n",
    "                image_instance_dicom = image_instance[\"dicom_image_file\"].pixel_array\n",
    "\n",
    "                severity = train_df.loc[example_train_df.index[0], coord_entry.m_condition]\n",
    "                title = f'image_instance_id: {image_instance_id} \\n {coord_entry.m_condition} - severity: {severity}'\n",
    "\n",
    "                display_image_with_coord(center_coord, image_instance_dicom, title)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "82970eb9",
   "metadata": {
    "papermill": {
     "duration": 0.00874,
     "end_time": "2024-07-12T23:51:36.514104",
     "exception": false,
     "start_time": "2024-07-12T23:51:36.505364",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# ALL IN ONE BLOCK CODE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1cf52b4a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-07-12T23:51:36.533962Z",
     "iopub.status.busy": "2024-07-12T23:51:36.533521Z",
     "iopub.status.idle": "2024-07-12T23:51:36.545497Z",
     "shell.execute_reply": "2024-07-12T23:51:36.544230Z"
    },
    "papermill": {
     "duration": 0.024158,
     "end_time": "2024-07-12T23:51:36.547237",
     "exception": true,
     "start_time": "2024-07-12T23:51:36.523079",
     "status": "failed"
    },
    "tags": []
   },
   "outputs": [
    {
     "ename": "IndentationError",
     "evalue": "unindent does not match any outer indentation level (<tokenize>, line 112)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;36m  File \u001b[0;32m<tokenize>:112\u001b[0;36m\u001b[0m\n\u001b[0;31m    def display_images_given_study_id(metadata_object, study_id):\u001b[0m\n\u001b[0m    ^\u001b[0m\n\u001b[0;31mIndentationError\u001b[0m\u001b[0;31m:\u001b[0m unindent does not match any outer indentation level\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import cv2\n",
    "import os\n",
    "from tqdm import tqdm\n",
    "\n",
    "import pydicom\n",
    "import numpy as np\n",
    "import glob\n",
    "\n",
    "df_train_series_descriptions = pd.read_csv(\"/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_series_descriptions.csv\")\n",
    "folder_train_images = os.listdir(\"/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_images\")\n",
    "# exclude .DS_store files\n",
    "folder_train_images = list(filter(lambda x: x.find('.DS') == -1, folder_train_images))\n",
    "\n",
    "def get_metadata_object(folder_images, df_series_descriptions):\n",
    "    '''\n",
    "    for intially the train_images folder and train_series_descriptions.csv,\n",
    "    later for the test_images folder and test_series_description.csv\n",
    "    '''\n",
    "    \n",
    "    # a list of tuples like (study_id, study_id's path location)\n",
    "    images_study_id_dirs = [(int(study_id),    # integer the study_id\n",
    "                                   f\"/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_images/{study_id}\") \n",
    "                                  for study_id in folder_images]\n",
    "\n",
    "    # convert the list of tuples into dictionary/metadata\n",
    "    metadata_object = {study_id: {'study_id_folder_path': path, \n",
    "                                    'SeriesInstanceUIDs': [],\n",
    "                                    'SeriesDescriptions': []\n",
    "                                 }\n",
    "                       for study_id, path in images_study_id_dirs\n",
    "                      }\n",
    "\n",
    "    # remove all the .DS files/folders (MacOS) from SeriesInstanceUIDs or series_ids folders\n",
    "    # then put the names for series_ids as well as the corresponding description to metadata\n",
    "    for study_id in tqdm(metadata_object):\n",
    "\n",
    "        # SERIES_ID\n",
    "        # get all series directories/folders inside each study_id directory\n",
    "        series_ids_dirs = os.listdir(metadata_object[study_id]['study_id_folder_path'])\n",
    "        filtered_series_ids_dirs = [int(x) for x in series_ids_dirs if x.find('.DS') == -1]   # integer(series_id)\n",
    "        # put to metadata_object\n",
    "        metadata_object[study_id]['SeriesInstanceUIDs'] = filtered_series_ids_dirs\n",
    "\n",
    "        # SERIES_DESCRIPTIONS\n",
    "        series_desc_df = df_series_descriptions[df_series_descriptions.study_id==study_id][[\"series_id\", \"series_description\"]]\n",
    "        for series_id in metadata_object[study_id]['SeriesInstanceUIDs']:\n",
    "\n",
    "            series_desc_list = series_desc_df[series_desc_df.series_id==series_id].series_description.values\n",
    "\n",
    "            if len(series_desc_list) == 0:\n",
    "                metadata_object[study_id]['SeriesDescriptions'].append(\"\")\n",
    "            else:\n",
    "                metadata_object[study_id]['SeriesDescriptions'].append(series_desc_list[0])\n",
    "                \n",
    "    return metadata_object\n",
    "\n",
    "metadata_object_train = get_metadata_object(folder_train_images, df_train_series_descriptions)\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "def get_series_metadata_object_given_study_id(metadata_object, study_id):\n",
    "    \"\"\"\n",
    "    one study_id can have many series => this func gets all series metadata for this \n",
    "    particular study_id\n",
    "    \"\"\"\n",
    "    \n",
    "    metadata_for_study_id = metadata_object[study_id]\n",
    "    \n",
    "    series_metadata_object_given_study_id = {}\n",
    "\n",
    "    for idx, series_id in enumerate(metadata_for_study_id[\"SeriesInstanceUIDs\"]):\n",
    "\n",
    "        # create bases for the series_images_metadata: each series contains desc and images files\n",
    "        series_metadata_object_given_study_id[series_id] = {'image_series_description': metadata_for_study_id[\"SeriesDescriptions\"][idx], \n",
    "                                                            'image_files': []\n",
    "                                                            }\n",
    "\n",
    "        # glob for patten matching as we want to get image files ending with .dcm\n",
    "        folder_path_study_id = metadata_for_study_id[\"study_id_folder_path\"]\n",
    "        # rmb: \"SeriesInstancesUIDs\" is just a list of images and series_id is the actual series-id\n",
    "        image_files = glob.glob(f\"{folder_path_study_id}/{series_id}/*.dcm\")\n",
    "\n",
    "\n",
    "        # inside image_files, create a metadata for id_image and corresponding dicom readable image file\n",
    "        sorted_image_files = sorted(image_files, key = lambda x: int(x.split('/')[-1].replace('.dcm', '')))\n",
    "\n",
    "        \n",
    "        # iterate through all image files (sorting to make sense, not very necessarily)\n",
    "        for image_file in sorted_image_files:\n",
    "            \n",
    "            dicom_image_id = image_file.split('/')[-1].replace(\".dcm\", '')\n",
    "            dicom_image_read = pydicom.dcmread(image_file)\n",
    "            \n",
    "            # metadata for one image instance\n",
    "            one_image_metadata = {\"SOPInstanceUID\": dicom_image_id,      # id of the dicom image instance file\n",
    "                                  \"dicom_image_file\": dicom_image_read}  # actual read of the dcm instance file\n",
    "\n",
    "            # append this image_metadata to list of image_files\n",
    "            series_metadata_object_given_study_id[series_id][\"image_files\"].append(one_image_metadata)\n",
    "\n",
    "    return series_metadata_object_given_study_id\n",
    "    \n",
    "    \n",
    "    \n",
    "    \n",
    "    \n",
    "    \n",
    " def display_images_given_study_id(metadata_object, study_id): \n",
    "    '''\n",
    "    inside there is another function specifically for this function\n",
    "    '''\n",
    "    \n",
    "    # view images for this study_id = 4003253 for a particular series_description\n",
    "    def display_images(image_files, series_description, max_images_per_row=5):\n",
    "\n",
    "        # grid for display\n",
    "        num_images = len(image_files)\n",
    "        num_rows = (num_images + max_images_per_row - 1) // max_images_per_row  # ceiling division (ignore the remainder, extra)\n",
    "\n",
    "        # subplot grid\n",
    "        fig, axes = plt.subplots(nrows=num_rows, ncols=max_images_per_row)\n",
    "\n",
    "        # flatten axes for easy looping if there are multiple rows\n",
    "        if num_rows > 1:\n",
    "            axes = axes.flatten()\n",
    "        else:\n",
    "            axes = [axes] # iterable for consistency\n",
    "\n",
    "        # plot each image\n",
    "        for idx, image_file in enumerate(image_files):\n",
    "            ax = axes[idx]\n",
    "            ax.imshow(image_file, cmap='gray') # Assuming grayscale for simplicity, change cmap as needed\n",
    "            ax.axis('off')\n",
    "\n",
    "        # turn off unused subplots\n",
    "        for idx in range(num_images, len(axes)):\n",
    "            axes[idx].axis(\"off\")\n",
    "\n",
    "        fig.suptitle(series_description, fontsize=12)\n",
    "        plt.show()\n",
    "        \n",
    "        \n",
    "        \n",
    "    series_metadata_object = get_series_metadata_object_given_study_id(metadata_object, study_id)\n",
    "    \n",
    "    for series_id in series_metadata_object:\n",
    "\n",
    "        series_description = series_metadata_object[series_id][\"image_series_description\"]\n",
    "\n",
    "        # get the image_files for this particular series_id\n",
    "        image_files = series_metadata_object[series_id][\"image_files\"]\n",
    "\n",
    "        # get the dicom files to a list\n",
    "        dicom_images = []\n",
    "        for image_metadata in image_files:\n",
    "            dicom_image = image_metadata['dicom_image_file'].pixel_array\n",
    "            dicom_images.append(dicom_image)\n",
    "\n",
    "        # display images for each series\n",
    "        display_images(dicom_images, series_description)\n",
    "        \n",
    "        \n",
    "\n",
    "        \n",
    "        \n",
    "        \n",
    "coord_df = pd.read_csv('/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train_label_coordinates.csv')\n",
    "# add the columns in coordinates regarding condition+level to match with train_df\n",
    "\n",
    "cols = ['condition', 'level']\n",
    "coord_df['m_condition'] = coord_df[cols].apply(lambda row: ' '.join(row.values.astype(str)).lower(), axis=1)\n",
    "coord_df['m_condition'] = coord_df['m_condition'].str.replace(r'[ /]', '_', regex=True)\n",
    "\n",
    "train_df = pd.read_csv('/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification/train.csv')\n",
    "\n",
    "\n",
    "\n",
    "def display_images_with_coord(metadata_object, study_id):\n",
    "    '''\n",
    "    again, there is an inner function to display imges\n",
    "    '''\n",
    "    \n",
    "    # this function is for one coord, one image, and one title/description/condition/level)\n",
    "    def display_image_with_coord(center_coord, image_instance_dicom, title):\n",
    "        '''\n",
    "        coord_entry is a particular coord for a particular image \n",
    "        image_meta is the image that specifically in the series, containing SOPInstanceUID and dicom_image_file, i.e. \n",
    "        {2448190387: {'image_series_description': 'Axial T2',\n",
    "                      'image_files': [{'SOPInstanceUID': '1',\n",
    "                                        'dicom_image_file': Dataset.file_meta -------------------------------\n",
    "                                        (0002, 0001) File Meta Informa\n",
    "        '''\n",
    "        radius = 10\n",
    "        color = (255, 0, 0)\n",
    "        thickness = 2\n",
    "\n",
    "        # for what?\n",
    "        image_normalized = cv2.normalize(image_instance_dicom, None, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8U)\n",
    "        # circling\n",
    "        image_circle = cv2.circle(image_normalized.copy(), center_coord, radius, color, thickness)\n",
    "\n",
    "        # convert image from BGR to RGB for correct color display in matplotlib\n",
    "        image_circle = cv2.cvtColor(image_circle, cv2.COLOR_BAYER_BG2BGR)\n",
    "\n",
    "        # display\n",
    "        plt.imshow(image_circle)\n",
    "        plt.axis('off')\n",
    "        plt.title(title)\n",
    "        plt.show()\n",
    "    \n",
    "    \n",
    "    \n",
    "    # example_study_id = 4003253\n",
    "    series_meta =  get_series_metadata_object_given_study_id(metadata_object, study_id) # series_meta all based on given study_id\n",
    "    example_train_df = train_df[train_df.study_id==study_id]\n",
    "    example_coord_entries_df = coord_df[coord_df.study_id==study_id]\n",
    "\n",
    "    for d, coord_entry in example_coord_entries_df.iterrows():\n",
    "\n",
    "        center_coord = (int(coord_entry['x']), int(coord_entry['y']))\n",
    "\n",
    "        # search for the image available for coord in all imgs in series\n",
    "        image_meta_instances_list = series_meta[coord_entry.series_id][\"image_files\"]\n",
    "        # check matching\n",
    "        image_instance_id = coord_entry.instance_number\n",
    "\n",
    "        for image_instance in image_meta_instances_list:\n",
    "\n",
    "            if int(image_instance[\"SOPInstanceUID\"]) == int(image_instance_id):\n",
    "\n",
    "                image_instance_dicom = image_instance[\"dicom_image_file\"].pixel_array\n",
    "\n",
    "                severity = train_df.loc[example_train_df.index[0], coord_entry.m_condition]\n",
    "                title = f'image_instance_id: {image_instance_id} \\n {coord_entry.m_condition} - severity: {severity}'\n",
    "\n",
    "                display_image_with_coord(center_coord, image_instance_dicom, title)"
   ]
  }
 ],
 "metadata": {
  "kaggle": {
   "accelerator": "none",
   "dataSources": [
    {
     "databundleVersionId": 8561470,
     "sourceId": 71549,
     "sourceType": "competition"
    }
   ],
   "dockerImageVersionId": 30746,
   "isGpuEnabled": false,
   "isInternetEnabled": true,
   "language": "python",
   "sourceType": "notebook"
  },
  "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": "3.10.13"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 14.055041,
   "end_time": "2024-07-12T23:51:37.077893",
   "environment_variables": {},
   "exception": true,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2024-07-12T23:51:23.022852",
   "version": "2.5.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}