Evaluation of the FUSION-X-US-II prototype to combine automated breast ultrasound and tomosynthesis

Diagnostic accuracy of supplemental three-dimensional breast ultrasound in the work-up of BI-RADS 0 screening recalls

OBJECTIVE

To evaluate the diagnostic accuracy of supplemental 3D automated breast ultrasound (ABUS) in the diagnostic work-up of BI-RADS 0 recalls. We hypothesized that 3D ABUS may reduce the benign biopsy rate.

MATERIALS AND METHODS

In this prospective multicenter diagnostic study, screening participants recalled after a BI-RADS 0 result underwent bilateral 3D ABUS supplemental to usual care: digital breast tomosynthesis (DBT) and targeted hand-held ultrasound (HHUS). Sensitivity, specificity, positive predictive value, and negative predictive value of 3D ABUS, and DBT plus HHUS, were calculated. New 3D ABUS findings and changes of management (biopsy or additional imaging) were recorded.

RESULTS

A total of 501 women (median age 55 years, IQR [51-64]) with 525 BI-RADS 0 lesions were included between April 2018 and March 2020. Cancer was diagnosed in 45 patients. 3D ABUS sensitivity was 72.1% (95% CI [57.2-83.4%]), specificity 84.4% (95% CI [80.8-87.4%]), PPV 29.2% (95% CI [21.4-38.5%]), and NPV 97.1% 95.0-98.4%). Sensitivity of DBT plus HHUS was 100% (95% CI [90.2-100%]), specificity 71.4% (95% CI [67.2-75.2%]), PPV 23.8% (95% CI [18.1-30.5%]) and NPV 100% (95% CI [98.7-100%]). Twelve out of 43 (27.9%) malignancies in BI-RADS 0 lesions were missed on 3D ABUS, despite being detected on DBT and/or HHUS. Supplemental 3D ABUS resulted in the detection of 57 new lesions and six extra biopsy procedures, all were benign.

CONCLUSION

3D ABUS in the diagnostic work-up of BI-RADS 0 recalls may miss over a quarter of cancers detected with HHUS and/or DBT and should not be used to omit biopsy. Supplemental 3D ABUS increases the benign biopsy rate.

TRIAL REGISTRATION

Dutch Trial Register, available via https://www.onderzoekmetmensen.nl/en/trial/29659 CRITICAL RELEVANCE STATEMENT: Supplemental 3D automated breast ultrasound in the work-up of BI-RADS 0 recalls may miss over a quarter of cancers detected with other methods and should not be used to omit biopsy; ABUS findings did increase benign biopsy rate.

KEY POINTS

Automated breast ultrasound (ABUS) may miss over 25% of cancers detectable by alternative methods. Don't rely solely on 3D ABUS to assess indication for biopsy. New findings with supplemental 3D ABUS increase the benign biopsy rate.

Best Practice Guideline - DEGUM Recommendations on Breast Ultrasound

Alongside mammography, breast ultrasound is an important and well-established method in assessment of breast lesions. With the "Best Practice Guideline", the DEGUM Breast Ultrasound (in German, "Mammasonografie") working group, intends to describe the additional and optional application modalities for the diagnostic confirmation of breast findings and to express DEGUM recommendations in this Part II, in addition to the current dignity criteria and assessment categories published in Part I, in order to facilitate the differential diagnosis of ambiguous lesions.The present "Best Practice Guideline" has set itself the goal of meeting the requirements for quality assurance and ensuring quality-controlled performance of breast ultrasound. The most important aspects of quality assurance are explained in this Part II of the Best Practice Guideline.

Clinical prototype implementation enabling an improved day-to-day mammography compression

PURPOSE

In mammography, breast compression is achieved by lowering a compression paddle on the breast. Despite the directive that compression is needed, there is no concrete guideline on its execution. To estimate the degree of compression, current mammography units only provide compression force and breast thickness as parameters. Therefore, radiographers could be induced to mainly determine the level of compression based on compression force and apply the same value to all breast sizes. In this case, smaller breast sizes are exposed to higher pressure. This results in a highly varying perception of discomfort or even pain during the procedure, depending on the breast size.

METHODS

To overcome this imbalance, current research results suggest that pressure might be a more qualified parameter for a more uniform compression among all breast sizes. To utilize pressure, the contact area between breast and compression paddle must be determined. In this paper, we present an easy-to-implement prototype enabling a real-time pressure-based measure without the need of direct patient contact. Using an optical camera, the contact area between the breast and the compression paddle is automatically segmented by a deep learning model.

RESULTS

The model provides a mean pixel accuracy of 96.7% (SD: 2.3%), mean frequency-weighted intersection over union of 88.5% (SD: 6.3%), and a Dice score of 93.6% (SD: 2.2%). The subsequent pressure display is updated more than five times per second which enables the use in clinical routines to set the compression level.

CONCLUSION

This prototype could help guiding to an improved breast compression routine in mammography procedures.

The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis

OBJECTIVES

AI-based algorithms for medical image analysis showed comparable performance to human image readers. However, in practice, diagnoses are made using multiple imaging modalities alongside other data sources. We determined the importance of this multi-modal information and compared the diagnostic performance of routine breast cancer diagnosis to breast ultrasound interpretations by humans or AI-based algorithms.

METHODS

Patients were recruited as part of a multicenter trial (NCT02638935). The trial enrolled 1288 women undergoing routine breast cancer diagnosis (multi-modal imaging, demographic, and clinical information). Three physicians specialized in ultrasound diagnosis performed a second read of all ultrasound images. We used data from 11 of 12 study sites to develop two machine learning (ML) algorithms using unimodal information (ultrasound features generated by the ultrasound experts) to classify breast masses which were validated on the remaining study site. The same ML algorithms were subsequently developed and validated on multi-modal information (clinical and demographic information plus ultrasound features). We assessed performance using area under the curve (AUC).

RESULTS

Of 1288 breast masses, 368 (28.6%) were histopathologically malignant. In the external validation set (n = 373), the performance of the two unimodal ultrasound ML algorithms (AUC 0.83 and 0.82) was commensurate with performance of the human ultrasound experts (AUC 0.82 to 0.84; p for all comparisons > 0.05). The multi-modal ultrasound ML algorithms performed significantly better (AUC 0.90 and 0.89) but were statistically inferior to routine breast cancer diagnosis (AUC 0.95, p for all comparisons ≤ 0.05).

CONCLUSIONS

The performance of humans and AI-based algorithms improves with multi-modal information.

KEY POINTS

• The performance of humans and AI-based algorithms improves with multi-modal information. • Multimodal AI-based algorithms do not necessarily outperform expert humans. • Unimodal AI-based algorithms do not represent optimal performance to classify breast masses.

Automated Breast Ultrasound: Technical Aspects, Impact on Breast Screening, and Future Perspectives

Purpose of Review

Automated breast ultrasound (ABUS) is a three-dimensional imaging technique, used as a supplemental screening tool in women with dense breasts. This review considers the technical aspects, pitfalls, and the use of ABUS in screening and clinical practice, together with new developments and future perspectives.

Recent Findings

ABUS has been approved in the USA and Europe as a screening tool for asymptomatic women with dense breasts in addition to mammography. Supplemental US screening has high sensitivity for cancer detection, especially early-stage invasive cancers, and reduces the frequency of interval cancers. ABUS has similar diagnostic performance to handheld ultrasound (HHUS) and is designed to overcome the drawbacks of operator dependence and poor reproducibility. Concerns with ABUS, like HHUS, include relatively high recall rates and lengthy reading time when compared to mammography. ABUS is a new technique with unique features; therefore, adequate training is required to improve detection and reduce false positives. Computer-aided detection may reduce reading times and improve cancer detection. Other potential applications of ABUS include local staging, treatment response evaluation, breast density assessment, and integration of radiomics.

Summary

ABUS provides an efficient, reproducible, and comprehensive supplemental imaging technique in breast screening. Developments with computer-aided detection may improve the sensitivity and specificity as well as radiologist confidence and reduce reading times, making this modality acceptable in large volume screening centers.

A Review of Breast Imaging for Timely Diagnosis of Disease

Breast cancer (BC) is the cancer with the highest incidence in women in the world. In this last period, the COVID-19 pandemic has caused in many cases a drastic reduction of routine breast imaging activity due to the combination of various factors. The survival of BC is directly proportional to the earliness of diagnosis, and especially during this period, it is at least fundamental to remember that a diagnostic delay of even just three months could affect BC outcomes. In this article we will review the state of the art of breast imaging, starting from morphological imaging, i.e., mammography, tomosynthesis, ultrasound and magnetic resonance imaging and contrast-enhanced mammography, and their most recent evolutions; and ending with functional images, i.e., magnetic resonance imaging and contrast enhanced mammography.