Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging

Yi Hsuan Chou, Shi Yu Hung, Gwo-Giun Lee, Wei Hung Weng, Yi Hua Liao, Chi Kung Sun, Han Ting Shih

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

Abstract

Instead of conventional manual cell segmentation, this paper introduces a computer-Aided diagnosis protocol based on non-invasive in vivo virtual biopsy, third harmonic generation (THG) microscopy, which provides consistency and prompt suggestions for immediate clinical decisions without pain to patients. Specifically, we present a nuclei location re-inspection mechanism using enhanced efficient ellipse Hough transform with labeling and weighting information building upon previous watershed-based nuclei segmentation. This transform approach cautiously identifies nuclei location by considering not only staining intensity, but also examine shape feature to enhance the accuracy of nuclei recognition. The current approach has been implemented and tested on about 400 THG images from 25 healthy volunteers, and the receiver operating characteristic (ROC) curve has demonstrated the better performance of decreased false positive rate and increased true positive rate as compared to other nuclei location detection algorithms.

Original languageEnglish
Title of host publication2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages807-811
Number of pages5
ISBN (Electronic)9781479919482
DOIs
Publication statusPublished - 2015 Aug 31
EventIEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Chengdu, China
Duration: 2015 Jul 122015 Jul 15

Publication series

Name2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings

Other

OtherIEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015
CountryChina
CityChengdu
Period15-07-1215-07-15

Fingerprint

Hough transforms
Harmonic generation
Microscopic examination
Imaging techniques
Computer aided diagnosis
Biopsy
Watersheds
Labeling
Inspection

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Signal Processing

Cite this

Chou, Y. H., Hung, S. Y., Lee, G-G., Weng, W. H., Liao, Y. H., Sun, C. K., & Shih, H. T. (2015). Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging. In 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings (pp. 807-811). [7230516] (2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ChinaSIP.2015.7230516
Chou, Yi Hsuan ; Hung, Shi Yu ; Lee, Gwo-Giun ; Weng, Wei Hung ; Liao, Yi Hua ; Sun, Chi Kung ; Shih, Han Ting. / Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging. 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 807-811 (2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings).
@inproceedings{ce9708ef77f14fc1a4d6907d91e2d0b6,
title = "Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging",
abstract = "Instead of conventional manual cell segmentation, this paper introduces a computer-Aided diagnosis protocol based on non-invasive in vivo virtual biopsy, third harmonic generation (THG) microscopy, which provides consistency and prompt suggestions for immediate clinical decisions without pain to patients. Specifically, we present a nuclei location re-inspection mechanism using enhanced efficient ellipse Hough transform with labeling and weighting information building upon previous watershed-based nuclei segmentation. This transform approach cautiously identifies nuclei location by considering not only staining intensity, but also examine shape feature to enhance the accuracy of nuclei recognition. The current approach has been implemented and tested on about 400 THG images from 25 healthy volunteers, and the receiver operating characteristic (ROC) curve has demonstrated the better performance of decreased false positive rate and increased true positive rate as compared to other nuclei location detection algorithms.",
author = "Chou, {Yi Hsuan} and Hung, {Shi Yu} and Gwo-Giun Lee and Weng, {Wei Hung} and Liao, {Yi Hua} and Sun, {Chi Kung} and Shih, {Han Ting}",
year = "2015",
month = "8",
day = "31",
doi = "10.1109/ChinaSIP.2015.7230516",
language = "English",
series = "2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "807--811",
booktitle = "2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings",
address = "United States",

}

Chou, YH, Hung, SY, Lee, G-G, Weng, WH, Liao, YH, Sun, CK & Shih, HT 2015, Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging. in 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings., 7230516, 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 807-811, IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, 15-07-12. https://doi.org/10.1109/ChinaSIP.2015.7230516

Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging. / Chou, Yi Hsuan; Hung, Shi Yu; Lee, Gwo-Giun; Weng, Wei Hung; Liao, Yi Hua; Sun, Chi Kung; Shih, Han Ting.

2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 807-811 7230516 (2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings).

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

TY - GEN

T1 - Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging

AU - Chou, Yi Hsuan

AU - Hung, Shi Yu

AU - Lee, Gwo-Giun

AU - Weng, Wei Hung

AU - Liao, Yi Hua

AU - Sun, Chi Kung

AU - Shih, Han Ting

PY - 2015/8/31

Y1 - 2015/8/31

N2 - Instead of conventional manual cell segmentation, this paper introduces a computer-Aided diagnosis protocol based on non-invasive in vivo virtual biopsy, third harmonic generation (THG) microscopy, which provides consistency and prompt suggestions for immediate clinical decisions without pain to patients. Specifically, we present a nuclei location re-inspection mechanism using enhanced efficient ellipse Hough transform with labeling and weighting information building upon previous watershed-based nuclei segmentation. This transform approach cautiously identifies nuclei location by considering not only staining intensity, but also examine shape feature to enhance the accuracy of nuclei recognition. The current approach has been implemented and tested on about 400 THG images from 25 healthy volunteers, and the receiver operating characteristic (ROC) curve has demonstrated the better performance of decreased false positive rate and increased true positive rate as compared to other nuclei location detection algorithms.

AB - Instead of conventional manual cell segmentation, this paper introduces a computer-Aided diagnosis protocol based on non-invasive in vivo virtual biopsy, third harmonic generation (THG) microscopy, which provides consistency and prompt suggestions for immediate clinical decisions without pain to patients. Specifically, we present a nuclei location re-inspection mechanism using enhanced efficient ellipse Hough transform with labeling and weighting information building upon previous watershed-based nuclei segmentation. This transform approach cautiously identifies nuclei location by considering not only staining intensity, but also examine shape feature to enhance the accuracy of nuclei recognition. The current approach has been implemented and tested on about 400 THG images from 25 healthy volunteers, and the receiver operating characteristic (ROC) curve has demonstrated the better performance of decreased false positive rate and increased true positive rate as compared to other nuclei location detection algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84957597942&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957597942&partnerID=8YFLogxK

U2 - 10.1109/ChinaSIP.2015.7230516

DO - 10.1109/ChinaSIP.2015.7230516

M3 - Conference contribution

AN - SCOPUS:84957597942

T3 - 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings

SP - 807

EP - 811

BT - 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chou YH, Hung SY, Lee G-G, Weng WH, Liao YH, Sun CK et al. Nuclei location enhancement based on improved efficient ellipse hough transform for third harmonic generation microscopy imaging. In 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 807-811. 7230516. (2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings). https://doi.org/10.1109/ChinaSIP.2015.7230516