Multireference level set for the characterization of nuclear morphology in glioblastoma multiforme

Hang Chang, Ju Han, Paul Spellman, Bahram Parvin

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Histological tissue sections provide rich information and continue to be the gold standard for the assessment of tissue neoplasm. However, there are a significant amount of technical and biological variations that impede analysis of large histological datasets. In this paper, we have proposed a novel approach for nuclear segmentation in tumor histology sections, which addresses the problem of technical and biological variations by incorporating information from both manually annotated reference patches and the original image. Subsequently, the solution is formulated within a multireference level set framework. This approach has been validated on manually annotated samples and then applied to the TCGA glioblastoma multiforme (GBM) dataset consisting of 440 whole mount tissue sections scanned with either a 20× or 40 × objective, in which, each tissue section varies in size from 40k × 40k pixels to 100k × 100k pixels. Experimental results show a superior performance of the proposed method in comparison with present state of art techniques.

Original languageEnglish (US)
Article number6298001
Pages (from-to)3460-3467
Number of pages8
JournalIEEE Transactions on Biomedical Engineering
Volume59
Issue number12
DOIs
StatePublished - 2012

Fingerprint

Tissue
Pixels
Histology
Tumors

Keywords

  • Multireference level set
  • nuclear segmentation
  • tumor histology sections

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Multireference level set for the characterization of nuclear morphology in glioblastoma multiforme. / Chang, Hang; Han, Ju; Spellman, Paul; Parvin, Bahram.

In: IEEE Transactions on Biomedical Engineering, Vol. 59, No. 12, 6298001, 2012, p. 3460-3467.

Research output: Contribution to journalArticle

@article{3fd4bdfcca5f4549bb88ac143b6e033a,
title = "Multireference level set for the characterization of nuclear morphology in glioblastoma multiforme",
abstract = "Histological tissue sections provide rich information and continue to be the gold standard for the assessment of tissue neoplasm. However, there are a significant amount of technical and biological variations that impede analysis of large histological datasets. In this paper, we have proposed a novel approach for nuclear segmentation in tumor histology sections, which addresses the problem of technical and biological variations by incorporating information from both manually annotated reference patches and the original image. Subsequently, the solution is formulated within a multireference level set framework. This approach has been validated on manually annotated samples and then applied to the TCGA glioblastoma multiforme (GBM) dataset consisting of 440 whole mount tissue sections scanned with either a 20× or 40 × objective, in which, each tissue section varies in size from 40k × 40k pixels to 100k × 100k pixels. Experimental results show a superior performance of the proposed method in comparison with present state of art techniques.",
keywords = "Multireference level set, nuclear segmentation, tumor histology sections",
author = "Hang Chang and Ju Han and Paul Spellman and Bahram Parvin",
year = "2012",
doi = "10.1109/TBME.2012.2218107",
language = "English (US)",
volume = "59",
pages = "3460--3467",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "12",

}

TY - JOUR

T1 - Multireference level set for the characterization of nuclear morphology in glioblastoma multiforme

AU - Chang, Hang

AU - Han, Ju

AU - Spellman, Paul

AU - Parvin, Bahram

PY - 2012

Y1 - 2012

N2 - Histological tissue sections provide rich information and continue to be the gold standard for the assessment of tissue neoplasm. However, there are a significant amount of technical and biological variations that impede analysis of large histological datasets. In this paper, we have proposed a novel approach for nuclear segmentation in tumor histology sections, which addresses the problem of technical and biological variations by incorporating information from both manually annotated reference patches and the original image. Subsequently, the solution is formulated within a multireference level set framework. This approach has been validated on manually annotated samples and then applied to the TCGA glioblastoma multiforme (GBM) dataset consisting of 440 whole mount tissue sections scanned with either a 20× or 40 × objective, in which, each tissue section varies in size from 40k × 40k pixels to 100k × 100k pixels. Experimental results show a superior performance of the proposed method in comparison with present state of art techniques.

AB - Histological tissue sections provide rich information and continue to be the gold standard for the assessment of tissue neoplasm. However, there are a significant amount of technical and biological variations that impede analysis of large histological datasets. In this paper, we have proposed a novel approach for nuclear segmentation in tumor histology sections, which addresses the problem of technical and biological variations by incorporating information from both manually annotated reference patches and the original image. Subsequently, the solution is formulated within a multireference level set framework. This approach has been validated on manually annotated samples and then applied to the TCGA glioblastoma multiforme (GBM) dataset consisting of 440 whole mount tissue sections scanned with either a 20× or 40 × objective, in which, each tissue section varies in size from 40k × 40k pixels to 100k × 100k pixels. Experimental results show a superior performance of the proposed method in comparison with present state of art techniques.

KW - Multireference level set

KW - nuclear segmentation

KW - tumor histology sections

UR - http://www.scopus.com/inward/record.url?scp=84870498543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870498543&partnerID=8YFLogxK

U2 - 10.1109/TBME.2012.2218107

DO - 10.1109/TBME.2012.2218107

M3 - Article

C2 - 22987497

AN - SCOPUS:84870498543

VL - 59

SP - 3460

EP - 3467

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 12

M1 - 6298001

ER -