Microscopy image analysis can provide substantial information for clinical study and understanding of biologicalstructures. Two-photon microscopy is a type of fluorescence microscopy that can image deep into tissue withnear-infrared excitation light. We are interested in methods that can detect and characterize nuclei in 3Dfluorescence microscopy image volumes. In general, several challenges exist for counting nuclei in 3D imagevolumes. These include “crowding” and touching of nuclei, overlapping of nuclei, and shape and size variancesof the nuclei. In this paper, a 3D nuclei counter using two different generative adversarial networks (GAN) isproposed and evaluated. Synthetic data that resembles real microscopy image is generated with a GAN andused to train another 3D GAN that counts the number of nuclei. Our approach is evaluated with respect tothe number of groundtruth nuclei and compared with common ways of counting used in the biological research.Fluorescence microscopy 3D image volumes of rat kidneys are used to test our 3D nuclei counter. The accuracyresults of proposed nuclei counter are compared with the ImageJ’s 3D object counter (JACoP) and the 3Dwatershed. Both the counting accuracy and the object-based evaluation show that the proposed technique issuccessful for counting nuclei in 3D.
展开▼
