Сегментация и типирование тучных клеток в данных гистологии методами глубокого обучения

Abstract

In this work, we propose a method for automatic segmentation of mast cells on histological images. The method includes a segmentation step and a classification step. The first step is performed by a neural network with UNet architecture, and the second step is performed by the convolutional neural network. Quality of classification reaches 0.68 at the validation dataset in the categorical accuracy metric.