Tracking-Assisted Detection of Dendritic Spines in Time-Lapse Microscopic Images

Abstract

Detecting morphological changes of dendritic spines in tim e-lapse microscopy images and correlating them with functional properties such as memory and learning, are fundam ental and challenging problems in neurobiology research. In this paper, we propose an algorithm for dendritic spine detection in time series. The proposed approach initially performs spine detection at each time point and improves the accuracy by exploiting the information obtained from tracking of individual spines over time. To detect dendritic spines in a time point image we em ploy an SVM classifier trained by pre-labeled SIFT feature descriptors in combination with a dot enhancement filter. Second, to track the growth or loss of spines, we apply a SIFT-based rigid registration method for the alignment of tim e-series images. This step takes into account both the structure and the movement of objects, combined with a robust dynamic scheme to link inform ation about spines that disappear and reappear over time. Next, we improve spine detection by em ploying a probabilistic dynam ic program m ing approach to search for an optimum solution to accurately detect missed spines. Finally, we determine the spine location more precisely by performing a watershed-geodesic active contour model. We quantitatively assess the perform ance of the proposed spine detection algorithm based on annotations performed by biologists and com pare its perform ance with the results obtained by the noncommercial software NeuronIQ. Experiments show that our approach can accurately detect and quantify spines in 2-photon m icroscopy tim e-lapse data and is able to accurately identify spine elimination and form ation. (C) 2018 IBRO. Published by Elsevier Ltd. AM rights reserved.