Archive Extraction

unzip[source]

unzip(path, zip_file)

Unzip and structure archive

Install packages on demand

install_package[source]

install_package(package)

import_package[source]

import_package(package)

compose_albumentations[source]

compose_albumentations(gamma_limit_lower=0, gamma_limit_upper=0, CLAHE_clip_limit=0.0, brightness_limit=0, contrast_limit=0.0, distort_limit=0.0)

Compose albumentations augmentations

Ensembling

ensemble_results[source]

ensemble_results(res_dict, file, std=False)

Combines single model predictions.

plot_results[source]

plot_results(*args, df, hastarget=False, model=None, unc_metric=None, figsize=(20, 20), **kwargs)

Plot images, (masks), predictions and uncertainties side-by-side.

Pixelwise Analysis

iou[source]

iou(a, b, threshold=0.5)

Computes the Intersection-Over-Union metric.

test_eq(iou(mask, mask), 1)
test_eq(iou(mask, empty_mask), 0)

ROI-wise Analysis

label_mask[source]

label_mask(mask, threshold=0.5, min_pixel=15, do_watershed=False, exclude_border=False)

Analyze regions and return labels

tst_lbl_a = label_mask(mask, min_pixel=0)
test_eq(tst_lbl_a.max(), 2)
test_eq(tst_lbl_a.min(), 0)
plt.imshow(tst_lbl_a);

tst_lbl_b = label_mask(mask, min_pixel=150)
test_eq(tst_lbl_b.max(), 1)
plt.imshow(tst_lbl_b);

get_candidates[source]

get_candidates(labels_a, labels_b)

Get candiate masks for ROI-wise analysis

iou_mapping[source]

iou_mapping(labels_a, labels_b)

Compare masks using ROI-wise analysis

test_eq(iou_mapping(tst_lbl_a, tst_lbl_a), ([0., 1., 1], [0, 1, 2], [0, 1, 2], 2, 2))
test_eq(iou_mapping(tst_lbl_a, tst_lbl_b), ([0., 1.], [0, 2], [0, 1], 2, 1))

calculate_roi_measures[source]

calculate_roi_measures(*masks, iou_threshold=0.5, **kwargs)

Calculates precision, recall, and f1_score on ROI-level

test_eq(calculate_roi_measures(mask, mask), (1.0, 1.0, 1.0))
test_eq(calculate_roi_measures(mask, mask, min_pixel=150), (1.0, 1.0, 1.0))

ROI Export to ImageJ

export_roi_set[source]

export_roi_set(mask, intensity_image, name='RoiSet', path=Path('.'), ascending=True, min_pixel=0)

EXPERIMENTAL: Export mask regions to imageJ ROI Set

export_roi_set(mask, mask)

Miscellaneous

calc_iterations[source]

calc_iterations(n_iter, ds_length, bs)

Calculate the number of required epochs for 'n_iter' iterations.

test_eq(calc_iterations(100, 8, 4), 50)

get_label_fn[source]

get_label_fn(img_path, msk_dir_path)

Infers suffix from mask name and return label_fn

save_mask[source]

save_mask(mask, path, filetype='.png')

def save_mask(mask, path, filetype='.png'):
    mask = mask.astype(np.uint8) if np.max(mask)>1 else (mask*255).astype(np.uint8)
    imageio.imsave(path.with_suffix(filetype), mask)

save_unc[source]

save_unc(unc, path, filetype='.png')

def save_unc(unc, path, filetype='.png'):
    unc = (unc/unc.max()*255).astype(np.uint8)
    imageio.imsave(path.with_suffix(filetype), unc)