Automatic summarization of changes in image sequences using algorithmic information theory

Andrew R. Cohen, Christopher Bjornsson, Ying Chen, Gary Banker, Ena Ladi, Ellen Robey, Sally Temple, Badrinath Roysam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

An algorithmic information theoretic method is presented for object-level summarization of meaningful changes in image sequences. Object extraction and tracking data are represented as an attributed tracking graph (ATG), whose connected subgraphs are compared using an adaptive information distance measure, aided by a closed-form multi-dimensional quantization. The summary is the clustering result and feature subset that maximize the gap statistic. The notion of meaningful summarization is captured by using the gap statistic to estimate the randomness deficiency from algorithmic statistics. When applied to movies of cultured neural progenitor cells, it correctly distinguished neurons from progenitors without requiring the use of a fixative stain. When analyzing intra-cellular molecular transport in cultured neurons undergoing axon specification, it automatically confirmed the role of kinesins in axon specification. Finally, it was able to differentiate wild type from genetically modified thymocyte cells.

Original languageEnglish (US)
Title of host publication2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI
Pages859-862
Number of pages4
DOIs
StatePublished - 2008
Event2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI - Paris, France
Duration: May 14 2008May 17 2008

Other

Other2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI
CountryFrance
CityParis
Period5/14/085/17/08

Fingerprint

Information theory
Statistics
Neurons
Specifications
Set theory
Axons

Keywords

  • Algorithmic information theory
  • Algorithmic statistics
  • Clustering
  • Gap statistic
  • Information distance

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Cohen, A. R., Bjornsson, C., Chen, Y., Banker, G., Ladi, E., Robey, E., ... Roysam, B. (2008). Automatic summarization of changes in image sequences using algorithmic information theory. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI (pp. 859-862). [4541132] https://doi.org/10.1109/ISBI.2008.4541132

Automatic summarization of changes in image sequences using algorithmic information theory. / Cohen, Andrew R.; Bjornsson, Christopher; Chen, Ying; Banker, Gary; Ladi, Ena; Robey, Ellen; Temple, Sally; Roysam, Badrinath.

2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 859-862 4541132.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cohen, AR, Bjornsson, C, Chen, Y, Banker, G, Ladi, E, Robey, E, Temple, S & Roysam, B 2008, Automatic summarization of changes in image sequences using algorithmic information theory. in 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI., 4541132, pp. 859-862, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, Paris, France, 5/14/08. https://doi.org/10.1109/ISBI.2008.4541132
Cohen AR, Bjornsson C, Chen Y, Banker G, Ladi E, Robey E et al. Automatic summarization of changes in image sequences using algorithmic information theory. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 859-862. 4541132 https://doi.org/10.1109/ISBI.2008.4541132
Cohen, Andrew R. ; Bjornsson, Christopher ; Chen, Ying ; Banker, Gary ; Ladi, Ena ; Robey, Ellen ; Temple, Sally ; Roysam, Badrinath. / Automatic summarization of changes in image sequences using algorithmic information theory. 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. pp. 859-862
@inproceedings{ad8ebc7fd7384dd4a43c0ef7741be020,
title = "Automatic summarization of changes in image sequences using algorithmic information theory",
abstract = "An algorithmic information theoretic method is presented for object-level summarization of meaningful changes in image sequences. Object extraction and tracking data are represented as an attributed tracking graph (ATG), whose connected subgraphs are compared using an adaptive information distance measure, aided by a closed-form multi-dimensional quantization. The summary is the clustering result and feature subset that maximize the gap statistic. The notion of meaningful summarization is captured by using the gap statistic to estimate the randomness deficiency from algorithmic statistics. When applied to movies of cultured neural progenitor cells, it correctly distinguished neurons from progenitors without requiring the use of a fixative stain. When analyzing intra-cellular molecular transport in cultured neurons undergoing axon specification, it automatically confirmed the role of kinesins in axon specification. Finally, it was able to differentiate wild type from genetically modified thymocyte cells.",
keywords = "Algorithmic information theory, Algorithmic statistics, Clustering, Gap statistic, Information distance",
author = "Cohen, {Andrew R.} and Christopher Bjornsson and Ying Chen and Gary Banker and Ena Ladi and Ellen Robey and Sally Temple and Badrinath Roysam",
year = "2008",
doi = "10.1109/ISBI.2008.4541132",
language = "English (US)",
isbn = "9781424420032",
pages = "859--862",
booktitle = "2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI",

}

TY - GEN

T1 - Automatic summarization of changes in image sequences using algorithmic information theory

AU - Cohen, Andrew R.

AU - Bjornsson, Christopher

AU - Chen, Ying

AU - Banker, Gary

AU - Ladi, Ena

AU - Robey, Ellen

AU - Temple, Sally

AU - Roysam, Badrinath

PY - 2008

Y1 - 2008

N2 - An algorithmic information theoretic method is presented for object-level summarization of meaningful changes in image sequences. Object extraction and tracking data are represented as an attributed tracking graph (ATG), whose connected subgraphs are compared using an adaptive information distance measure, aided by a closed-form multi-dimensional quantization. The summary is the clustering result and feature subset that maximize the gap statistic. The notion of meaningful summarization is captured by using the gap statistic to estimate the randomness deficiency from algorithmic statistics. When applied to movies of cultured neural progenitor cells, it correctly distinguished neurons from progenitors without requiring the use of a fixative stain. When analyzing intra-cellular molecular transport in cultured neurons undergoing axon specification, it automatically confirmed the role of kinesins in axon specification. Finally, it was able to differentiate wild type from genetically modified thymocyte cells.

AB - An algorithmic information theoretic method is presented for object-level summarization of meaningful changes in image sequences. Object extraction and tracking data are represented as an attributed tracking graph (ATG), whose connected subgraphs are compared using an adaptive information distance measure, aided by a closed-form multi-dimensional quantization. The summary is the clustering result and feature subset that maximize the gap statistic. The notion of meaningful summarization is captured by using the gap statistic to estimate the randomness deficiency from algorithmic statistics. When applied to movies of cultured neural progenitor cells, it correctly distinguished neurons from progenitors without requiring the use of a fixative stain. When analyzing intra-cellular molecular transport in cultured neurons undergoing axon specification, it automatically confirmed the role of kinesins in axon specification. Finally, it was able to differentiate wild type from genetically modified thymocyte cells.

KW - Algorithmic information theory

KW - Algorithmic statistics

KW - Clustering

KW - Gap statistic

KW - Information distance

UR - http://www.scopus.com/inward/record.url?scp=51049088823&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049088823&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2008.4541132

DO - 10.1109/ISBI.2008.4541132

M3 - Conference contribution

SN - 9781424420032

SP - 859

EP - 862

BT - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

ER -