Abstract

Histology is used in both clinical and research contexts as a highly sensitive method for detecting morphological abnormalities in organ tissues. Although modern scanning equipment has enabled high-throughput digitization of high-resolution histology slides, the manual scoring and annotation of these images is a tedious, subjective, and sometimes error-prone process. A number of methods have been proposed for the automated characterization of histology images, most of which rely on the extraction of texture features used for classifier training. The irregular, nonlinear shapes of certain types of tissues can obscure the implicit symmetries observed within them, making it difficult or cumbersome for automated methods to extract texture features quickly and reliably. Using larval zebrafish eye and gut tissues as a pilot model, we present a prototype method for transforming the appearance of these irregularly-shaped tissues into onedimensional, "frieze-like" patterns. We show that the reduced dimensionality of the patterns may allow them to be characterized with greater efficiency and accuracy than by previous methods of image analysis, which in turn enables potentially greater accuracy in the retrieval of histology images exhibiting abnormalities of interest to pathologists and researchers.

Original languageEnglish (US)
Title of host publicationCIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval
Pages581-590
Number of pages10
DOIs
StatePublished - Dec 17 2008
Event2008 International Conference on Image and Video Retrieval, CIVR 2008 - Niagara Falls, ON, United States
Duration: Jul 7 2008Jul 9 2008

Publication series

NameCIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval

Other

Other2008 International Conference on Image and Video Retrieval, CIVR 2008
CountryUnited States
CityNiagara Falls, ON
Period7/7/087/9/08

Fingerprint

Histology
Tissue
Textures
Analog to digital conversion
Image analysis
Classifiers
Throughput
Scanning

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Canada, B. A., Thomas, G. K., Cheng, K. C., Wang, J. Z., & Liu, Y. (2008). Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns. In CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval (pp. 581-590). (CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval). https://doi.org/10.1145/1386352.1386437
Canada, Brian A. ; Thomas, Georgia K. ; Cheng, Keith C. ; Wang, James Z. ; Liu, Yanxi. / Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns. CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval. 2008. pp. 581-590 (CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval).
@inproceedings{188c4ff9ba8244e9b8d4fe64ab2e6eb0,
title = "Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns",
abstract = "Histology is used in both clinical and research contexts as a highly sensitive method for detecting morphological abnormalities in organ tissues. Although modern scanning equipment has enabled high-throughput digitization of high-resolution histology slides, the manual scoring and annotation of these images is a tedious, subjective, and sometimes error-prone process. A number of methods have been proposed for the automated characterization of histology images, most of which rely on the extraction of texture features used for classifier training. The irregular, nonlinear shapes of certain types of tissues can obscure the implicit symmetries observed within them, making it difficult or cumbersome for automated methods to extract texture features quickly and reliably. Using larval zebrafish eye and gut tissues as a pilot model, we present a prototype method for transforming the appearance of these irregularly-shaped tissues into onedimensional, {"}frieze-like{"} patterns. We show that the reduced dimensionality of the patterns may allow them to be characterized with greater efficiency and accuracy than by previous methods of image analysis, which in turn enables potentially greater accuracy in the retrieval of histology images exhibiting abnormalities of interest to pathologists and researchers.",
author = "Canada, {Brian A.} and Thomas, {Georgia K.} and Cheng, {Keith C.} and Wang, {James Z.} and Yanxi Liu",
year = "2008",
month = "12",
day = "17",
doi = "10.1145/1386352.1386437",
language = "English (US)",
isbn = "9781605580708",
series = "CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval",
pages = "581--590",
booktitle = "CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval",

}

Canada, BA, Thomas, GK, Cheng, KC, Wang, JZ & Liu, Y 2008, Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns. in CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval. CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval, pp. 581-590, 2008 International Conference on Image and Video Retrieval, CIVR 2008, Niagara Falls, ON, United States, 7/7/08. https://doi.org/10.1145/1386352.1386437

Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns. / Canada, Brian A.; Thomas, Georgia K.; Cheng, Keith C.; Wang, James Z.; Liu, Yanxi.

CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval. 2008. p. 581-590 (CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval).

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

TY - GEN

T1 - Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns

AU - Canada, Brian A.

AU - Thomas, Georgia K.

AU - Cheng, Keith C.

AU - Wang, James Z.

AU - Liu, Yanxi

PY - 2008/12/17

Y1 - 2008/12/17

N2 - Histology is used in both clinical and research contexts as a highly sensitive method for detecting morphological abnormalities in organ tissues. Although modern scanning equipment has enabled high-throughput digitization of high-resolution histology slides, the manual scoring and annotation of these images is a tedious, subjective, and sometimes error-prone process. A number of methods have been proposed for the automated characterization of histology images, most of which rely on the extraction of texture features used for classifier training. The irregular, nonlinear shapes of certain types of tissues can obscure the implicit symmetries observed within them, making it difficult or cumbersome for automated methods to extract texture features quickly and reliably. Using larval zebrafish eye and gut tissues as a pilot model, we present a prototype method for transforming the appearance of these irregularly-shaped tissues into onedimensional, "frieze-like" patterns. We show that the reduced dimensionality of the patterns may allow them to be characterized with greater efficiency and accuracy than by previous methods of image analysis, which in turn enables potentially greater accuracy in the retrieval of histology images exhibiting abnormalities of interest to pathologists and researchers.

AB - Histology is used in both clinical and research contexts as a highly sensitive method for detecting morphological abnormalities in organ tissues. Although modern scanning equipment has enabled high-throughput digitization of high-resolution histology slides, the manual scoring and annotation of these images is a tedious, subjective, and sometimes error-prone process. A number of methods have been proposed for the automated characterization of histology images, most of which rely on the extraction of texture features used for classifier training. The irregular, nonlinear shapes of certain types of tissues can obscure the implicit symmetries observed within them, making it difficult or cumbersome for automated methods to extract texture features quickly and reliably. Using larval zebrafish eye and gut tissues as a pilot model, we present a prototype method for transforming the appearance of these irregularly-shaped tissues into onedimensional, "frieze-like" patterns. We show that the reduced dimensionality of the patterns may allow them to be characterized with greater efficiency and accuracy than by previous methods of image analysis, which in turn enables potentially greater accuracy in the retrieval of histology images exhibiting abnormalities of interest to pathologists and researchers.

UR - http://www.scopus.com/inward/record.url?scp=57549111054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57549111054&partnerID=8YFLogxK

U2 - 10.1145/1386352.1386437

DO - 10.1145/1386352.1386437

M3 - Conference contribution

AN - SCOPUS:57549111054

SN - 9781605580708

T3 - CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval

SP - 581

EP - 590

BT - CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval

ER -

Canada BA, Thomas GK, Cheng KC, Wang JZ, Liu Y. Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns. In CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval. 2008. p. 581-590. (CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval). https://doi.org/10.1145/1386352.1386437