Development of a fully automatic scheme for detection of masses in whole breast ultrasound images

Abstract

Ultrasonography has been used for breast cancer screening in Japan. Screening using a conventional hand-held probe is operator dependent and thus it is possible that some areas of the breast may not be scanned. To overcome such problems, a mechanical whole breast ultrasound (US) scanner has been proposed and developed for screening purposes. However, another issue is that radiologists might tire while interpreting all images in a large-volume screening; this increases the likelihood that masses may remain undetected. Therefore, the aim of this study is to develop a fully automatic scheme for the detection of masses in whole breast US images in order to assist the interpretations of radiologists and potentially improve the screening accuracy. The authors database comprised 109 whole breast US imagoes, which include 36 masses (16 malignant masses, 5 fibroadenomas, and 15 cysts). A whole breast US image with 84 slice images (interval between two slice images: 2 mm) was obtained by the ASU-1004 US scanner (ALOKA Co., Ltd., Japan). The feature based on the edge directions in each slice and a method for subtracting between the slice images were used for the detection of masses in the authors proposed scheme. The Canny edge detector was applied to detect edges in US images; these edges were classified as near-vertical edges or near-horizontal edges using a morphological method. The positions of mass candidates were located using the near-vertical edges as a cue. Then, the located positions were segmented by the watershed algorithm and mass candidate regions were detected using the segmented regions and the low-density regions extracted by the slice subtraction method. For the removal of false positives (FPs), rule-based schemes and a quadratic discriminant analysis were applied for the distribution between masses and FPs. As a result, the sensitivity of the authors scheme for the detection of masses was 80.6% (29/36) with 3.8 FPs per whole breast image. The authors scheme for a computer-aided detection may be useful in improving the screening performance and efficiency.

Computer-aided detection system for masses in automated whole breast ultrasonography: development and evaluation of the effectiveness

“…However, hand-held US (HHUS) is operator dependent and time-consuming for whole breast evaluation. To overcome these problems, several automated breast US (ABUS) machines have been developed [4,5]. …”

Automated analysis of breast parenchymal patterns in whole breast ultrasound images: preliminary experience

“…A patient positions her one breast at a time on a membrane covering the water tank, and the instrument scans her entire breast in three overlapping runs. A whole breast slice image (axial plane) was generated from three original images by using an integration algorithm proposed in our previous work for computerized detection of masses in whole breast US images [25]. The whole breast slice image consisted of 167 slice images with 1-mm slice intervals, and the width and depth of each slice image were 611 and 469 pixels, respectively.…”

“…The point with the maximum value of y axis in a breast volume was determined as the nipple position N = (n x, , n y , n z ), where x y and z axes are defined in axial plane and in the slice direction, respectively. The breast volume was segmented from the image f 3 with our proposed method [25], as shown in Fig. 5.…”

Automated breast ultrasound system (ABUS): reproducibility of mass localization, size measurement, and characterization on serial examinations

“…We expect high reproducibility for lesion characterization with ABUS, however, these techniques are not standardized. Thus, there is a risk for differences in data acquisition (19,20).…”