Tumor localization in tissue microarrays using rotation invariant superpixel pyramids

Shazia Akbar; Lee Jordan; Alastair M. Thompson; Stephen J. McKenna

doi:10.1109/ISBI.2015.7164111

Tumor localization in tissue microarrays using rotation invariant superpixel pyramids

Shazia Akbar (Lead / Corresponding author), Lee Jordan, Alastair M. Thompson, Stephen J. McKenna

Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

356 Downloads (Pure)

Abstract

Tumor localization is an important component of histopathology image analysis; it has yet to be reliably automated for breast cancer histopathology. This paper investigates the use of superpixel classification to localize tumor regions. A superpixel representation retains information about visual structures such as cellular compartments, connective tissue, lumen and fatty tissue without having to commit to semantic segmentation at this level. In order to localize tumor in large images, a rotation invariant spatial pyramid representation is proposed using bags-of-superpixels. The method is evaluated on expert-annotated oestrogen-receptor stained TMA spots and compared to other superpixel classification techniques. Results demonstrate that it performs favorably.

Original language	English
Title of host publication	2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI 2015)
Publisher	IEEE
Pages	1292-1295
Number of pages	4
ISBN (Print)	9781467393300
DOIs	https://doi.org/10.1109/ISBI.2015.7164111
Publication status	Published - 2015
Event	2015 IEEE International Symposium on Biomedical Imaging: From Nano to Macro - New York Marriott at Brooklyn Bridge, New York, United States Duration: 16 Apr 2015 → 19 Apr 2015 http://biomedicalimaging.org/2015/

Conference

Conference	2015 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
Abbreviated title	ISBI 2015
Country/Territory	United States
City	New York
Period	16/04/15 → 19/04/15
Internet address	http://biomedicalimaging.org/2015/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISBI.2015.7164111

Author Accepted Manuscript
© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works Published in: Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium on 16-19 April 2015 Page(s): 1292 - 1295
Accepted author manuscript, 930 KB

Tumour Localisation in Histopathology Images
Akbar, S. (Author), McKenna, S. (Supervisor), Thompson, A. (Supervisor) & Jordan, L. (Supervisor), 2015
Student thesis: Doctoral Thesis › Doctor of Philosophy

File

Cite this

@inproceedings{a1cd81585d0844c3815956e5bcfcbb8a,

title = "Tumor localization in tissue microarrays using rotation invariant superpixel pyramids",

abstract = "Tumor localization is an important component of histopathology image analysis; it has yet to be reliably automated for breast cancer histopathology. This paper investigates the use of superpixel classification to localize tumor regions. A superpixel representation retains information about visual structures such as cellular compartments, connective tissue, lumen and fatty tissue without having to commit to semantic segmentation at this level. In order to localize tumor in large images, a rotation invariant spatial pyramid representation is proposed using bags-of-superpixels. The method is evaluated on expert-annotated oestrogen-receptor stained TMA spots and compared to other superpixel classification techniques. Results demonstrate that it performs favorably.",

author = "Shazia Akbar and Lee Jordan and Thompson, {Alastair M.} and McKenna, {Stephen J.}",

year = "2015",

doi = "10.1109/ISBI.2015.7164111",

language = "English",

isbn = "9781467393300",

pages = "1292--1295",

booktitle = "2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI 2015)",

publisher = "IEEE",

note = "2015 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2015 ; Conference date: 16-04-2015 Through 19-04-2015",

url = "http://biomedicalimaging.org/2015/",

}

Akbar, S, Jordan, L, Thompson, AM & McKenna, SJ 2015, Tumor localization in tissue microarrays using rotation invariant superpixel pyramids. in 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI 2015). IEEE, pp. 1292-1295, 2015 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, New York, United States, 16/04/15. https://doi.org/10.1109/ISBI.2015.7164111

TY - GEN

T1 - Tumor localization in tissue microarrays using rotation invariant superpixel pyramids

AU - Akbar, Shazia

AU - Jordan, Lee

AU - Thompson, Alastair M.

AU - McKenna, Stephen J.

PY - 2015

Y1 - 2015

N2 - Tumor localization is an important component of histopathology image analysis; it has yet to be reliably automated for breast cancer histopathology. This paper investigates the use of superpixel classification to localize tumor regions. A superpixel representation retains information about visual structures such as cellular compartments, connective tissue, lumen and fatty tissue without having to commit to semantic segmentation at this level. In order to localize tumor in large images, a rotation invariant spatial pyramid representation is proposed using bags-of-superpixels. The method is evaluated on expert-annotated oestrogen-receptor stained TMA spots and compared to other superpixel classification techniques. Results demonstrate that it performs favorably.

AB - Tumor localization is an important component of histopathology image analysis; it has yet to be reliably automated for breast cancer histopathology. This paper investigates the use of superpixel classification to localize tumor regions. A superpixel representation retains information about visual structures such as cellular compartments, connective tissue, lumen and fatty tissue without having to commit to semantic segmentation at this level. In order to localize tumor in large images, a rotation invariant spatial pyramid representation is proposed using bags-of-superpixels. The method is evaluated on expert-annotated oestrogen-receptor stained TMA spots and compared to other superpixel classification techniques. Results demonstrate that it performs favorably.

U2 - 10.1109/ISBI.2015.7164111

DO - 10.1109/ISBI.2015.7164111

M3 - Conference contribution

SN - 9781467393300

SP - 1292

EP - 1295

BT - 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI 2015)

PB - IEEE

T2 - 2015 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

Y2 - 16 April 2015 through 19 April 2015

ER -

Tumor localization in tissue microarrays using rotation invariant superpixel pyramids

Abstract

Conference

UN SDGs

Access to Document

Fingerprint

Student theses

Tumour Localisation in Histopathology Images

Cite this