Nuclei detection based on secant normal voting with skipping ranges in stained histopathological images

Research output: Contribution to journalArticle

Abstract

Seed detection or sometimes known as nuclei detection is a prerequisite step of nuclei segmentation which plays a critical role in quantitative cell analysis. The detection result is considered as accurate if each detected seed lies only in one nucleus and is close to the nucleus center. In previous works, voting methods are employed to detect nucleus center by extracting the nucleus saliency features. However, these methods still encounter the risk of false seeding, especially for the heterogeneous intensity images. To overcome the drawbacks of previous works, a novel detection method is proposed, which is called secant normal voting. Secant normal voting achieves good performance with the proposed skipping range. Skipping range avoids over-segmentation by preventing false seeding on the occlusion regions. Nucleus centers are obtained by mean-shift clustering from clouds of voting points. In the experiments, we show that our proposed method outperforms the comparison methods by achieving high detection accuracy without sacrificing the computational efficiency.

Original languageEnglish
Pages (from-to)523-530
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE101D
Issue number2
DOIs
Publication statusPublished - 2018 Feb 1

Fingerprint

Seed
Computational efficiency
Experiments

Keywords

  • Hematoxylin and Eosin (H&E) staining
  • Nuclei detection
  • Secant normal voting
  • Skipping range
  • Splitting point

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

@article{3500dbf2788e4ee7a6db30fed2ca53e1,
title = "Nuclei detection based on secant normal voting with skipping ranges in stained histopathological images",
abstract = "Seed detection or sometimes known as nuclei detection is a prerequisite step of nuclei segmentation which plays a critical role in quantitative cell analysis. The detection result is considered as accurate if each detected seed lies only in one nucleus and is close to the nucleus center. In previous works, voting methods are employed to detect nucleus center by extracting the nucleus saliency features. However, these methods still encounter the risk of false seeding, especially for the heterogeneous intensity images. To overcome the drawbacks of previous works, a novel detection method is proposed, which is called secant normal voting. Secant normal voting achieves good performance with the proposed skipping range. Skipping range avoids over-segmentation by preventing false seeding on the occlusion regions. Nucleus centers are obtained by mean-shift clustering from clouds of voting points. In the experiments, we show that our proposed method outperforms the comparison methods by achieving high detection accuracy without sacrificing the computational efficiency.",
keywords = "Hematoxylin and Eosin (H&E) staining, Nuclei detection, Secant normal voting, Skipping range, Splitting point",
author = "Xueting Lim and Kenjiro Sugimoto and Seiichiro Kamata",
year = "2018",
month = "2",
day = "1",
doi = "10.1587/transinf.2017EDP7326",
language = "English",
volume = "E101D",
pages = "523--530",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "2",

}

TY - JOUR

T1 - Nuclei detection based on secant normal voting with skipping ranges in stained histopathological images

AU - Lim, Xueting

AU - Sugimoto, Kenjiro

AU - Kamata, Seiichiro

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Seed detection or sometimes known as nuclei detection is a prerequisite step of nuclei segmentation which plays a critical role in quantitative cell analysis. The detection result is considered as accurate if each detected seed lies only in one nucleus and is close to the nucleus center. In previous works, voting methods are employed to detect nucleus center by extracting the nucleus saliency features. However, these methods still encounter the risk of false seeding, especially for the heterogeneous intensity images. To overcome the drawbacks of previous works, a novel detection method is proposed, which is called secant normal voting. Secant normal voting achieves good performance with the proposed skipping range. Skipping range avoids over-segmentation by preventing false seeding on the occlusion regions. Nucleus centers are obtained by mean-shift clustering from clouds of voting points. In the experiments, we show that our proposed method outperforms the comparison methods by achieving high detection accuracy without sacrificing the computational efficiency.

AB - Seed detection or sometimes known as nuclei detection is a prerequisite step of nuclei segmentation which plays a critical role in quantitative cell analysis. The detection result is considered as accurate if each detected seed lies only in one nucleus and is close to the nucleus center. In previous works, voting methods are employed to detect nucleus center by extracting the nucleus saliency features. However, these methods still encounter the risk of false seeding, especially for the heterogeneous intensity images. To overcome the drawbacks of previous works, a novel detection method is proposed, which is called secant normal voting. Secant normal voting achieves good performance with the proposed skipping range. Skipping range avoids over-segmentation by preventing false seeding on the occlusion regions. Nucleus centers are obtained by mean-shift clustering from clouds of voting points. In the experiments, we show that our proposed method outperforms the comparison methods by achieving high detection accuracy without sacrificing the computational efficiency.

KW - Hematoxylin and Eosin (H&E) staining

KW - Nuclei detection

KW - Secant normal voting

KW - Skipping range

KW - Splitting point

UR - http://www.scopus.com/inward/record.url?scp=85041536743&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041536743&partnerID=8YFLogxK

U2 - 10.1587/transinf.2017EDP7326

DO - 10.1587/transinf.2017EDP7326

M3 - Article

AN - SCOPUS:85041536743

VL - E101D

SP - 523

EP - 530

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 2

ER -