Agradecimentos: We are grateful for funding by the Helmholtz Association in the program BioInterfaces in Technology and Medicine (RM), the German Research Foundation DFG in the project MI1315/4-1 (JS, RM), the Center for Advanced Methods in Biological Image Analysis, Beckman Institute at Caltech (JS, TS, EM, AC), the Howard Hughes Medical Institute (EM), the Gordon and Betty Moore Foundation (EM and AC), the São Paulo Research Foundation in projects 2016/11853-2, 2015/09446-7, and 2014/12236–1 (TS, AF), and the Serrapilheira Institute in the project Serra-1708-16161 (TS). The Titan Xp used for this research was donated by the NVIDIA Corporation Ver menos

Abstract: Automated segmentation approaches are crucial to quantitatively analyze large-scale 3D microscopy images. Particularly in deep tissue regions, automatic methods still fail to provide error-free segmentations. To improve the segmentation quality throughout imaged samples, we present a new supervoxel-based 3D segmentation approach that outperforms current methods and reduces the manual correction effort. The algorithm consists of gentle preprocessing and a conservative super-voxel generation method followed by supervoxel agglomeration based on local signal properties and a postprocessing step to fix under-segmentation errors using a Convolutional Neural Network. We validate the functionality of the algorithm on manually labeled 3D confocal images of the plant Arabidopsis thaliana and compare the results to a state-of-the-art meristem segmentation algorithm Ver menos