Classification of Benign and Malignant Breast Tumors in Ultrasound Images with Posterior Acoustic Shadowing Using Half-Contour Features.

Zhuhuang Zhou,King-Jen Chang,Shuicai Wu,Chung-Chih Lin,Po-Hsiang Tsui,Yung-Sheng Chen,Wen-Hung Kuo,Wei-Ren Chen

doi:10.1007/s40846-015-0031-x

Abstract

Posterior acoustic shadowing (PAS) can bias breast tumor segmentation and classification in ultrasound images. In this paper, half-contour features are proposed to classify benign and malignant breast tumors with PAS, considering the fact that the upper half of the tumor contour is less affected by PAS. Adaptive thresholding and disk expansion are employed to detect tumor contours. Based on the detected full contour, the upper half contour is extracted. For breast tumor classification, six quantitative feature parameters are analyzed for both full contours and half contours, including standard deviation of degree (SDD), which is proposed to describe tumor irregularity. Fifty clinical cases (40 with PAS and 10 without PAS) were used. Tumor circularity (TC) and SDD were both effective full- and half-contour parameters in classifying images without PAS. Half-contour TC [74 % accuracy, 72 % sensitivity, 76 % specificity, 0.78 area under the receiver operating characteristic curve (AUC), p > 0.05] significantly improved the classification of breast tumors with PAS compared to that with full-contour TC (54 % accuracy, 56 % sensitivity, 52 % specificity, 0.52 AUC, p > 0.05). Half-contour SDD (72 % accuracy, 76 % sensitivity, 68 % specificity, 0.81 AUC, p < 0.05) improved the classification of breast tumors with PAS compared to that with full-contour SDD (62 % accuracy, 80 % sensitivity, 44 % specificity, 0.61 AUC, p > 0.05). The proposed half-contour TC and SDD may be useful in classifying benign and malignant breast tumors in ultrasound images affected by PAS.

Highlights

Breast cancer is a health problem for women worldwide [1]
Since the upper half of the tumor contour is less affected by the Posterior acoustic shadowing (PAS) effect than is the lower half, the present study proposes using features based on the upper half contour to classify benign and malignant breast tumors in ultrasound images with PAS
Among the six feature parameters, Tumor circularity (TC) and standard deviation of degree (SDD) were most effective for classifying tumors without PAS, both for full contours and half contours

Summary

Introduction

Ultrasound has become a useful adjunct modality for breast tumor diagnosis because it is cost-effective, noninvasive, and performed in real time [2]. Certain inherent characteristics of ultrasound images, including low contrast, speckle noise, and tissue-related textures, may cause difficulties for radiologists [3]. Interor intraobserver differences in the understanding and Classification of Benign and Malignant Breast Tumors. Diagnosis of ultrasound images might occur [4]. Developing a computer-aided detection/diagnosis (CAD) system for analyzing ultrasound images is crucial [3, 5,6,7]. The diagnosis result of a CAD system can provide a second opinion for radiologists in the detection and diagnosis of breast lesions [4, 8, 9]

Methods

Results

Conclusion