The method of trainable active contour is one of the semi-automatic segmentation methods that can be applied to segment glands in histological images. In this paper, we propose a method for automatic initialization of trainable active contour model, which makes the segmentation method fully automatic. Using a U-Net like architecture, a preprocessed image segmentation masks is predicted for the input image, from which initial approximations of contours are calculated for each gland. The proposed method correctly marks 96.2 % part for the glands on the test set of the PATH-DT-MSU S1-v2 dataset. As a result, we get initial approximations located inside each gland in the image.

Glands segmentation, active contours, convolution neural networks, histological images, instance segmentation

Yakovlev Nikita,  ,  orcid.org/0009-0009-2905-3951,  Lomonosov Moscow State University

Khvostikov Alexander Vladimirovich,  ,  orcid.org/0000-0002-4217-7141,  Lomonosov Moscow State University

Krylov Andrey Serdjevich,  ,  orcid.org/0000-0001-9910-4501,  Lomonosov Moscow State University