Nuclei Detection Based on Secant Normal Voting with Skipping Ranges in Stained Histopathological Images

XueTing LIM; Kenjiro SUGIMOTO; Sei-ichiro KAMATA

doi:10.1587/transinf.2017EDP7326

Nuclei Detection Based on Secant Normal Voting with Skipping Ranges in Stained Histopathological Images

XueTing LIM, Kenjiro SUGIMOTO, Sei-ichiro KAMATA

Full Text Views

0

Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.2 pp.523-530

Publication Date: 2018/02/01

Publicized: 2017/11/14

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017EDP7326

Type of Manuscript: PAPER

Category: Biological Engineering

Authors

XueTing LIM
  Waseda University
Kenjiro SUGIMOTO
  Waseda University
Sei-ichiro KAMATA
  Waseda University

Keyword

secant normal voting, skipping range, splitting point, nuclei detection, Hematoxylin and Eosin (H&E) staining

Cite this

Copy

XueTing LIM, Kenjiro SUGIMOTO, Sei-ichiro KAMATA, "Nuclei Detection Based on Secant Normal Voting with Skipping Ranges in Stained Histopathological Images" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 2, pp. 523-530, February 2018, doi: 10.1587/transinf.2017EDP7326.
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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7326/_p

Copy

@ARTICLE{e101-d_2_523,
author={XueTing LIM, Kenjiro SUGIMOTO, Sei-ichiro KAMATA, },
journal={IEICE TRANSACTIONS on Information},
title={Nuclei Detection Based on Secant Normal Voting with Skipping Ranges in Stained Histopathological Images},
year={2018},
volume={E101-D},
number={2},
pages={523-530},
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={},
doi={10.1587/transinf.2017EDP7326},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Nuclei Detection Based on Secant Normal Voting with Skipping Ranges in Stained Histopathological Images
T2 - IEICE TRANSACTIONS on Information
SP - 523
EP - 530
AU - XueTing LIM
AU - Kenjiro SUGIMOTO
AU - Sei-ichiro KAMATA
PY - 2018
DO - 10.1587/transinf.2017EDP7326
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2018
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.
ER -