Upload New File

Notebook_EDA.ipynb

+%% Cell type:code id: tags:
 
+``` python
+!pip install pydicom
+import matplotlib.pyplot as plt
+import pydicom
+from pydicom.data import get_testdata_file
+
+ 
+import numpy as np
+import pandas as pd
+
+import matplotlib.pyplot as plt
+import seaborn as sns
+from pathlib import Path
+
+import os
+import json
+import glob
+import random
+import collections
+import cv2
+import pandas as pd
+import pydicom
+from pydicom.pixel_data_handlers.util import apply_voi_lut
+from tqdm.notebook import tqdm
+import os
+import glob
+
+
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import roc_auc_score, accuracy_score, log_loss
+
+from scipy import ndimage
+
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras.utils import to_categorical
+from tensorflow.keras import layers
+
+from matplotlib import animation, rc
+rc('animation', html='jshtml')
 ```
 
+%% Cell type:code id: tags:
 
+``` python
+path_data="/kaggle/input/rsna-miccai-brain-tumor-radiogenomic-classification/"
+train_df = pd.read_csv(path_data+"train_labels.csv")
+def load_dicom(path):
+    dicom = pydicom.read_file(path,force=True)
+    data = dicom.pixel_array
+    data = data - np.min(data)
+    if np.max(data) != 0:
+        data = data / np.max(data)
+    data = (data * 255).astype(np.uint8)
+    return data
+
+
+def visualize_sample(
+    brats21id, 
+    slice_i,
+    mgmt_value,
+    types=("FLAIR", "T1w", "T1wCE", "T2w")
+):
+    plt.figure(figsize=(10, 3))
+    patient_path = os.path.join(
+        path_data+"train/", 
+        str(brats21id).zfill(5),
+    )
+    for i, t in enumerate(types, 1):
+        t_paths = sorted(
+            glob.glob(os.path.join(patient_path, t, "*")), 
+            key=lambda x: int(x[:-4].split("-")[-1]),
+        )
+        data = load_dicom(t_paths[int(len(t_paths) * slice_i)])
+        plt.subplot(1, 4, i)
+        plt.imshow(data, cmap="gray")
+        plt.title(f"{t}", fontsize=10)
+        plt.axis("off")
+    plt.show()
+
+
+
+
+def create_animation(ims):
+    fig = plt.figure(figsize=(5, 5))
+    plt.axis('off')
+    im = plt.imshow(ims[0], cmap="gray")
+
+    def animate_func(i):
+        im.set_array(ims[i])
+        #return [im]
+    return animation.FuncAnimation(fig, animate_func, frames = len(ims), interval = 1000//4)
+
+def load_dicom_line(path):
+    t_paths = sorted(
+        glob.glob(os.path.join(path, "*")), 
+        key=lambda x: int(x[:-4].split("-")[-1]),
+    )
+    images = []
+    for filename in t_paths:
+        data = load_dicom(filename)
+        if data.max() == 0:
+            continue
+        images.append(data)
+        
+    return images
+
+
+def create_animation(ims):
+    fig = plt.figure(figsize=(5, 5))
+    plt.axis('off')
+    im = plt.imshow(ims[0], cmap="gray")
+
+    def animate_func(i):
+        im.set_array(ims[i])
+        #return [im]
+    return animation.FuncAnimation(fig, animate_func, frames = len(ims), interval = 1000//4)
+
+def load_dicom_line(path):
+    t_paths = sorted(
+        glob.glob(os.path.join(path, "*")), 
+        key=lambda x: int(x[:-4].split("-")[-1]),
+    )
+    images = []
+    for filename in t_paths:
+        data = load_dicom(filename)
+        if data.max() == 0:
+            continue
+        images.append(data)
+    return images
+
+create_animation(load_dicom_line("../input/rsna-miccai-brain-tumor-radiogenomic-classification/train/00176/T2w"))
+    
 ```
 
+%% Cell type:code id: tags:
 
+``` python
 ```