{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":22307,"databundleVersionId":1502524,"sourceType":"competition"}],"dockerImageVersionId":30674,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np \nimport pandas as pd \nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nimport pydicom\nimport pydicom as dcm\nimport pydicom as dicom\n\nfrom os import listdir, mkdir\nimport os\n\nimport warnings\nwarnings.filterwarnings(\"ignore\", category=DeprecationWarning)\nwarnings.filterwarnings(\"ignore\", category=UserWarning)\nwarnings.filterwarnings(\"ignore\", category=FutureWarning)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-04-12T11:31:26.370704Z","iopub.execute_input":"2024-04-12T11:31:26.371056Z","iopub.status.idle":"2024-04-12T11:31:28.976075Z","shell.execute_reply.started":"2024-04-12T11:31:26.371023Z","shell.execute_reply":"2024-04-12T11:31:28.975241Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# navigation and directory management libraries\nimport os, glob, pydicom, imageio","metadata":{"execution":{"iopub.status.busy":"2024-04-12T11:31:32.566162Z","iopub.execute_input":"2024-04-12T11:31:32.567328Z","iopub.status.idle":"2024-04-12T11:31:32.625295Z","shell.execute_reply.started":"2024-04-12T11:31:32.567288Z","shell.execute_reply":"2024-04-12T11:31:32.624302Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a style=\"font-family: Verdana; font-size: 24px; font-style: normal; font-weight: bold; text-decoration: none; text-transform: none; letter-spacing: 3px; color: navy; background-color: #ffffff;\" id=\"setup\">&nbsp;&nbsp;NOTEBOOK SETUP</a>","metadata":{}},{"cell_type":"code","source":"import time\n\nstart_time = time.time()\nPATH = \"../input/rsna-str-pulmonary-embolism-detection/\"\ntrain_df = pd.read_csv(PATH + \"train.csv\")\ntest_df = pd.read_csv(PATH + \"test.csv\")\n\nTRAIN_PATH = PATH + \"train/\"\nTEST_PATH = PATH + \"test/\"\nsub = pd.read_csv(PATH + \"sample_submission.csv\")\ntrain_image_file_paths = glob.glob(TRAIN_PATH + '/*/*/*.dcm')\ntest_image_file_paths = glob.glob(TEST_PATH + '/*/*/*.dcm')\n\nprint(f'Train dataframe shape  :{train_df.shape}')\nprint(f'Test dataframe shape   :{test_df.shape}')\n\nprint(f'Number of train images : {len(train_image_file_paths)}')\nprint(f'Number of test images  : {len(test_image_file_paths)}')\n    \nend_time = time.time()\nexecution_time = end_time - start_time\nprint(f'Execution time to load data: {execution_time:.2f} seconds')\n","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:05:02.536501Z","iopub.execute_input":"2024-04-12T12:05:02.537222Z","iopub.status.idle":"2024-04-12T12:05:21.372067Z","shell.execute_reply.started":"2024-04-12T12:05:02.537192Z","shell.execute_reply":"2024-04-12T12:05:21.37112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"DATA_DIR = \"/kaggle/input/rsna-str-pulmonary-embolism-detection\"\n\n# Define paths to the relevant csv files\nTRAIN_CSV = os.path.join(DATA_DIR, \"train.csv\")\nSS_CSV = os.path.join(DATA_DIR, \"sample_submission.csv\")\n\n\n# Create the relevant dataframe objects\ntrain_df = pd.read_csv(TRAIN_CSV)\nss_df = pd.read_csv(SS_CSV)\n\n\nprint(\"\\n\\n Train DataFrame \\n\\n\")\ndisplay(train_df.head(3))\n\nprint(\"\\n\\n Sample Submission Dataframe \\n\\n\")\ndisplay(ss_df.head(3))","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:03:36.012717Z","iopub.execute_input":"2024-04-12T12:03:36.013099Z","iopub.status.idle":"2024-04-12T12:03:38.737559Z","shell.execute_reply.started":"2024-04-12T12:03:36.013067Z","shell.execute_reply":"2024-04-12T12:03:38.736639Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Number of unique values in StudyInstanceUID:\", train_df['StudyInstanceUID'].nunique())\n\nprint(\"Number of unique values in SeriesInstanceUID:\", train_df['SeriesInstanceUID'].nunique())\n\nprint(\"Number of unique values in SOPInstanceUID:\", train_df['SOPInstanceUID'].nunique())\n","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:03:44.516633Z","iopub.execute_input":"2024-04-12T12:03:44.516986Z","iopub.status.idle":"2024-04-12T12:03:45.673927Z","shell.execute_reply.started":"2024-04-12T12:03:44.516946Z","shell.execute_reply":"2024-04-12T12:03:45.673027Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.dtypes","metadata":{"execution":{"iopub.status.busy":"2024-04-11T11:57:20.10666Z","iopub.execute_input":"2024-04-11T11:57:20.109078Z","iopub.status.idle":"2024-04-11T11:57:20.119992Z","shell.execute_reply.started":"2024-04-11T11:57:20.109011Z","shell.execute_reply":"2024-04-11T11:57:20.118517Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Data fields**\n\n- **StudyInstanceUID** - unique ID for each study (exam) in the data.\n- **SeriesInstanceUID** - unique ID for each series within the study.\n- **SOPInstanceUID** - unique ID for each image within the study (and data).\n- **pe_present_on_image** - image-level, notes whether any form of PE is present on the image.\n- **negative_exam_for_pe** - exam-level, whether there are any images in the study that have PE present.\n- **qa_motion** - informational, indicates whether radiologists noted an issue with motion in the study.\n- **qa_contrast** - informational, indicates whether radiologists noted an issue with contrast in the study.\n- **flow_artifact** - informational\n- **rv_lv_ratio_gte_1** - exam-level, indicates whether the RV/LV ratio present in the study is >= 1\n- **rv_lv_ratio_lt_1** - exam-level, indicates whether the RV/LV ratio present in the study is < 1\n- **leftsided_pe** - exam-level, indicates that there is PE present on the left side of the images in the study\n- **chronic_pe** - exam-level, indicates that the PE in the study is chronic\n- **true_filling_defect_not_pe** - informational, indicates a defect that is NOT PE\n- **rightsided_pe** - exam-level, indicates that there is PE present on the right side of the images in the study\n- **acute_and_chronic_pe** - exam-level, indicates that the PE present in the study is both acute AND chronic\n- **central_pe** - exam-level, indicates that there is PE present in the center of the images in the study\n- **indeterminate** -exam-level, indicates that while the study is not negative for PE, an ultimate set of exam-level labels could not be created, due to QA issues","metadata":{}},{"cell_type":"markdown","source":"**So, What are we going to predict?**\n\n   > Every study / exam has a row for each label that is scored (detailed in the Data page). It is uniquely indicated by the StudyInstanceUID (first label). Every image, further, has a row for the PE Present on Image label and is uniquely indicated by the SOPInstanceUID. \n   \n   >Your prediction file should have a number of rows equal to: (number of images) + (number of studies * number of scored labels).\nIn other words:\n\n>For each image, we're going to predict the column \"pe_present_on_image\"\n>For each \"StudyInstanceUID\" we're goin to predict:\n> - linkcode\n> - negative_exam_for_pe\n> - rv_lv_ratio_gte_1\n> - rv_lv_ratio_lt_1\n> - chronic_pe\n> - true_filling_defect_not_pe\n> - acute_and_chronic_pe\n> - rightsided_pe\n> - leftsided_pe\n> - central_pe","metadata":{}},{"cell_type":"code","source":"train_cols = ['pe_present_on_image', 'negative_exam_for_pe', 'qa_motion',\n       'qa_contrast', 'flow_artifact', 'rv_lv_ratio_gte_1', 'rv_lv_ratio_lt_1',\n       'leftsided_pe', 'chronic_pe', 'true_filling_defect_not_pe',\n       'rightsided_pe', 'acute_and_chronic_pe', 'central_pe', 'indeterminate']\n\ndef plot_grid(cols = train_cols):\n    fig=plt.figure(figsize=(12, 12))\n    columns = 3\n    rows = 5\n    for i in range(1, columns*rows):\n        col = cols[i-1]\n        fig.add_subplot(rows, columns, i)\n        train_df[col].value_counts().plot(kind = \"bar\")\n        indices = train_df[col].value_counts().index.tolist()\n        count_0 = train_df[col].value_counts()[0]\n        count_1 = train_df[col].value_counts()[1]\n        plt.xlabel(f\"{col}\\n {indices[0]}: {count_0}\\n {indices[1]}: {count_1}\")\n    plt.tight_layout()\n    plt.show()\n\nplot_grid()","metadata":{"execution":{"iopub.status.busy":"2024-04-11T12:04:03.782871Z","iopub.execute_input":"2024-04-11T12:04:03.78335Z","iopub.status.idle":"2024-04-11T12:04:06.756032Z","shell.execute_reply.started":"2024-04-11T12:04:03.783309Z","shell.execute_reply":"2024-04-11T12:04:06.754755Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"corr_mat = train_df[train_cols].corr()\nmask = np.triu(np.ones_like(corr_mat, dtype=bool))\nf, ax = plt.subplots(figsize=(14, 12))\nsns.heatmap(corr_mat, mask = mask, annot = True, vmax = 0.3, square = False, linewidths = 0.5, center = 0, cmap='coolwarm')","metadata":{"execution":{"iopub.status.busy":"2024-04-11T12:30:02.257357Z","iopub.execute_input":"2024-04-11T12:30:02.258353Z","iopub.status.idle":"2024-04-11T12:30:04.573782Z","shell.execute_reply.started":"2024-04-11T12:30:02.258315Z","shell.execute_reply":"2024-04-11T12:30:04.572571Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can note the following observations:\n\n- By looking at the images, only 5.4% of patients have active cases of PE But exam shows that 32.4% of the images involve active cases of PE, which means that image-based prediction gives many false-negatives\n- There are almost no issues related to motion (0.8%) / contrast in the studies (1.6%)\n- RV/LV values are not consistent\n- Most defects are right-sided or left-sided. There are only few cases of central cases of PE","metadata":{}},{"cell_type":"markdown","source":"![inbox-115173-a2a5ee66b5799274141dd547cc3ea466-PE figure.jpg](attachment:664c4a19-5cb2-472e-8e32-92ae072a9dc9.jpg)","metadata":{},"attachments":{"664c4a19-5cb2-472e-8e32-92ae072a9dc9.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"What is image-level and exam-level features:\n\nIn this competition, image-level feature prediction means you have to find predict that particular feature for each of the image separately. Here all the images are unique.\n\nOn the contrary exam-label feature means you have to characterize that particular image exam or observation. Here one thing should be very clear that one exam has many images. Here the prediction is based on the experiment/examination.\n\nThe following image is a flowchart outlining the relationships between labels. Note that there are four labels in the training set that are purely informational and require no predictions. They are QA Contrast, QA Motion, True filling defect not PE, and Flow artifact, and are not scored, but are meant to be used as helpers. Also note that Acute PE is not an explicit label, but is implied by the lack of Chronic PEor Acute and Chronic PE.","metadata":{}},{"cell_type":"code","source":"# Train DYCOM File information\n\ndcm_file =  pydicom.read_file(\"/kaggle/input/rsna-str-pulmonary-embolism-detection/train/0003b3d648eb/d2b2960c2bbf/00ac73cfc372.dcm\")\nprint(dcm_file.file_meta)","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:05:55.980569Z","iopub.execute_input":"2024-04-12T12:05:55.981412Z","iopub.status.idle":"2024-04-12T12:05:56.013955Z","shell.execute_reply.started":"2024-04-12T12:05:55.981378Z","shell.execute_reply":"2024-04-12T12:05:56.013143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Train DYCOM File information\n\ndcm_file_test =  pydicom.read_file(\"/kaggle/input/rsna-str-pulmonary-embolism-detection/test/00268ff88746/75d23269adbd/012c12fe09c3.dcm\")\nprint(dcm_file_test.file_meta)","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:05:58.269931Z","iopub.execute_input":"2024-04-12T12:05:58.270841Z","iopub.status.idle":"2024-04-12T12:05:58.291573Z","shell.execute_reply.started":"2024-04-12T12:05:58.270806Z","shell.execute_reply":"2024-04-12T12:05:58.290754Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In addition to this metadata, there are lot of important information in the dicom file. \n\nWe can extract those information from the dicom files and use them in the preprocessing steps of these CT-Scans. \n\nLet's have a look at the additional paramers stored in the dicom files.\n\nSo the class of this is a CT scan, the implementation is dcm4che (potentially expanded form DCM for Chest), and you have all the standard metadata of a DICOM file for the lungs. \n\nSome checks on the pixel array:","metadata":{}},{"cell_type":"code","source":"dcm_file","metadata":{"execution":{"iopub.status.busy":"2024-04-11T12:34:49.964744Z","iopub.execute_input":"2024-04-11T12:34:49.965782Z","iopub.status.idle":"2024-04-11T12:34:49.974947Z","shell.execute_reply.started":"2024-04-11T12:34:49.965747Z","shell.execute_reply":"2024-04-11T12:34:49.974054Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\nHere among these large number of parameter, there are several paramers that a radiologist must have a good understanding of. They are\n\n\n- (0020, 0013)\tInstance Number\tIS: \"40\"\n- (0028, 0030)\tPixel Spacing\tDS: [0.871094,0.871094]\n- (0028, 1050)\tWindow Center\tDS: \"40.0\"\n- (0028, 1051)\tWindow Width\tDS: \"400.0\"\n- (0028, 1052)\tRescale Intercept\tDS: \"-1024.0\"\n- (0028, 1053)\tRescale Slope\tDS: \"1.0\"","metadata":{}},{"cell_type":"markdown","source":"These parameters are must needed for preprocessing the CT-Scans. Without these parameters it will be very difficult to fully utilize the potential of the CT-Scans.","metadata":{}},{"cell_type":"code","source":"image = dcm_file.pixel_array\nprint(f'Image Size: {image.shape}')","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:06:02.009304Z","iopub.execute_input":"2024-04-12T12:06:02.009644Z","iopub.status.idle":"2024-04-12T12:06:02.015957Z","shell.execute_reply.started":"2024-04-12T12:06:02.009616Z","shell.execute_reply":"2024-04-12T12:06:02.014856Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(2,1,figsize=(20,10))\nfor file in train_image_file_paths[0:10]:\n    dataset = pydicom.read_file(file)\n    image = dataset.pixel_array.flatten()\n    rescaled_image = image * dataset.RescaleSlope + dataset.RescaleIntercept\n    sns.distplot(image.flatten(), ax=ax[0]);\n    sns.distplot(rescaled_image.flatten(), ax=ax[1])\nax[0].set_title(\"Raw pixel array distributions for 10 examples\");","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:06:04.178151Z","iopub.execute_input":"2024-04-12T12:06:04.178812Z","iopub.status.idle":"2024-04-12T12:06:25.322907Z","shell.execute_reply.started":"2024-04-12T12:06:04.178779Z","shell.execute_reply":"2024-04-12T12:06:25.321979Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_dicom(file_path, show = False, cmap = 'gray'):\n    im = pydicom.read_file(file_path)\n    image_unscaled = im.pixel_array\n    image_rescaled = im.pixel_array * im.RescaleSlope + im.RescaleIntercept\n    \n    image_rescaled[image_rescaled <-1500] = 0\n    \n    if show:\n        f, axarr = plt.subplots(1,2)\n        axarr[0].imshow(image_unscaled, cmap = cmap)\n        axarr[0].axis(False)\n        axarr[0].set_title('no_rescale')\n        \n        axarr[1].imshow(image_rescaled, cmap = cmap)\n        axarr[1].axis(False)\n        axarr[1].set_title('windowed')\n    return image_rescaled\n\n\nimage = read_dicom(train_image_file_paths[2200], show = True)\nimage.dtype","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:24:14.08334Z","iopub.execute_input":"2024-04-12T12:24:14.084028Z","iopub.status.idle":"2024-04-12T12:24:14.420903Z","shell.execute_reply.started":"2024-04-12T12:24:14.08399Z","shell.execute_reply":"2024-04-12T12:24:14.420005Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Now let's have a look at the images of the training set. In the following image, 15 of the images are just displayed. As a title of the images, I have set the maximum and minimum value of the pixel which explains why some of the slices are darker than the others.","metadata":{}},{"cell_type":"code","source":"counter  = 0\nrows = 3\ncols = 5\nfig = plt.figure(figsize=(25,15))\nfor i in range(1, rows*cols+1):\n    img = read_dicom(train_image_file_paths[counter + i])\n    fig.add_subplot(rows, cols, i)\n    plt.imshow(img, cmap='gray')\n    plt.title(f'[{img.min()} {img.max()}]')\n    plt.axis(False)\n    fig.add_subplot\ncounter += rows*cols","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:24:23.212731Z","iopub.execute_input":"2024-04-12T12:24:23.21308Z","iopub.status.idle":"2024-04-12T12:24:25.622436Z","shell.execute_reply.started":"2024-04-12T12:24:23.21305Z","shell.execute_reply":"2024-04-12T12:24:25.62131Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In the above image, just the images are printed irrespective of any of the patients. Now we will just have a look at a single exam and will observe if the images are of same patient or different patient.","metadata":{}},{"cell_type":"code","source":"selected_exam = 10\nEXAM_IDs = os.listdir(TRAIN_PATH)\nSERIES = os.listdir(TRAIN_PATH + '/' + EXAM_IDs[selected_exam])\nfiles = os.listdir(TRAIN_PATH + '/' + EXAM_IDs[selected_exam] + '/' + SERIES[0])\nsingle_experiment_files = [TRAIN_PATH + '/' + EXAM_IDs[selected_exam] + '/' + SERIES[0] + '/' + file for file in files]","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:25:44.053268Z","iopub.execute_input":"2024-04-12T12:25:44.05363Z","iopub.status.idle":"2024-04-12T12:25:44.06321Z","shell.execute_reply.started":"2024-04-12T12:25:44.053601Z","shell.execute_reply":"2024-04-12T12:25:44.062297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"counter  = 0\nrows = 3\ncols = 5\nfig = plt.figure(figsize=(25,15))\nfor i in range(1, rows*cols+1):\n    fig.add_subplot(rows, cols, i)\n    plt.imshow(read_dicom(single_experiment_files[counter + i]), cmap='gray')\n    plt.axis(False)\n    fig.add_subplot\ncounter += rows*cols","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:25:46.025112Z","iopub.execute_input":"2024-04-12T12:25:46.026242Z","iopub.status.idle":"2024-04-12T12:25:47.86211Z","shell.execute_reply.started":"2024-04-12T12:25:46.026203Z","shell.execute_reply":"2024-04-12T12:25:47.861204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Read of the same CT - Sequential Read**","metadata":{}},{"cell_type":"markdown","source":"So far we have been able to print the random CT-Scan Slices of the patient. However just printing and looking at the random slices don't make any sense because they have a particular sequence and they only make sense in that particualr sequence. Now in the following part of this notebook we will try to print the scans in a sequence.\n\n","metadata":{}},{"cell_type":"code","source":"#### \n\n\ndef load_slice(file_paths):\n    slices = [pydicom.dcmread(file) for file in file_paths]\n    slices.sort(key=lambda x: float(x.ImagePositionPatient[2]))\n    image = np.stack([s.pixel_array for s in slices])\n    return image\n\ndef transform_to_hu(images):\n    hu_images = []\n    for slice_number in range(len(images)):\n        image = images[slice_number]\n        intercept = image.RescaleIntercept\n        slope = image.RescaleSlope\n\n        if slope != 1:\n            image = slope * image.astype(np.float64)\n            image = image.astype(np.int16)\n\n        image += np.int16(intercept)\n        hu_images.append(image)\n    \n    return np.array(hu_images, dtype=np.int16)","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:31:12.670954Z","iopub.execute_input":"2024-04-12T12:31:12.671616Z","iopub.status.idle":"2024-04-12T12:31:12.678826Z","shell.execute_reply.started":"2024-04-12T12:31:12.671586Z","shell.execute_reply":"2024-04-12T12:31:12.677828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef sample_stack(stack, rows=6, cols=6, start_with=10, show_every=3):\n    fig, ax = plt.subplots(rows, cols, figsize=[20, 22])\n    for i in range(rows * cols):\n        ind = start_with + i * show_every\n        ax[int(i / rows), int(i % rows)].set_title(f'slice {ind}')\n        ax[int(i / rows), int(i % rows)].imshow(stack[ind], cmap='gray')\n        ax[int(i / rows), int(i % rows)].axis('off')\n    plt.show()\n\nsingle_experiment_files = [TRAIN_PATH + '/' + EXAM_IDs[selected_exam] + '/' + SERIES[0] + '/' + file for file in files]\nstacked_dicoms = load_slice(single_experiment_files)\nstacked_patient_pixels = transform_to_hu(stacked_dicoms)\n\nprint(f'Total Number of Slices: {len(stacked_patient_pixels)}')\nsample_stack(stacked_patient_pixels, \n             show_every=int((len(stacked_patient_pixels) - 10) / 36))","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:31:17.047224Z","iopub.execute_input":"2024-04-12T12:31:17.048048Z","iopub.status.idle":"2024-04-12T12:31:17.878552Z","shell.execute_reply.started":"2024-04-12T12:31:17.048018Z","shell.execute_reply":"2024-04-12T12:31:17.87732Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"stacked_dicoms = load_slice(single_experiment_files)\nstacked_patient_pixels = transform_to_hu(stacked_dicoms)\n\ndef sample_stack(stack, rows=6, cols=6, start_with=10, show_every=3):\n    fig,ax = plt.subplots(rows,cols,figsize=[20,22])\n    for i in range(rows*cols):\n        ind = start_with + i*show_every\n        ax[int(i/rows),int(i % rows)].set_title(f'slice {ind}')\n        ax[int(i/rows),int(i % rows)].imshow(stack[ind],cmap='gray')\n        ax[int(i/rows),int(i % rows)].axis('off')\n    plt.show()\n\nprint(f'Total Number of Slices: {len(stacked_patient_pixels)}')\nsample_stack(stacked_patient_pixels, \n             show_every = int((len(stacked_patient_pixels)-10)/36))","metadata":{"execution":{"iopub.status.busy":"2024-04-12T12:30:40.476958Z","iopub.execute_input":"2024-04-12T12:30:40.477297Z","iopub.status.idle":"2024-04-12T12:30:41.256398Z","shell.execute_reply.started":"2024-04-12T12:30:40.477271Z","shell.execute_reply":"2024-04-12T12:30:41.255213Z"},"trusted":true},"execution_count":null,"outputs":[]}]}