Compresso: Efficient Compression of Segmentation Data for Connectomics

Handle URI:
http://hdl.handle.net/10754/626684
Title:
Compresso: Efficient Compression of Segmentation Data for Connectomics
Authors:
Matejek, Brian; Haehn, Daniel; Lekschas, Fritz; Mitzenmacher, Michael; Pfister, Hanspeter
Abstract:
Recent advances in segmentation methods for connectomics and biomedical imaging produce very large datasets with labels that assign object classes to image pixels. The resulting label volumes are bigger than the raw image data and need compression for efficient storage and transfer. General-purpose compression methods are less effective because the label data consists of large low-frequency regions with structured boundaries unlike natural image data. We present Compresso, a new compression scheme for label data that outperforms existing approaches by using a sliding window to exploit redundancy across border regions in 2D and 3D. We compare our method to existing compression schemes and provide a detailed evaluation on eleven biomedical and image segmentation datasets. Our method provides a factor of 600–2200x compression for label volumes, with running times suitable for practice.
Citation:
Matejek B, Haehn D, Lekschas F, Mitzenmacher M, Pfister H (2017) Compresso: Efficient Compression of Segmentation Data for Connectomics. Lecture Notes in Computer Science: 781–788. Available: http://dx.doi.org/10.1007/978-3-319-66182-7_89.
Publisher:
Springer International Publishing
Journal:
Medical Image Computing and Computer Assisted Intervention − MICCAI 2017
KAUST Grant Number:
OSR-2015-CCF-2533-01
Issue Date:
3-Sep-2017
DOI:
10.1007/978-3-319-66182-7_89
Type:
Book Chapter
ISSN:
0302-9743; 1611-3349
Sponsors:
M. Mitzenmacher is supported in part by NSF grants CNS-1228598, CCF-1320231, CCF-1535795, and CCF-1563710. H. Pfister is supported in part by NSF grants IIS-1447344 and IIS-1607800, by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/Interior Business Center (DoI/IBC) contract number D16PC00002, and by the King Abdullah University of Science and Technology (KAUST) under Award No. OSR-2015-CCF-2533-01.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorMatejek, Brianen
dc.contributor.authorHaehn, Danielen
dc.contributor.authorLekschas, Fritzen
dc.contributor.authorMitzenmacher, Michaelen
dc.contributor.authorPfister, Hanspeteren
dc.date.accessioned2018-01-04T07:51:39Z-
dc.date.available2018-01-04T07:51:39Z-
dc.date.issued2017-09-03en
dc.identifier.citationMatejek B, Haehn D, Lekschas F, Mitzenmacher M, Pfister H (2017) Compresso: Efficient Compression of Segmentation Data for Connectomics. Lecture Notes in Computer Science: 781–788. Available: http://dx.doi.org/10.1007/978-3-319-66182-7_89.en
dc.identifier.issn0302-9743en
dc.identifier.issn1611-3349en
dc.identifier.doi10.1007/978-3-319-66182-7_89en
dc.identifier.urihttp://hdl.handle.net/10754/626684-
dc.description.abstractRecent advances in segmentation methods for connectomics and biomedical imaging produce very large datasets with labels that assign object classes to image pixels. The resulting label volumes are bigger than the raw image data and need compression for efficient storage and transfer. General-purpose compression methods are less effective because the label data consists of large low-frequency regions with structured boundaries unlike natural image data. We present Compresso, a new compression scheme for label data that outperforms existing approaches by using a sliding window to exploit redundancy across border regions in 2D and 3D. We compare our method to existing compression schemes and provide a detailed evaluation on eleven biomedical and image segmentation datasets. Our method provides a factor of 600–2200x compression for label volumes, with running times suitable for practice.en
dc.description.sponsorshipM. Mitzenmacher is supported in part by NSF grants CNS-1228598, CCF-1320231, CCF-1535795, and CCF-1563710. H. Pfister is supported in part by NSF grants IIS-1447344 and IIS-1607800, by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/Interior Business Center (DoI/IBC) contract number D16PC00002, and by the King Abdullah University of Science and Technology (KAUST) under Award No. OSR-2015-CCF-2533-01.en
dc.publisherSpringer International Publishingen
dc.subjectCompressionen
dc.subjectEncodingen
dc.subjectSegmentationen
dc.subjectConnectomicsen
dc.titleCompresso: Efficient Compression of Segmentation Data for Connectomicsen
dc.typeBook Chapteren
dc.identifier.journalMedical Image Computing and Computer Assisted Intervention − MICCAI 2017en
dc.contributor.institutionHarvard University, Cambridge, USAen
kaust.grant.numberOSR-2015-CCF-2533-01en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.