Localization of Neuron Nucleuses in Microscopy Images with Convolutional Neural Networks

Arkadiusz Tomczyk, Bartlomiej Stasiak, Pawel Tarasiuk, Anna Gorzkiewicz, Anna Walczewska, Piotr S. Szczepaniak

Abstract: In this paper, an automatic method of neuron nucleuses localization in the images, taken with the fluorescent microscope, is presented. The proposed approach has two phases. During the first phase, a properly trained convolutional neural network acts as a non-linear filter which indicates regions of interest. The network architecture and specific method of its training are original concepts of the authors of this work. In the second phase, analysis of these regions allows to identify points representing positions of the nucleuses. To illustrate the method, images of neurons isolated from neonatal rat cerebral cortex were used. These images were inspected by a domain expert and all the visible nucleuses were manually annotated. This allowed not only to objectively assess the obtained detection results but it enabled the application of machine learning as well.