Adding large EM stack support

Handle URI:
http://hdl.handle.net/10754/622512
Title:
Adding large EM stack support
Authors:
Holst, Glendon; Berg, Stuart; Kare, Kalpana; Magistretti, Pierre J. ( 0000-0002-6678-320X ) ; Cali, Corrado
Abstract:
Serial section electron microscopy (SSEM) image stacks generated using high throughput microscopy techniques are an integral tool for investigating brain connectivity and cell morphology. FIB or 3View scanning electron microscopes easily generate gigabytes of data. In order to produce analyzable 3D dataset from the imaged volumes, efficient and reliable image segmentation is crucial. Classical manual approaches to segmentation are time consuming and labour intensive. Semiautomatic seeded watershed segmentation algorithms, such as those implemented by ilastik image processing software, are a very powerful alternative, substantially speeding up segmentation times. We have used ilastik effectively for small EM stacks – on a laptop, no less; however, ilastik was unable to carve the large EM stacks we needed to segment because its memory requirements grew too large – even for the biggest workstations we had available. For this reason, we refactored the carving module of ilastik to scale it up to large EM stacks on large workstations, and tested its efficiency. We modified the carving module, building on existing blockwise processing functionality to process data in manageable chunks that can fit within RAM (main memory). We review this refactoring work, highlighting the software architecture, design choices, modifications, and issues encountered.
KAUST Department:
KAUST Visualization Laboratory (KVL); Biological and Environmental Sciences and Engineering (BESE) Division
Citation:
Holst G, Berg S, Kare K, Magistretti P, Cali C (2016) Adding large EM stack support. 2016 4th Saudi International Conference on Information Technology (Big Data Analysis) (KACSTIT). Available: http://dx.doi.org/10.1109/KACSTIT.2016.7756066.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2016 4th Saudi International Conference on Information Technology (Big Data Analysis) (KACSTIT)
Issue Date:
1-Dec-2016
DOI:
10.1109/KACSTIT.2016.7756066
Type:
Conference Paper
Sponsors:
This work was supported by CRG3 KAUST grant
Additional Links:
http://ieeexplore.ieee.org/document/7756066/
Appears in Collections:
Conference Papers; KAUST Visualization Laboratory (KVL); Biological and Environmental Sciences and Engineering (BESE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorHolst, Glendonen
dc.contributor.authorBerg, Stuarten
dc.contributor.authorKare, Kalpanaen
dc.contributor.authorMagistretti, Pierre J.en
dc.contributor.authorCali, Corradoen
dc.date.accessioned2017-01-02T09:55:27Z-
dc.date.available2017-01-02T09:55:27Z-
dc.date.issued2016-12-01en
dc.identifier.citationHolst G, Berg S, Kare K, Magistretti P, Cali C (2016) Adding large EM stack support. 2016 4th Saudi International Conference on Information Technology (Big Data Analysis) (KACSTIT). Available: http://dx.doi.org/10.1109/KACSTIT.2016.7756066.en
dc.identifier.doi10.1109/KACSTIT.2016.7756066en
dc.identifier.urihttp://hdl.handle.net/10754/622512-
dc.description.abstractSerial section electron microscopy (SSEM) image stacks generated using high throughput microscopy techniques are an integral tool for investigating brain connectivity and cell morphology. FIB or 3View scanning electron microscopes easily generate gigabytes of data. In order to produce analyzable 3D dataset from the imaged volumes, efficient and reliable image segmentation is crucial. Classical manual approaches to segmentation are time consuming and labour intensive. Semiautomatic seeded watershed segmentation algorithms, such as those implemented by ilastik image processing software, are a very powerful alternative, substantially speeding up segmentation times. We have used ilastik effectively for small EM stacks – on a laptop, no less; however, ilastik was unable to carve the large EM stacks we needed to segment because its memory requirements grew too large – even for the biggest workstations we had available. For this reason, we refactored the carving module of ilastik to scale it up to large EM stacks on large workstations, and tested its efficiency. We modified the carving module, building on existing blockwise processing functionality to process data in manageable chunks that can fit within RAM (main memory). We review this refactoring work, highlighting the software architecture, design choices, modifications, and issues encountered.en
dc.description.sponsorshipThis work was supported by CRG3 KAUST granten
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/document/7756066/en
dc.subjectcode refactoringen
dc.subjectimage analysisen
dc.subjectsegmentationen
dc.subjectblockwise carvingen
dc.subjectlarge dataen
dc.titleAdding large EM stack supporten
dc.typeConference Paperen
dc.contributor.departmentKAUST Visualization Laboratory (KVL)en
dc.contributor.departmentBiological and Environmental Sciences and Engineering (BESE) Divisionen
dc.identifier.journal2016 4th Saudi International Conference on Information Technology (Big Data Analysis) (KACSTIT)en
dc.contributor.institutionHHMI Janelia Research Campus Virginia, United Statesen
kaust.authorHolst, Glendonen
kaust.authorKare, Kalpanaen
kaust.authorMagistretti, Pierre J.en
kaust.authorCali, Corradoen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.