CaltechAUTHORS
  A Caltech Library Service

Cell segmentation in 3D confocal images using supervoxel merge-forests with CNN-based hypothesis selection

Stegmaier, Johannes and Spina, Thiago V. and Falcão, Alexandre X. and Bartschat, Andreas and Mikut, Ralf and Meyerowitz, Elliot and Cunha, Alexandre (2018) Cell segmentation in 3D confocal images using supervoxel merge-forests with CNN-based hypothesis selection. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). IEEE , Piscataway, NJ, pp. 382-386. ISBN 978-1-5386-3636-7. http://resolver.caltech.edu/CaltechAUTHORS:20180601-083044304

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180601-083044304

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.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/ISBI.2018.8363598DOIArticle
https://ieeexplore.ieee.org/document/8363598PublisherArticle
ORCID:
AuthorORCID
Meyerowitz, Elliot0000-0003-4798-5153
Additional Information:© 2018 IEEE. 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.
Funders:
Funding AgencyGrant Number
Helmholtz-Gemeinschaft Deutscher Forschungszentren (HGF)UNSPECIFIED
Deutsche Forschungsgemeinschaft (DFG)MI1315/4-1
Caltech Beckman InstituteUNSPECIFIED
Howard Hughes Medical Institute (HHMI)UNSPECIFIED
Fundação de Amparo à Pesquisa do Estado de Sao Paulo (FAPESP)2016/11853-2
Fundação de Amparo à Pesquisa do Estado de Sao Paulo (FAPESP)2015/09446-7
Fundação de Amparo à Pesquisa do Estado de Sao Paulo (FAPESP)2014/12236-1
Serrapilheira InstituteSerra-1708-16161
Gordon and Betty Moore FoundationUNSPECIFIED
Subject Keywords:Cell Segmentation, Convolutional Neural Networks, Developmental Biology, Arabidopsis, Meristem
Record Number:CaltechAUTHORS:20180601-083044304
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180601-083044304
Official Citation:J. Stegmaier et al., "Cell segmentation in 3D confocal images using supervoxel merge-forests with CNN-based hypothesis selection," 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA, 2018, pp. 382-386. doi: 10.1109/ISBI.2018.8363598
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:86734
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:01 Jun 2018 16:07
Last Modified:01 Jun 2018 16:07

Repository Staff Only: item control page