Spaces:
Sleeping
Sleeping
| from scipy.ndimage import label, find_objects | |
| import numpy as np | |
| import cv2 | |
| IMAGE_SPACING_X = 0.7031 | |
| IMAGE_SPACING_Y = 0.7031 | |
| IMAGE_SPACING_Z = 2.5 | |
| def compute_largest_diameter(binary_mask): | |
| # Label connected components in the binary mask | |
| labeled_array, num_features = label(binary_mask) | |
| # Find the objects (tumors) in the labeled array | |
| tumor_objects = find_objects(labeled_array) | |
| # Initialize the largest diameter variable | |
| largest_diameter = 0 | |
| # Iterate through each tumor object | |
| for obj in tumor_objects: | |
| # Calculate the dimensions of the tumor object | |
| z_dim = obj[2].stop - obj[2].start | |
| y_dim = obj[1].stop - obj[1].start | |
| x_dim = obj[0].stop - obj[0].start | |
| # Calculate the diameter using the longest dimension | |
| diameter = max(z_dim * IMAGE_SPACING_Z, y_dim * IMAGE_SPACING_Y, x_dim * IMAGE_SPACING_X) | |
| # Update the largest diameter if necessary | |
| if diameter > largest_diameter: | |
| largest_diameter = diameter | |
| return largest_diameter / 10 # IN CM | |
| def generate_features(img, liver, tumor): | |
| contours, _ = cv2.findContours(mask_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) | |
| features = { | |
| "lesion size (cm)": compute_largest_diameter(tumor), | |
| "lesion shape": "irregular", | |
| "lesion density (HU)": np.mean(img[tumor==1]), | |
| "involvement of adjacent organs:": "Yes" if np.sum(np.multiply(liver==0, tumor)) > 0 else "No" | |
| } | |
| return features | |