Adaptive segmentation of nuclei in H&E stained tendon microscopy

Bo I. Chuang, Po-Ting Wu, Jian Han Hsu, I. Ming Jou, Fong-chin Su, Yung-Nien Sun

研究成果: Conference contribution

摘要

Tendiopathy is a popular clinical issue in recent years. In most cases like trigger finger or tennis elbow, the pathology change can be observed under H&E stained tendon microscopy. However, the qualitative analysis is too subjective and thus the results heavily depend on the observers. We develop an automatic segmentation procedure which segments and counts the nuclei in H&E stained tendon microscopy fast and precisely. This procedure first determines the complexity of images and then segments the nuclei from the image. For the complex images, the proposed method adopts sampling-based thresholding to segment the nuclei. While for the simple images, the Laplacian-based thresholding is employed to re-segment the nuclei more accurately. In the experiments, the proposed method is compared with the experts outlined results. The nuclei number of proposed method is closed to the experts counted, and the processing time of proposed method is much faster than the experts'.

原文English
主出版物標題Seventh International Conference on Graphic and Image Processing, ICGIP 2015
編輯Xudong Jiang, Xudong Jiang, Yulin Wang, Xudong Jiang, Yulin Wang, Xudong Jiang, Yulin Wang, Yulin Wang
發行者SPIE
ISBN(電子)9781510600584, 9781510600584, 9781510600584, 9781510600584
DOIs
出版狀態Published - 2015 一月 1
事件7th International Conference on Graphic and Image Processing, ICGIP 2015 - Singapore, Singapore
持續時間: 2015 十月 232015 十月 25

出版系列

名字Proceedings of SPIE - The International Society for Optical Engineering
9817
ISSN(列印)0277-786X
ISSN(電子)1996-756X

Other

Other7th International Conference on Graphic and Image Processing, ICGIP 2015
國家Singapore
城市Singapore
期間15-10-2315-10-25

指紋

tendons
Tendons
Microscopy
Nucleus
Microscopic examination
Segmentation
microscopy
nuclei
Pathology
Thresholding
Sampling
Processing
qualitative analysis
pathology
Sampling Methods
Qualitative Analysis
Trigger
Experiments
Observer
Count

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

引用此文

Chuang, B. I., Wu, P-T., Hsu, J. H., Jou, I. M., Su, F., & Sun, Y-N. (2015). Adaptive segmentation of nuclei in H&E stained tendon microscopy. 於 X. Jiang, X. Jiang, Y. Wang, X. Jiang, Y. Wang, X. Jiang, Y. Wang, ... Y. Wang (編輯), Seventh International Conference on Graphic and Image Processing, ICGIP 2015 [98170L] (Proceedings of SPIE - The International Society for Optical Engineering; 卷 9817). SPIE. https://doi.org/10.1117/12.2228807
Chuang, Bo I. ; Wu, Po-Ting ; Hsu, Jian Han ; Jou, I. Ming ; Su, Fong-chin ; Sun, Yung-Nien. / Adaptive segmentation of nuclei in H&E stained tendon microscopy. Seventh International Conference on Graphic and Image Processing, ICGIP 2015. 編輯 / Xudong Jiang ; Xudong Jiang ; Yulin Wang ; Xudong Jiang ; Yulin Wang ; Xudong Jiang ; Yulin Wang ; Yulin Wang. SPIE, 2015. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{8e54a0087c784345ad51251569a557fe,
title = "Adaptive segmentation of nuclei in H&E stained tendon microscopy",
abstract = "Tendiopathy is a popular clinical issue in recent years. In most cases like trigger finger or tennis elbow, the pathology change can be observed under H&E stained tendon microscopy. However, the qualitative analysis is too subjective and thus the results heavily depend on the observers. We develop an automatic segmentation procedure which segments and counts the nuclei in H&E stained tendon microscopy fast and precisely. This procedure first determines the complexity of images and then segments the nuclei from the image. For the complex images, the proposed method adopts sampling-based thresholding to segment the nuclei. While for the simple images, the Laplacian-based thresholding is employed to re-segment the nuclei more accurately. In the experiments, the proposed method is compared with the experts outlined results. The nuclei number of proposed method is closed to the experts counted, and the processing time of proposed method is much faster than the experts'.",
author = "Chuang, {Bo I.} and Po-Ting Wu and Hsu, {Jian Han} and Jou, {I. Ming} and Fong-chin Su and Yung-Nien Sun",
year = "2015",
month = "1",
day = "1",
doi = "10.1117/12.2228807",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Xudong Jiang and Xudong Jiang and Yulin Wang and Xudong Jiang and Yulin Wang and Xudong Jiang and Yulin Wang and Yulin Wang",
booktitle = "Seventh International Conference on Graphic and Image Processing, ICGIP 2015",
address = "United States",

}

Chuang, BI, Wu, P-T, Hsu, JH, Jou, IM, Su, F & Sun, Y-N 2015, Adaptive segmentation of nuclei in H&E stained tendon microscopy. 於 X Jiang, X Jiang, Y Wang, X Jiang, Y Wang, X Jiang, Y Wang & Y Wang (編輯), Seventh International Conference on Graphic and Image Processing, ICGIP 2015., 98170L, Proceedings of SPIE - The International Society for Optical Engineering, 卷 9817, SPIE, 7th International Conference on Graphic and Image Processing, ICGIP 2015, Singapore, Singapore, 15-10-23. https://doi.org/10.1117/12.2228807

Adaptive segmentation of nuclei in H&E stained tendon microscopy. / Chuang, Bo I.; Wu, Po-Ting; Hsu, Jian Han; Jou, I. Ming; Su, Fong-chin; Sun, Yung-Nien.

Seventh International Conference on Graphic and Image Processing, ICGIP 2015. 編輯 / Xudong Jiang; Xudong Jiang; Yulin Wang; Xudong Jiang; Yulin Wang; Xudong Jiang; Yulin Wang; Yulin Wang. SPIE, 2015. 98170L (Proceedings of SPIE - The International Society for Optical Engineering; 卷 9817).

研究成果: Conference contribution

TY - GEN

T1 - Adaptive segmentation of nuclei in H&E stained tendon microscopy

AU - Chuang, Bo I.

AU - Wu, Po-Ting

AU - Hsu, Jian Han

AU - Jou, I. Ming

AU - Su, Fong-chin

AU - Sun, Yung-Nien

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Tendiopathy is a popular clinical issue in recent years. In most cases like trigger finger or tennis elbow, the pathology change can be observed under H&E stained tendon microscopy. However, the qualitative analysis is too subjective and thus the results heavily depend on the observers. We develop an automatic segmentation procedure which segments and counts the nuclei in H&E stained tendon microscopy fast and precisely. This procedure first determines the complexity of images and then segments the nuclei from the image. For the complex images, the proposed method adopts sampling-based thresholding to segment the nuclei. While for the simple images, the Laplacian-based thresholding is employed to re-segment the nuclei more accurately. In the experiments, the proposed method is compared with the experts outlined results. The nuclei number of proposed method is closed to the experts counted, and the processing time of proposed method is much faster than the experts'.

AB - Tendiopathy is a popular clinical issue in recent years. In most cases like trigger finger or tennis elbow, the pathology change can be observed under H&E stained tendon microscopy. However, the qualitative analysis is too subjective and thus the results heavily depend on the observers. We develop an automatic segmentation procedure which segments and counts the nuclei in H&E stained tendon microscopy fast and precisely. This procedure first determines the complexity of images and then segments the nuclei from the image. For the complex images, the proposed method adopts sampling-based thresholding to segment the nuclei. While for the simple images, the Laplacian-based thresholding is employed to re-segment the nuclei more accurately. In the experiments, the proposed method is compared with the experts outlined results. The nuclei number of proposed method is closed to the experts counted, and the processing time of proposed method is much faster than the experts'.

UR - http://www.scopus.com/inward/record.url?scp=85028353568&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028353568&partnerID=8YFLogxK

U2 - 10.1117/12.2228807

DO - 10.1117/12.2228807

M3 - Conference contribution

AN - SCOPUS:85028353568

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Seventh International Conference on Graphic and Image Processing, ICGIP 2015

A2 - Jiang, Xudong

A2 - Jiang, Xudong

A2 - Wang, Yulin

A2 - Jiang, Xudong

A2 - Wang, Yulin

A2 - Jiang, Xudong

A2 - Wang, Yulin

A2 - Wang, Yulin

PB - SPIE

ER -

Chuang BI, Wu P-T, Hsu JH, Jou IM, Su F, Sun Y-N. Adaptive segmentation of nuclei in H&E stained tendon microscopy. 於 Jiang X, Jiang X, Wang Y, Jiang X, Wang Y, Jiang X, Wang Y, Wang Y, 編輯, Seventh International Conference on Graphic and Image Processing, ICGIP 2015. SPIE. 2015. 98170L. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2228807