Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network

Nan-Chyuan Tsai, Hong Wei Chen, Sheng Liang Hsu

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

Abstract

A high-sensitivity computer-aided diagnosis algorithm which can detect and quantify micro-calcifications for early-stage breast cancer is proposed in this research. The algorithm can be divided into two phases: image reconstruction and recognition on micro-calcification regions. For Phase I, the suspicious micro-calcification regions are separated from the normal tissues by wavelet layers and Renyi's information theory. The Morphology-Dilation and Majority Voting Rule are employed to reconstruct the scattered regions of suspicious micro-calcification. For Phase II, total 49 descriptors which mainly includes shape inertia, compactness, eccentricity and grey-level co-occurrence matrix are introduced to define the characteristics of the suspicious micro-calcification clusters. In order to reduce the computation load, principal component analysis is used to transform these descriptors to a compact but efficient expression by linear combination method. The performance of proposed diagnosis algorithm is verified by intensive experiments upon realistic clinic patients. The efficacy of back-propagation neural network classifier exhibits its superiority in terms of high true positive rate(TP rate) and low false positive(FP rate) rate, in comparison to Bayes classifier.

Original languageEnglish
Title of host publication2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009
Pages209-214
Number of pages6
DOIs
Publication statusPublished - 2009 Nov 4
Event2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009 - Singapore, Singapore
Duration: 2009 Jul 142009 Jul 17

Publication series

NameIEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM

Other

Other2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009
CountrySingapore
CitySingapore
Period09-07-1409-07-17

Fingerprint

Wavelet transforms
Neural networks
Classifiers
Chemical analysis
Computer aided diagnosis
Image recognition
Information theory
Image reconstruction
Backpropagation
Principal component analysis
Tissue
Experiments

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Tsai, N-C., Chen, H. W., & Hsu, S. L. (2009). Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network. In 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009 (pp. 209-214). [5230014] (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM). https://doi.org/10.1109/AIM.2009.5230014
Tsai, Nan-Chyuan ; Chen, Hong Wei ; Hsu, Sheng Liang. / Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network. 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009. 2009. pp. 209-214 (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM).
@inproceedings{320f34e337414ad5821ba28cbe30d67c,
title = "Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network",
abstract = "A high-sensitivity computer-aided diagnosis algorithm which can detect and quantify micro-calcifications for early-stage breast cancer is proposed in this research. The algorithm can be divided into two phases: image reconstruction and recognition on micro-calcification regions. For Phase I, the suspicious micro-calcification regions are separated from the normal tissues by wavelet layers and Renyi's information theory. The Morphology-Dilation and Majority Voting Rule are employed to reconstruct the scattered regions of suspicious micro-calcification. For Phase II, total 49 descriptors which mainly includes shape inertia, compactness, eccentricity and grey-level co-occurrence matrix are introduced to define the characteristics of the suspicious micro-calcification clusters. In order to reduce the computation load, principal component analysis is used to transform these descriptors to a compact but efficient expression by linear combination method. The performance of proposed diagnosis algorithm is verified by intensive experiments upon realistic clinic patients. The efficacy of back-propagation neural network classifier exhibits its superiority in terms of high true positive rate(TP rate) and low false positive(FP rate) rate, in comparison to Bayes classifier.",
author = "Nan-Chyuan Tsai and Chen, {Hong Wei} and Hsu, {Sheng Liang}",
year = "2009",
month = "11",
day = "4",
doi = "10.1109/AIM.2009.5230014",
language = "English",
isbn = "9781424428533",
series = "IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM",
pages = "209--214",
booktitle = "2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009",

}

Tsai, N-C, Chen, HW & Hsu, SL 2009, Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network. in 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009., 5230014, IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM, pp. 209-214, 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009, Singapore, Singapore, 09-07-14. https://doi.org/10.1109/AIM.2009.5230014

Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network. / Tsai, Nan-Chyuan; Chen, Hong Wei; Hsu, Sheng Liang.

2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009. 2009. p. 209-214 5230014 (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM).

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

TY - GEN

T1 - Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network

AU - Tsai, Nan-Chyuan

AU - Chen, Hong Wei

AU - Hsu, Sheng Liang

PY - 2009/11/4

Y1 - 2009/11/4

N2 - A high-sensitivity computer-aided diagnosis algorithm which can detect and quantify micro-calcifications for early-stage breast cancer is proposed in this research. The algorithm can be divided into two phases: image reconstruction and recognition on micro-calcification regions. For Phase I, the suspicious micro-calcification regions are separated from the normal tissues by wavelet layers and Renyi's information theory. The Morphology-Dilation and Majority Voting Rule are employed to reconstruct the scattered regions of suspicious micro-calcification. For Phase II, total 49 descriptors which mainly includes shape inertia, compactness, eccentricity and grey-level co-occurrence matrix are introduced to define the characteristics of the suspicious micro-calcification clusters. In order to reduce the computation load, principal component analysis is used to transform these descriptors to a compact but efficient expression by linear combination method. The performance of proposed diagnosis algorithm is verified by intensive experiments upon realistic clinic patients. The efficacy of back-propagation neural network classifier exhibits its superiority in terms of high true positive rate(TP rate) and low false positive(FP rate) rate, in comparison to Bayes classifier.

AB - A high-sensitivity computer-aided diagnosis algorithm which can detect and quantify micro-calcifications for early-stage breast cancer is proposed in this research. The algorithm can be divided into two phases: image reconstruction and recognition on micro-calcification regions. For Phase I, the suspicious micro-calcification regions are separated from the normal tissues by wavelet layers and Renyi's information theory. The Morphology-Dilation and Majority Voting Rule are employed to reconstruct the scattered regions of suspicious micro-calcification. For Phase II, total 49 descriptors which mainly includes shape inertia, compactness, eccentricity and grey-level co-occurrence matrix are introduced to define the characteristics of the suspicious micro-calcification clusters. In order to reduce the computation load, principal component analysis is used to transform these descriptors to a compact but efficient expression by linear combination method. The performance of proposed diagnosis algorithm is verified by intensive experiments upon realistic clinic patients. The efficacy of back-propagation neural network classifier exhibits its superiority in terms of high true positive rate(TP rate) and low false positive(FP rate) rate, in comparison to Bayes classifier.

UR - http://www.scopus.com/inward/record.url?scp=70350459409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350459409&partnerID=8YFLogxK

U2 - 10.1109/AIM.2009.5230014

DO - 10.1109/AIM.2009.5230014

M3 - Conference contribution

SN - 9781424428533

T3 - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM

SP - 209

EP - 214

BT - 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009

ER -

Tsai N-C, Chen HW, Hsu SL. Quantitative analysis of micro-calcifications for breast cancer via wavelet transform and neural network. In 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2009. 2009. p. 209-214. 5230014. (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM). https://doi.org/10.1109/AIM.2009.5230014