Robust Phase-based Texture Descriptor for Classification of Breast Ultrasound Images

Overview

Journal Biomed Eng Online

Publisher Biomed Central

Specialty Biomedical Engineering

Date 2015 Apr 19

PMID 25889570

Citations 14

Authors

Lingyun Cai

Xin Wang

Yuanyuan Wang

Yi Guo

Jinhua Yu

Yi Wang

Affiliations

Soon will be listed here.

Abstract

Background: Classification of breast ultrasound (BUS) images is an important step in the computer-aided diagnosis (CAD) system for breast cancer. In this paper, a novel phase-based texture descriptor is proposed for efficient and robust classifiers to discriminate benign and malignant tumors in BUS images.

Method: The proposed descriptor, namely the phased congruency-based binary pattern (PCBP) is an oriented local texture descriptor that combines the phase congruency (PC) approach with the local binary pattern (LBP). The support vector machine (SVM) is further applied for the tumor classification. To verify the efficiency of the proposed PCBP texture descriptor, we compare the PCBP with other three state-of-art texture descriptors, and experiments are carried out on a BUS image database including 138 cases. The receiver operating characteristic (ROC) analysis is firstly performed and seven criteria are utilized to evaluate the classification performance using different texture descriptors. Then, in order to verify the robustness of the PCBP against illumination variations, we train the SVM classifier on texture features obtained from the original BUS images, and use this classifier to deal with the texture features extracted from BUS images with different illumination conditions (i.e., contrast-improved, gamma-corrected and histogram-equalized). The area under ROC curve (AUC) index is used as the figure of merit to evaluate the classification performances.

Results And Conclusions: The proposed PCBP texture descriptor achieves the highest values (i.e. 0.894) and the least variations in respect of the AUC index, regardless of the gray-scale variations. It's revealed in the experimental results that classifications of BUS images with the proposed PCBP texture descriptor are efficient and robust, which may be potentially useful for breast ultrasound CADs.

Citing Articles

A scoping review of robustness concepts for machine learning in healthcare.

Balendran A, Beji C, Bouvier F, Khalifa O, Evgeniou T, Ravaud P NPJ Digit Med. 2025; 8(1):38.

PMID: 39824951 PMC: 11742061. DOI: 10.1038/s41746-024-01420-1.

Firefly-SVM predictive model for breast cancer subgroup classification with clinicopathological parameters.

Sarkar S, Mali K Digit Health. 2023; 9:20552076231207203.

PMID: 37860702 PMC: 10583530. DOI: 10.1177/20552076231207203.

A Review of Machine Learning Techniques for the Classification and Detection of Breast Cancer from Medical Images.

Jalloul R, Chethan H, Alkhatib R Diagnostics (Basel). 2023; 13(14).

PMID: 37510204 PMC: 10378151. DOI: 10.3390/diagnostics13142460.

Improving breast cancer diagnosis by incorporating raw ultrasound parameters into machine learning.

Baek J, OConnell A, Parker K Mach Learn Sci Technol. 2023; 3(4):045013.

PMID: 36698865 PMC: 9855672. DOI: 10.1088/2632-2153/ac9bcc.

A Machine Learning Applied Diagnosis Method for Subcutaneous Cyst by Ultrasonography.

Feng H, Tang Q, Yu Z, Tang H, Yin M, Wei A Oxid Med Cell Longev. 2022; 2022:1526540.

PMID: 36299601 PMC: 9592196. DOI: 10.1155/2022/1526540.

References

Chen D, Chang R, Huang Y . Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. Radiology. 1999; 213(2):407-12. DOI: 10.1148/radiology.213.2.r99nv13407. View

Sahiner B, Chan H, Hadjiiski L . Classifier performance prediction for computer-aided diagnosis using a limited dataset. Med Phys. 2008; 35(4):1559-70. PMC: 2811557. DOI: 10.1118/1.2868757. View

Chang R, Wu W, Moon W, Chen D . Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Res Treat. 2005; 89(2):179-85. DOI: 10.1007/s10549-004-2043-z. View

Crystal P, Strano S, Shcharynski S, Koretz M . Using sonography to screen women with mammographically dense breasts. AJR Am J Roentgenol. 2003; 181(1):177-82. DOI: 10.2214/ajr.181.1.1810177. View

Alvarenga A, Pereira W, Infantosi A, Azevedo C . Complexity curve and grey level co-occurrence matrix in the texture evaluation of breast tumor on ultrasound images. Med Phys. 2007; 34(2):379-87. DOI: 10.1118/1.2401039. View

Chen C, Chou Y, Han K, Hung G, Tiu C, Chiou H . Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks. Radiology. 2003; 226(2):504-14. DOI: 10.1148/radiol.2262011843. View

Huber S, Danes J, Zuna I, Teubner J, Medl M, Delorme S . Relevance of sonographic B-mode criteria and computer-aided ultrasonic tissue characterization in differential/diagnosis of solid breast masses. Ultrasound Med Biol. 2000; 26(8):1243-52. DOI: 10.1016/s0301-5629(00)00274-x. View

Wu W, Lin S, Moon W . Combining support vector machine with genetic algorithm to classify ultrasound breast tumor images. Comput Med Imaging Graph. 2012; 36(8):627-33. DOI: 10.1016/j.compmedimag.2012.07.004. View

Garra B, Krasner B, Horii S, Ascher S, Mun S, Zeman R . Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis. Ultrason Imaging. 1993; 15(4):267-85. DOI: 10.1177/016173469301500401. View

10.

Stavros A, Thickman D, Rapp C, Dennis M, Parker S, Sisney G . Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. Radiology. 1995; 196(1):123-34. DOI: 10.1148/radiology.196.1.7784555. View

11.

Baldi P, Brunak S, Chauvin Y, Andersen C, Nielsen H . Assessing the accuracy of prediction algorithms for classification: an overview. Bioinformatics. 2000; 16(5):412-24. DOI: 10.1093/bioinformatics/16.5.412. View

12.

Hanley J, McNeil B . The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology. 1982; 143(1):29-36. DOI: 10.1148/radiology.143.1.7063747. View

13.

Gomez W, Pereira W, Infantosi A . Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound. IEEE Trans Med Imaging. 2012; 31(10):1889-99. DOI: 10.1109/TMI.2012.2206398. View

14.

Lefebvre F, Meunier M, Thibault F, Laugier P, Berger G . Computerized ultrasound B-scan characterization of breast nodules. Ultrasound Med Biol. 2001; 26(9):1421-8. DOI: 10.1016/s0301-5629(00)00302-1. View

15.

Chen D, Chang R, Kuo W, Chen M, Huang Y . Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. Ultrasound Med Biol. 2002; 28(10):1301-10. DOI: 10.1016/s0301-5629(02)00620-8. View

16.

Matthews B . Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta. 1975; 405(2):442-51. DOI: 10.1016/0005-2795(75)90109-9. View

17.

Yang M, Moon W, Wang Y, Bae M, Huang C, Chen J . Robust Texture Analysis Using Multi-Resolution Gray-Scale Invariant Features for Breast Sonographic Tumor Diagnosis. IEEE Trans Med Imaging. 2013; 32(12):2262-73. DOI: 10.1109/TMI.2013.2279938. View

18.

Liao Y, Tsui P, Li C, Chang K, Kuo W, Chang C . Classification of scattering media within benign and malignant breast tumors based on ultrasound texture-feature-based and Nakagami-parameter images. Med Phys. 2011; 38(4):2198-207. DOI: 10.1118/1.3566064. View

19.

Chen D, Chang R, Huang Y, Chou Y, Tiu C, Tsai P . Texture analysis of breast tumors on sonograms. Semin Ultrasound CT MR. 2000; 21(4):308-16. DOI: 10.1016/s0887-2171(00)90025-8. View

20.

Kovesi P . Phase congruency: a low-level image invariant. Psychol Res. 2001; 64(2):136-48. DOI: 10.1007/s004260000024. View