2026-09-20T02:32:11Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1006442026-06-06T00:55:33Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Nir Shavit. Nguyen, Quan, M. Eng. (Quan T.) Massachusetts Institute of Technology Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2016-01-04T20:01:38Z 2016-01-04T20:01:38Z 2015 2015 http://hdl.handle.net/1721.1/100644 933241344 Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Title as it appears in MIT Commencement Exercises program, June 5, 2015: Connectomics project : performance engineering neural image segmentation. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 77-79). Segmentation of images, the process of grouping together pixels of the same object, is one of the major challenges in connectome extraction. Since connectomics data consist of large quantity of digital information generated by the electron microscope, there is a necessity for a highly scalable system that performs segmentation. To date, the state-of-the-art segmentation libraries such as GALA and NeuroProof lack parallel capability to be run on multicore machines in a distributed setting in order to achieve the scalability desired. Employing many performance engineering techniques, I parallelize a pipeline that uses the existing segmentation algorithms as building blocks to perform segmentation on EM grayscale images. For an input image stack of dimensions 1024 x 1024 x 100, the parallel segmentation program achieves a speedup of 5.3 counting I/O and 9.4 not counting I/O running on an 18-core machine. The program has become I/O bound, which is a better fit to run on a distributed computing framework. In this thesis, the contribution includes coming up with parallel algorithms for constructing a regional adjacency graph from labeled pixels and agglomerating an over-segmentation to obtain the final segmentation. The agglomeration process in particular is challenging to parallelize because most graph-based segmentation libraries entail very complex dependency. This has led many people to believe that the process is inherently sequential. However, I found a way to get good speedup by sacrificing some segmentation quality. It turns out that one could trade o a negligible amount in quality for a large gain in parallelism. by Quan Nguyen. M.Eng. 79 pages eng Massachusetts Institute of Technology M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Parallel and scalable neural image segmentation for connectome graph extraction Connectomics project : performance engineering neural image segmentation Performance engineering neural image segmentation Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b2ac27a3-47d8-406c-9bd3-ccd0cc51e77e"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Parallel and scalable neural image segmentation for connectome graph extraction</Title> <Subtitle>Connectomics project : performance engineering neural image segmentation</Subtitle> <Subtitle>Performance engineering neural image segmentation</Subtitle> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2015</PublicationDate> <Authors> <Author> <DisplayName>Nguyen, Quan, M. Eng. (Quan T.) Massachusetts Institute of Technology</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>Segmentation of images, the process of grouping together pixels of the same object, is one of the major challenges in connectome extraction. Since connectomics data consist of large quantity of digital information generated by the electron microscope, there is a necessity for a highly scalable system that performs segmentation. To date, the state-of-the-art segmentation libraries such as GALA and NeuroProof lack parallel capability to be run on multicore machines in a distributed setting in order to achieve the scalability desired. Employing many performance engineering techniques, I parallelize a pipeline that uses the existing segmentation algorithms as building blocks to perform segmentation on EM grayscale images. For an input image stack of dimensions 1024 x 1024 x 100, the parallel segmentation program achieves a speedup of 5.3 counting I/O and 9.4 not counting I/O running on an 18-core machine. The program has become I/O bound, which is a better fit to run on a distributed computing framework. In this thesis, the contribution includes coming up with parallel algorithms for constructing a regional adjacency graph from labeled pixels and agglomerating an over-segmentation to obtain the final segmentation. The agglomeration process in particular is challenging to parallelize because most graph-based segmentation libraries entail very complex dependency. This has led many people to believe that the process is inherently sequential. However, I found a way to get good speedup by sacrificing some segmentation quality. It turns out that one could trade o a negligible amount in quality for a large gain in parallelism.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>