Curvelet-based classification of prostate cancer histological images of critical Gleason scores

Wen Chyi Lin, Ching Chung Li, Christhunesa S. Christudass, Jonathan Ira Epstein, Robert W. Veltri

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

Abstract

This paper is aimed at the development of an approach of applying the curvelet transform to images of prostatectomy pathological specimens of critical Gleason grades for computer-aided classification. A set of Tissue MicroArray (TMA) images from the Johns Hopkins University have been used as the data base. We utilize a moving window to sample multiple patches of a given image leading to a majority decision by the patches for image class assignment. The curvelet-based feature extraction may capture both textural and, implicitly, structural information in an image patch. A tree-structured classifier consisting of three Gaussian-kernel support vector machines each with an embedded voting mechanism has been successfully trained and tested yielding high accuracy to classify tissue images of four critical Gleason scores (GS) 3+3, 3+4, 4+3 and 4+4. The experimental result has demonstrated an enhanced performance as compared to other reported works.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages1020-1023
Number of pages4
Volume2015-July
ISBN (Print)9781479923748
DOIs
StatePublished - Jul 21 2015
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: Apr 16 2015Apr 19 2015

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period4/16/154/19/15

Fingerprint

Neoplasm Grading
Prostatic Neoplasms
Tissue
Politics
Microarrays
Prostatectomy
Support vector machines
Feature extraction
Classifiers
Databases
1,21-diamino-4,9,13,18-tetraazahenicosane
Support Vector Machine

Keywords

  • Curvelets
  • Gleason grading
  • Gleason scores
  • prostate cancer
  • tissue texture classification

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Lin, W. C., Li, C. C., Christudass, C. S., Epstein, J. I., & Veltri, R. W. (2015). Curvelet-based classification of prostate cancer histological images of critical Gleason scores. In Proceedings - International Symposium on Biomedical Imaging (Vol. 2015-July, pp. 1020-1023). [7164044] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7164044

Curvelet-based classification of prostate cancer histological images of critical Gleason scores. / Lin, Wen Chyi; Li, Ching Chung; Christudass, Christhunesa S.; Epstein, Jonathan Ira; Veltri, Robert W.

Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. p. 1020-1023 7164044.

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

Lin, WC, Li, CC, Christudass, CS, Epstein, JI & Veltri, RW 2015, Curvelet-based classification of prostate cancer histological images of critical Gleason scores. in Proceedings - International Symposium on Biomedical Imaging. vol. 2015-July, 7164044, IEEE Computer Society, pp. 1020-1023, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 4/16/15. https://doi.org/10.1109/ISBI.2015.7164044
Lin WC, Li CC, Christudass CS, Epstein JI, Veltri RW. Curvelet-based classification of prostate cancer histological images of critical Gleason scores. In Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July. IEEE Computer Society. 2015. p. 1020-1023. 7164044 https://doi.org/10.1109/ISBI.2015.7164044
Lin, Wen Chyi ; Li, Ching Chung ; Christudass, Christhunesa S. ; Epstein, Jonathan Ira ; Veltri, Robert W. / Curvelet-based classification of prostate cancer histological images of critical Gleason scores. Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. pp. 1020-1023
@inproceedings{cb3ff472d5d3485db3b26b45907c5a3c,
title = "Curvelet-based classification of prostate cancer histological images of critical Gleason scores",
abstract = "This paper is aimed at the development of an approach of applying the curvelet transform to images of prostatectomy pathological specimens of critical Gleason grades for computer-aided classification. A set of Tissue MicroArray (TMA) images from the Johns Hopkins University have been used as the data base. We utilize a moving window to sample multiple patches of a given image leading to a majority decision by the patches for image class assignment. The curvelet-based feature extraction may capture both textural and, implicitly, structural information in an image patch. A tree-structured classifier consisting of three Gaussian-kernel support vector machines each with an embedded voting mechanism has been successfully trained and tested yielding high accuracy to classify tissue images of four critical Gleason scores (GS) 3+3, 3+4, 4+3 and 4+4. The experimental result has demonstrated an enhanced performance as compared to other reported works.",
keywords = "Curvelets, Gleason grading, Gleason scores, prostate cancer, tissue texture classification",
author = "Lin, {Wen Chyi} and Li, {Ching Chung} and Christudass, {Christhunesa S.} and Epstein, {Jonathan Ira} and Veltri, {Robert W.}",
year = "2015",
month = "7",
day = "21",
doi = "10.1109/ISBI.2015.7164044",
language = "English (US)",
isbn = "9781479923748",
volume = "2015-July",
pages = "1020--1023",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Curvelet-based classification of prostate cancer histological images of critical Gleason scores

AU - Lin, Wen Chyi

AU - Li, Ching Chung

AU - Christudass, Christhunesa S.

AU - Epstein, Jonathan Ira

AU - Veltri, Robert W.

PY - 2015/7/21

Y1 - 2015/7/21

N2 - This paper is aimed at the development of an approach of applying the curvelet transform to images of prostatectomy pathological specimens of critical Gleason grades for computer-aided classification. A set of Tissue MicroArray (TMA) images from the Johns Hopkins University have been used as the data base. We utilize a moving window to sample multiple patches of a given image leading to a majority decision by the patches for image class assignment. The curvelet-based feature extraction may capture both textural and, implicitly, structural information in an image patch. A tree-structured classifier consisting of three Gaussian-kernel support vector machines each with an embedded voting mechanism has been successfully trained and tested yielding high accuracy to classify tissue images of four critical Gleason scores (GS) 3+3, 3+4, 4+3 and 4+4. The experimental result has demonstrated an enhanced performance as compared to other reported works.

AB - This paper is aimed at the development of an approach of applying the curvelet transform to images of prostatectomy pathological specimens of critical Gleason grades for computer-aided classification. A set of Tissue MicroArray (TMA) images from the Johns Hopkins University have been used as the data base. We utilize a moving window to sample multiple patches of a given image leading to a majority decision by the patches for image class assignment. The curvelet-based feature extraction may capture both textural and, implicitly, structural information in an image patch. A tree-structured classifier consisting of three Gaussian-kernel support vector machines each with an embedded voting mechanism has been successfully trained and tested yielding high accuracy to classify tissue images of four critical Gleason scores (GS) 3+3, 3+4, 4+3 and 4+4. The experimental result has demonstrated an enhanced performance as compared to other reported works.

KW - Curvelets

KW - Gleason grading

KW - Gleason scores

KW - prostate cancer

KW - tissue texture classification

UR - http://www.scopus.com/inward/record.url?scp=84944322076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944322076&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7164044

DO - 10.1109/ISBI.2015.7164044

M3 - Conference contribution

SN - 9781479923748

VL - 2015-July

SP - 1020

EP - 1023

BT - Proceedings - International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -