monailabel.scribbles.utils module

monailabel.scribbles.utils.get_eps(data)[source]
monailabel.scribbles.utils.learn_and_apply_gmm_monai(image, scrib, scribbles_bg_label, scribbles_fg_label, num_mixtures)[source]
monailabel.scribbles.utils.make_histograms(image, scrib, scribbles_bg_label, scribbles_fg_label, alpha_bg=1, alpha_fg=1, bins=32)[source]
monailabel.scribbles.utils.make_iseg_unary(prob, scribbles, scribbles_bg_label=2, scribbles_fg_label=3)[source]

Implements ISeg unary term from the following paper: Wang, Guotai, et al. “Interactive medical image segmentation using deep learning with image-specific fine tuning.” IEEE transactions on medical imaging 37.7 (2018): 1562-1573. (preprint: https://arxiv.org/pdf/1710.04043.pdf) ISeg unary term is constructed using Equation 7 on page 4 of the above mentioned paper.

monailabel.scribbles.utils.make_likelihood_image_gmm(image, scrib, scribbles_bg_label, scribbles_fg_label, num_mixtures=20, return_label=False)[source]
monailabel.scribbles.utils.make_likelihood_image_histogram(image, scrib, scribbles_bg_label, scribbles_fg_label, num_bins=64, return_label=False)[source]
monailabel.scribbles.utils.maxflow(image, prob, lamda=5, sigma=0.1)[source]