A new fourier-based approach to measure irregularity of breast masses in mammograms

Gensheng Zhang, Sung Shin, Wei Wang, Carrie B Hruska, Hyung D. Choi

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

1 Citation (Scopus)

Abstract

Morphologic appearance is one of intuitive diagnosis factors of mass lesions in breast imaging, and irregular shape is one of the most frequent appearances for malignant masses. Thus, an effective measure of morphological irregularity will provide a helpful reference to determine malignancy of breast masses. In this paper, a new measure based on Fourier Transform, named Fourier Irregularity Index (FII), was developed to provide a reliable malignant/benign classification factor. The experiment was conducted with 418 breast masses, including 190 malignant cases and 218 benign cases. Performance was assessed and compared among various methods using Receiver Operating Characteristics (ROC) analysis. The proposed measure in this study achieved malignant/benign classification accuracy of 96% with an area (Az) of 0.99 under the receiver operating characteristics (ROC) curve, which outperformed typical traditional approaches, such as Compactness (accuracy of 90%, Az = 0.96), Fractal Dimension (accuracy of 90%, Az = 0.95), Fourier Factor (accuracy of 90%, Az = 0.97), and Fractional Concavity (accuracy of 75%, A z = 0.65).

Original languageEnglish (US)
Title of host publicationProceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012
Pages153-157
Number of pages5
DOIs
StatePublished - 2012
Event2012 ACM Research in Applied Computation Symposium, RACS 2012 - San Antonio, TX, United States
Duration: Oct 23 2012Oct 26 2012

Other

Other2012 ACM Research in Applied Computation Symposium, RACS 2012
CountryUnited States
CitySan Antonio, TX
Period10/23/1210/26/12

Fingerprint

Fractal dimension
Fourier transforms
Imaging techniques
Experiments

Keywords

  • Fourier irregularity index
  • Irregularity measure
  • Shape factor

ASJC Scopus subject areas

  • Computational Theory and Mathematics

Cite this

Zhang, G., Shin, S., Wang, W., Hruska, C. B., & Choi, H. D. (2012). A new fourier-based approach to measure irregularity of breast masses in mammograms. In Proceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012 (pp. 153-157) https://doi.org/10.1145/2401603.2401638

A new fourier-based approach to measure irregularity of breast masses in mammograms. / Zhang, Gensheng; Shin, Sung; Wang, Wei; Hruska, Carrie B; Choi, Hyung D.

Proceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012. 2012. p. 153-157.

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

Zhang, G, Shin, S, Wang, W, Hruska, CB & Choi, HD 2012, A new fourier-based approach to measure irregularity of breast masses in mammograms. in Proceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012. pp. 153-157, 2012 ACM Research in Applied Computation Symposium, RACS 2012, San Antonio, TX, United States, 10/23/12. https://doi.org/10.1145/2401603.2401638
Zhang G, Shin S, Wang W, Hruska CB, Choi HD. A new fourier-based approach to measure irregularity of breast masses in mammograms. In Proceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012. 2012. p. 153-157 https://doi.org/10.1145/2401603.2401638
Zhang, Gensheng ; Shin, Sung ; Wang, Wei ; Hruska, Carrie B ; Choi, Hyung D. / A new fourier-based approach to measure irregularity of breast masses in mammograms. Proceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012. 2012. pp. 153-157
@inproceedings{14b394bbf24b4565bed7851c047e5e33,
title = "A new fourier-based approach to measure irregularity of breast masses in mammograms",
abstract = "Morphologic appearance is one of intuitive diagnosis factors of mass lesions in breast imaging, and irregular shape is one of the most frequent appearances for malignant masses. Thus, an effective measure of morphological irregularity will provide a helpful reference to determine malignancy of breast masses. In this paper, a new measure based on Fourier Transform, named Fourier Irregularity Index (FII), was developed to provide a reliable malignant/benign classification factor. The experiment was conducted with 418 breast masses, including 190 malignant cases and 218 benign cases. Performance was assessed and compared among various methods using Receiver Operating Characteristics (ROC) analysis. The proposed measure in this study achieved malignant/benign classification accuracy of 96{\%} with an area (Az) of 0.99 under the receiver operating characteristics (ROC) curve, which outperformed typical traditional approaches, such as Compactness (accuracy of 90{\%}, Az = 0.96), Fractal Dimension (accuracy of 90{\%}, Az = 0.95), Fourier Factor (accuracy of 90{\%}, Az = 0.97), and Fractional Concavity (accuracy of 75{\%}, A z = 0.65).",
keywords = "Fourier irregularity index, Irregularity measure, Shape factor",
author = "Gensheng Zhang and Sung Shin and Wei Wang and Hruska, {Carrie B} and Choi, {Hyung D.}",
year = "2012",
doi = "10.1145/2401603.2401638",
language = "English (US)",
isbn = "9781450314923",
pages = "153--157",
booktitle = "Proceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012",

}

TY - GEN

T1 - A new fourier-based approach to measure irregularity of breast masses in mammograms

AU - Zhang, Gensheng

AU - Shin, Sung

AU - Wang, Wei

AU - Hruska, Carrie B

AU - Choi, Hyung D.

PY - 2012

Y1 - 2012

N2 - Morphologic appearance is one of intuitive diagnosis factors of mass lesions in breast imaging, and irregular shape is one of the most frequent appearances for malignant masses. Thus, an effective measure of morphological irregularity will provide a helpful reference to determine malignancy of breast masses. In this paper, a new measure based on Fourier Transform, named Fourier Irregularity Index (FII), was developed to provide a reliable malignant/benign classification factor. The experiment was conducted with 418 breast masses, including 190 malignant cases and 218 benign cases. Performance was assessed and compared among various methods using Receiver Operating Characteristics (ROC) analysis. The proposed measure in this study achieved malignant/benign classification accuracy of 96% with an area (Az) of 0.99 under the receiver operating characteristics (ROC) curve, which outperformed typical traditional approaches, such as Compactness (accuracy of 90%, Az = 0.96), Fractal Dimension (accuracy of 90%, Az = 0.95), Fourier Factor (accuracy of 90%, Az = 0.97), and Fractional Concavity (accuracy of 75%, A z = 0.65).

AB - Morphologic appearance is one of intuitive diagnosis factors of mass lesions in breast imaging, and irregular shape is one of the most frequent appearances for malignant masses. Thus, an effective measure of morphological irregularity will provide a helpful reference to determine malignancy of breast masses. In this paper, a new measure based on Fourier Transform, named Fourier Irregularity Index (FII), was developed to provide a reliable malignant/benign classification factor. The experiment was conducted with 418 breast masses, including 190 malignant cases and 218 benign cases. Performance was assessed and compared among various methods using Receiver Operating Characteristics (ROC) analysis. The proposed measure in this study achieved malignant/benign classification accuracy of 96% with an area (Az) of 0.99 under the receiver operating characteristics (ROC) curve, which outperformed typical traditional approaches, such as Compactness (accuracy of 90%, Az = 0.96), Fractal Dimension (accuracy of 90%, Az = 0.95), Fourier Factor (accuracy of 90%, Az = 0.97), and Fractional Concavity (accuracy of 75%, A z = 0.65).

KW - Fourier irregularity index

KW - Irregularity measure

KW - Shape factor

UR - http://www.scopus.com/inward/record.url?scp=84871637087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871637087&partnerID=8YFLogxK

U2 - 10.1145/2401603.2401638

DO - 10.1145/2401603.2401638

M3 - Conference contribution

AN - SCOPUS:84871637087

SN - 9781450314923

SP - 153

EP - 157

BT - Proceeding of the 2012 ACM Research in Applied Computation Symposium, RACS 2012

ER -