Automated Breast Ultrasonography (ABUS) in the Screening and Diagnostic Setting: Indications and Practical Use

Diagnostic performance of automated breast ultrasound and handheld ultrasound in women with dense breasts

PURPOSE

As an adjunct to mammography, ultrasound can improve the detection of breast cancer in women with dense breasts. We aimed to evaluate the diagnostic performance of automated breast ultrasound system (ABUS) and handheld ultrasound (HHUS) in Chinese women with dense breasts, both in combination with mammography and separately.

METHODS

This is a cross-sectional multicenter clinical research study. Nine hundred and thirty-seven women with dense breasts underwent ABUS, HHUS, and mammography at one of five tertiary-care hospitals. The diagnostic performance of ABUS and HHUS was evaluated in combination with mammography, or separately in women with mammography-negative dense breasts. The agreement between ABUS and HHUS in breast cancer detection was also assessed.

RESULTS

The sensitivity of the combination of ABUS or HHUS with mammography was 99.1% (219/221), and the specificities were 86.9% (622/716) and 84.9% (608/716), respectively. The area under the curve was 0.93 for ABUS combined with mammography and 0.92 for that of HHUS combined with mammography. Statistically significant agreement between ABUS and HHUS in breast cancer detection was observed (percent agreement = 0.94, κ = 0.85). The incremental cancer detection rate in mammography-negative dense breasts was 42.8 per 1000 ultrasound examinations.

CONCLUSIONS

Both ABUS and HHUS as adjuncts to mammography can significantly improve the breast cancer detection rate in women with dense breasts, and there is a strong correlation between them. Given the high prevalence of dense breasts and the multiple advantages of ABUS over HHUS, such as less operator dependence and reproducibility, ABUS showed great potential for use in breast cancer early detection, especially in resource-limited areas.

Breast Cancer Classification in Automated Breast Ultrasound Using Multiview Convolutional Neural Network with Transfer Learning

To assist radiologists in breast cancer classification in automated breast ultrasound (ABUS) imaging, we propose a computer-aided diagnosis based on a convolutional neural network (CNN) that classifies breast lesions as benign and malignant. The proposed CNN adopts a modified Inception-v3 architecture to provide efficient feature extraction in ABUS imaging. Because the ABUS images can be visualized in transverse and coronal views, the proposed CNN provides an efficient way to extract multiview features from both views. The proposed CNN was trained and evaluated on 316 breast lesions (135 malignant and 181 benign). An observer performance test was conducted to compare five human reviewers' diagnostic performance before and after referring to the predicting outcomes of the proposed CNN. Our method achieved an area under the curve (AUC) value of 0.9468 with five-folder cross-validation, for which the sensitivity and specificity were 0.886 and 0.876, respectively. Compared with conventional machine learning-based feature extraction schemes, particularly principal component analysis (PCA) and histogram of oriented gradients (HOG), our method achieved a significant improvement in classification performance. The proposed CNN achieved a >10% increased AUC value compared with PCA and HOG. During the observer performance test, the diagnostic results of all human reviewers had increased AUC values and sensitivities after referring to the classification results of the proposed CNN, and four of the five human reviewers' AUCs were significantly improved. The proposed CNN employing a multiview strategy showed promise for the diagnosis of breast cancer, and could be used as a second reviewer for increasing diagnostic reliability.

A Prospective Study of Automated Breast Ultrasound Screening of Women with Dense Breasts in a Digital Breast Tomosynthesis-based Practice

OBJECTIVE

To assess prospectively the interpretative performance of automated breast ultrasound (ABUS) as a supplemental screening after digital breast tomosynthesis (DBT) or as a standalone screening of women with dense breast tissue.

METHODS

Under an IRB-approved protocol (written consent required), women with dense breasts prospectively underwent concurrent baseline DBT and ABUS screening. Examinations were independently evaluated, in opposite order, by two of seven Mammography Quality Standards Act-qualified radiologists, with the primary radiologist arbitrating disagreements and making clinical management recommendations. We report results for 1111 screening examinations (598 first year and 513 second year) for which all diagnostic workups are complete. Imaging was also retrospectively reviewed for all cancers. Statistical assessments used a 0.05 significance level and accounted for correlation between participants' examinations.

RESULTS

Of 1111 women screened, primary radiologists initially "recalled" based on DBT alone (6.6%, 73/1111, CI: 5.2%-8.2%), of which 20 were biopsied, yielding 6/8 total cancers. Automated breast ultrasound increased recalls overall to 14.4% (160/1111, CI: 12.4%-16.6%), with 27 total biopsies, yielding 1 additional cancer. Double reading of DBT alone increased the recall rate to 10.7% (119/1111), with 21 biopsies, with no improvement in cancer detection. Double reading ABUS increased the recall rate to 15.2% (169/1111, CI: 13.2%-17.5%) of women, of whom 22 were biopsied, yielding the detection of 7 cancers, including one seen only on double reading ABUS. Inter-radiologist agreement was similar for recall recommendations from DBT (κ = 0.24, CI: 0.14-0.34) and ABUS (κ = 0.23, CI: 0.15-0.32). Integrated assessments from both readers resulted in a recall rate of 15.1% (168/1111, CI: 13.1%-17.4%).

CONCLUSION

Supplemental or standalone ABUS screening detected cancers not seen on DBT, but substantially increased noncancer recall rates.

Production and clinical evaluation of breast lesion skin markers for automated three-dimensional ultrasonography of the breast: a pilot study

Objectives

Automated ultrasound of the breast has the advantage to have the whole breast scanned by technicians. Consequently, feedback to the radiologist about concurrent focal abnormalities (e.g., palpable lesions) is lost. To enable marking of patient- or physician-reported focal abnormalities, we aimed to develop skin markers that can be used without disturbing the interpretability of the image.

Methods

Disk-shaped markers were casted out of silicone. In this IRB-approved prospective study, 16 patients were included with a mean age of 57 (39–85). In all patients, the same volume was imaged twice using an automated breast ultrasound system, once with and once without a marker in place. Nine radiologists from two medical centers filled scoring forms regarding image quality, image interpretation, and confidence in providing a diagnosis based on the images.

Results

Marker adhesion was sufficient for automated scanning. Observer scores showed a significant shift in scores from excellent to good regarding diagnostic yield/image quality (χ², 15.99, p < 0.01), and image noise (χ², 21.20, p < 0.01) due to marker presence. In 93% of cases, the median score of observers “agree” with the statement that marker-induced noise did not influence image interpretability. Marker presence did not interfere with confidence in diagnosis (χ², 6.00, p = 0.20).

Conclusion

Inexpensive, easy producible skin markers can be used for accurate lesion marking in automated ultrasound examinations of the breast while image interpretability is preserved. Any marker-induced noise and decreased image quality did not affect confidence in providing a diagnosis.

Key Points

• The use of a skin marker enables the reporting radiologist to identify a location which a patient is concerned about.

• The developed skin marker can be used for accurate breast lesion marking in ultrasound examinations.

Breast ultrasound: automated or hand-held? Exploring patients' experience and preference

Background

Our aim was to compare women’s experience with automated breast ultrasound (ABUS) versus breast hand-held ultrasound (HHUS) and to evaluate their acceptance rate.

Methods

After ethical approval, from October 2017 to March 2018, 79 consecutive patients were enrolled in this prospective study. On the same day, patients underwent HHUS followed by ABUS. Each patient’s experience was assessed using the modified testing morbidities index (TMI) (the lower the score, the better is the experience). Nine items were assessed for both techniques: seven directly related to the examination technique (pain or discomfort immediately before (preparation), during and after testing, fear or anxiety immediately before (preparation) and during testing, physical and mental function after testing) and two indirectly related to the examination technique (embarrassment during testing and overall satisfaction). Finally, we asked patients to choose between the two techniques for a potential next breast examination. Wilcoxon signed ranks test was used.

Results

The median TMI score for the seven items was found to be significantly better for HHUS (8, interquartile range [IQR] 7–11) compared to ABUS (9, IQR 8–12) (p = 0.003). The item ‘pain/discomfort during the test’ (p < 0.001) was significantly higher for ABUS compared to HHUS. Instead, the item ‘fear/anxiety before the test’ was higher for HHUS (p = 0.001). Overall, 40.5% of the patients chose HHUS, 29.1% chose ABUS, and 30.4% were unable to choose.

Conclusions

ABUS and HHUS exams were well tolerated and accepted. However, HHUS was perceived to be less painful than ABUS.

Automatic Breast Volume Scanner versus Handheld Ultrasound in Differentiation of Benign and Malignant Breast Lesions: A Systematic Review and Meta-analysis

The goal of the study described here was to compare the automatic breast volume scanner (ABVS) and handheld ultrasound (HHUS) with respect to diagnostic performance in the differential diagnosis of benign and malignant breast lesions. A literature search of the PubMed, EMBASE and Cochrane Library databases through 30 June 2018 was conducted. Pooled sensitivity, specificity, positive and negative likelihood ratios and diagnostic odds ratios of the ABVS and HHUS were calculated, and summary receiver operating characteristic (SROC) curves were drawn. A total of nine studies, including 1985 lesions (628 malignant and 1357 benign) from 1774 patients, were analyzed. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and diagnostic odds ratio for ABVS were 90.8% (95% confidence interval: 88.3%-93.0%), 82.2% (80.0%-84.2%), 5.39 (4.26-6.80), 0.10 (0.06-0.15) and 61.68 (32.31-117.76); those for HHUS were 90.6% (88.1%-92.8%), 81.0% (78.8%-83.0%), 5.22 (3.14-8.67), 0.11 (0.08-0.17) and 52.60 (32.06-86.35), respectively. The areas under the SROC curves in the differentiation of benign and malignant breast lesions were 0.93 and 0.94 for ABVS and HHUS, respectively, which were not significantly different (p = 0.853). In conclusion, based on available evidence in the literature, ABVS the diagnostic performance of the ABVS is similar to that of HHUS in the differentiation of benign and malignant breast lesions.

Factors affecting the concordance of radiologic and pathologic tumor size in breast carcinoma

Background

Radiologic assessment of tumor size is an integral part of the work-up for breast carcinoma. With improved radiologic equipment, surgical decision relies profoundly upon radiologic/clinical stage. We wanted to see the concordance between radiologic and pathologic tumor size to infer how accurate radiologic/clinical staging is.

Materials and methods

The surgical pathology and ultrasonography reports of patients with breast carcinoma were reviewed. Data were collected for 406 cases. Concordance was defined as a size difference within ±2 mm.

Results

The difference between radiologic and pathologic tumor size was within ±2 mm in 40.4% cases. The mean radiologic size was 1.73 ± 1.06 cm. The mean pathologic size was 1.84 ± 1.24 cm. A paired t-test showed a significant mean difference between radiologic and pathologic measurements (0.12 ± 1.03 cm, p = 0.03). Despite the size difference, stage classification was the same in 59.9% of cases. Radiologic size overestimated stage in 14.5% of cases and underestimated stage in 25.6% of cases. The concordance rate was significantly higher for tumors ≤2 cm (pT1) (51.1%) as compared to those greater than 2 cm (≥pT2) (19.7%) (p < 0.0001). Significantly more lumpectomy specimens (47.5%) had concordance when compared to mastectomy specimens (29.8%) (p < 0.0001). Invasive ductal carcinoma had better concordance compared to other tumors (p = 0.02).

Conclusion

Mean pathologic tumor size was significantly different from mean radiologic tumor size. Concordance was in just over 40% of cases and the stage classification was the same in about 60% of cases only. Therefore, surgical decision of lumpectomy versus mastectomy based on radiologic tumor size may not always be accurate.