2017/10/18 by Johannes Stegmaier, Stegmaier, Johannes, Thiago V. Spina +11
Agricultural and Biological Sciences · Biochemistry, Genetics and Molecular Biology · Engineering · #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Smart Agriculture and AI
paper · pdf · doi:10.48550/arxiv.1710.06608
openalex publication_date 2017/10/18 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28
Automated segmentation approaches are crucial to quantitatively analyze\nlarge-scale 3D microscopy images. Particularly in deep tissue regions,\nautomatic methods still fail to provide error-free segmentations. To improve\nthe segmentation quality throughout imaged samples, we present a new\nsupervoxel-based 3D segmentation approach that outperforms current methods and\nreduces the manual correction effort. The algorithm consists of gentle\npreprocessing and a conservative super-voxel generation method followed by\nsupervoxel agglomeration based on local signal properties and a postprocessing\nstep to fix under-segmentation errors using a Convolutional Neural Network. We\nvalidate the functionality of the algorithm on manually labeled 3D confocal\nimages of the plant Arabidopis thaliana and compare the results to a\nstate-of-the-art meristem segmentation algorithm.\n