Fourier-based shape feature extraction technique for computer-aided B-Mode ultrasound diagnosis of breast tumor

• Published in: 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society Vol. 2012; pp. 6551 - 6554
• Main Authors: Lee, Jong-Ha, Seong, Yeong Kyeong, Chang, Chu-Ho, Park, Jinman, Park, Moonho, Woo, Kyoung-Gu, Ko, Eun Young
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01-01-2012
• Subjects: Accuracy; Adolescent; Adult; Aged; Aged, 80 and over; Area Under Curve; Breast - pathology; Breast Neoplasms - classification; Breast Neoplasms - diagnostic imaging; Breast tumors; Cancer; Child; Diagnosis, Computer-Assisted - methods; Feature extraction; Female; Fourier Analysis; Humans; Mammography; Middle Aged; Models, Statistical; Predictive Value of Tests; Reproducibility of Results; Shape; Signal Processing, Computer-Assisted; Support Vector Machine; Support vector machines; Ultrasonic imaging; Ultrasonography, Mammary - instrumentation; Ultrasonography, Mammary - methods; Young Adult
• ISBN: 1424441196; 9781424441198
• ISSN: 1094-687X; 1557-170X; 1558-4615
• DOI: 10.1109/EMBC.2012.6347495

Early detection of breast tumor is critical in determining the best possible treatment approach. Due to its superiority compared with mammography in its possibility to detect lesions in dense breast tissue, ultrasound imaging has become an important modality in breast tumor detection and classification. This paper discusses the novel Fourier-based shape feature extraction techniques that provide enhanced classification accuracy for breast tumor in the computer-aided B-mode ultrasound diagnosis system. To demonstrate the effectiveness of the proposed method, experiments were performed using 4,107 ultrasound images with 2,508 malignancy cases. Experimental results show that the breast tumor classification accuracy of the proposed technique was 15.8%, 5.43%, 17.32%, and 13.86% higher than the previous shape features such as number of protuberances, number of depressions, lobulation index, and dissimilarity, respectively.