Diagnostic Breast Ultrasound: Current Status and Future Directions

Application of artificial intelligence in predicting malignancy risk in breast masses on ultrasound

Objective

To evaluate the results obtained with an artificial intelligence-based software for predicting the risk of malignancy in breast masses from ultrasound images.

Materials and Methods

This was a retrospective, single-center study evaluating 555 breast masses submitted to percutaneous biopsy at a cancer referral center. Ultrasonographic findings were classified in accordance with the BI-RADS lexicon. The images were analyzed by using Koios DS Breast software and classified as benign, probably benign, low to intermediate suspicion, high suspicion, or probably malignant. The histological classification was considered the reference standard.

Results

The mean age of the patients was 51 years, and the mean mass size was 16 mm. The radiologist evaluation had a sensitivity and specificity of 99.1% and 34.0%, respectively, compared with 98.2% and 39.0%, respectively, for the software evaluation. The positive predictive value for malignancy for the BI-RADS categories was similar between the radiologist and software evaluations. Two false-negative results were identified in the radiologist evaluation, the masses in question being classified as suspicious by the software, whereas four false-negative results were identified in the software evaluation, the masses in question being classified as suspicious by the radiologist.

Conclusion

In our sample, the performance of artificial intelligence-based software was comparable to that of a radiologist.

Color Doppler Ultrasound Improves Machine Learning Diagnosis of Breast Cancer

Color Doppler is used in the clinic for visually assessing the vascularity of breast masses on ultrasound, to aid in determining the likelihood of malignancy. In this study, quantitative color Doppler radiomics features were algorithmically extracted from breast sonograms for machine learning, producing a diagnostic model for breast cancer with higher performance than models based on grayscale and clinical category from the Breast Imaging Reporting and Data System for ultrasound (BI-RADS_US). Ultrasound images of 159 solid masses were analyzed. Algorithms extracted nine grayscale features and two color Doppler features. These features, along with patient age and BI-RADS_US category, were used to train an AdaBoost ensemble classifier. Though training on computer-extracted grayscale features and color Doppler features each significantly increased performance over that of models trained on clinical features, as measured by the area under the receiver operating characteristic (ROC) curve, training on both color Doppler and grayscale further increased the ROC area, from 0.925 ± 0.022 to 0.958 ± 0.013. Pruning low-confidence cases at 20% improved this to 0.986 ± 0.007 with 100% sensitivity, whereas 64% of the cases had to be pruned to reach this performance without color Doppler. Fewer borderline diagnoses and higher ROC performance were both achieved for diagnostic models of breast cancer on ultrasound by machine learning on color Doppler features.

Classification of Benign and Malignant Breast Tumors Using H-Scan Ultrasound Imaging

Breast cancer is one of the most common cancers among women worldwide. Ultrasound imaging has been widely used in the detection and diagnosis of breast tumors. However, due to factors such as limited spatial resolution and speckle noise, classification of benign and malignant breast tumors using conventional B-mode ultrasound still remains a challenging task. H-scan is a new ultrasound technique that images the relative size of acoustic scatterers. However, the feasibility of H-scan ultrasound imaging in the classification of benign and malignant breast tumors has not been investigated. In this paper, we proposed a new method based on H-scan ultrasound imaging to classify benign and malignant breast tumors. Backscattered ultrasound radiofrequency signals of 100 breast tumors were used (48 benign and 52 malignant cases). H-scan ultrasound images were constructed with the radiofrequency signals by matched filtering using Gaussian-weighted Hermite polynomials. Experimental results showed that benign breast tumors had more red components, while malignant breast tumors had more blue components in H-scan ultrasound images. There were significant differences between the RGB channels of H-scan ultrasound images of benign and malignant breast tumors. We conclude H-scan ultrasound imaging can be used as a new method for classifying benign and malignant breast tumors.

Expanding Acquisition and Clutter Filter Dimensions for Improved Perfusion Sensitivity

A method is explored for increasing the sensitivity of power-Doppler imaging without contrast enhancement. We acquire 1-10 s of echo signals and arrange it into a 3-D spatiotemporal data array. An eigenfilter developed to preserve all three dimensions of the array yields power estimates for blood flow and perfusion that are well separated from tissue clutter. This method is applied at high frequency (24-MHz pulses) to a murine model of an ischemic hindlimb. We demonstrate enhancements to tissue perfusion maps in normal and ischemic tissues. The method can be applied to data from any ultrasonic instrument that provides beamformed RF echo data.

Leverage of an Existing Cervical Cancer Prevention Service Platform to Initiate Breast Cancer Control Services in Zambia: Experiences and Early Outcomes

PURPOSE

In 2005, the Cervical Cancer Prevention Program in Zambia (CCPPZ) was implemented and has since provided cervical cancer screen-and-treat services to more than 500,000 women. By leveraging the successes and experiences of the CCPPZ, we intended to build capacity for the early detection and surgical treatment of breast cancer.

METHODS

Our initiative sought to build capacity for breast cancer care through the (1) formation of a breast cancer advocacy alliance to raise awareness, (2) creation of resource-appropriate breast cancer care training curricula for mid- and high-level providers, and (3) implementation of early detection and treatment capacity within two major health care facilities.

RESULTS

Six months after the completion of the initiative, the following outcomes were documented: Breast health education and clinical breast examination (CBE) services were successfully integrated into the service platforms of four CCPPZ clinics. Two new breast diagnostic centers were opened, which provided access to breast ultrasound, ultrasound-guided core needle biopsy, and needle aspiration. Breast health education and CBE were provided to 1,955 clients, 167 of whom were evaluated at the two diagnostic centers; 55 of those evaluated underwent core-needle biopsy, of which 17 were diagnosed with invasive cancer. Newly trained surgeons performed six sentinel lymph node mappings, eight sentinel lymph node dissections, and 10 breast conservation surgeries (lumpectomies).

CONCLUSION

This initiative successfully established clinical services in Zambia that are critical for the early detection and surgical management of breast cancer.

Efficiency of U.S. Tissue Perfusion Estimators

We measure the detection and discrimination efficiencies of conventional power-Doppler estimation of perfusion without contrast enhancement. The measurements are made in a phantom with known blood-mimicking fluid flow rates in the presence of clutter and noise. Efficiency is measured by comparing functions of the areas under the receiver operating characteristic curve for Doppler estimators with those of the ideal discriminator, for which we estimate the temporal covariance matrix from echo data. Principal-component analysis is examined as a technique for increasing the accuracy of covariance matrices estimated from echo data. We find that Doppler estimators are <50% efficient at directed perfusion detection between 0.1 and 2.0 mL/min per 2 cm(2) flow area. The efficiency was 20%-40% for the task of discriminating between two perfusion rates in the same range. We conclude that there are reasons to search for more efficient perfusion estimators, one that incorporates covariance matrix information that could significantly enhance the utility of Doppler ultrasound without contrast enhancement.

Label-free Detection of Lymph Node Metastases with US-guided Functional Photoacoustic Imaging

PURPOSE

To determine the ability of ultrasonography (US)-guided spectroscopic photoacoustic (sPA) imaging to depict changes in blood oxygen saturation (SO2) in metastatic lymph nodes of a mouse model of oral cancer.

MATERIALS AND METHODS

All studies were performed by following protocols approved by the institutional animal care and use committee at the University of Texas at Austin. Coregistered US and photoacoustic images were acquired spanning volumes containing a total of 31 lymph nodes in 17 female nu/nu mice. The mice were either healthy (three mice, five nodes) or bearing a primary tumor consisting of luciferase-labeled FaDu cells (14 mice, 26 nodes). Ten photoacoustic images acquired with optical wavelengths spanning from 680 to 860 nm were spectrally unmixed by using a linear least-squares method to obtain sPA images. After imaging, histologic analysis enabled confirmation of the presence of micrometastases. Generalized estimating equations were used to compare metastatic and normal lymph nodes, with a P value of .05 taken to indicate a significant difference. Sensitivity and specificity were determined with a receiver operator characteristic curve constructed from the background-subtracted SO2 values.

RESULTS

Metastatic lymph nodes (n = 7) exhibited a significantly (P = .018) lower spatially averaged background-subtracted SO2 (mean, 5.4% ± 3.5 [standard error]) when compared with lymph nodes without metastases (mean, 13.7% ± 1.3; n = 24). This effect was observed throughout the entire volume of the nodes rather than being limited to the metastatic foci. The change in SO2, which was inversely related to the size of the metastasis, was detectable in metastases as small as 2.6 × 10(-3) mm(3).

CONCLUSION

The results show that US-guided sPA imaging is capable of depicting changes in SO2 in lymph nodes that were correlated with metastatic invasion.

High-quality breast ultrasonography

Ultrasonography is an important modality that is frequently used in all aspects of breast imaging, including breast cancer screening, the evaluation of palpable abnormalities, further characterization of lesions seen mammographically, and for determining the method of percutaneous biopsy. Understanding the basic technical aspects of ultrasonography equipment is critical to ensure high breast ultrasonography image quality.

In Vivo response to compression of 35 breast lesions observed with a two-dimensional locally regularized strain estimation method

The objective of this study was to assess the in vivo performance of our 2-D locally regularized strain estimation method with 35 breast lesions, mainly cysts, fibroadenomas and carcinomas. The specific 2-D deformation model used, as well as the method's adaptability, led to an algorithm that is able to track tissue motion from radiofrequency ultrasound images acquired in clinical conditions. Particular attention was paid to strain estimation reliability, implying analysis of the mean normalized correlation coefficient maps. For all lesions examined, the results indicated that strain image interpretation, as well as its comparison with B-mode data, should take into account the information provided by the mean normalized correlation coefficient map. Different trends were observed in the tissue response to compression. In particular, carcinomas appeared larger in strain images than in B-mode images, resulting in a mean strain/B-mode lesion area ratio of 2.59 ± 1.36. In comparison, the same ratio was assessed as 1.04 ± 0.26 for fibroadenomas. These results are in agreement with those of previous studies, and confirm the interest of a more thorough consideration of size difference as one parameter discriminating between malignant and benign lesions.

Indicações de ressonância magnética das mamas em um centro de referência em oncologia

OBJETIVO: Avaliar e discutir as indicações de ressonância magnética das mamas em um centro de referência oncológico. MATERIAIS E MÉTODOS: Estudo retrospectivo, aprovado pelo Comitê de Ética e Pesquisa da instituição, conduzido através da revisão de prontuários e laudos médicos. Foram incluídos todos os exames de ressonância magnética das mamas realizados no período de julho de 2008 a julho de 2009 (n = 529). RESULTADOS: A idade média das pacientes foi de 49 anos, variando de 17 a 86 anos. História familiar de câncer de mama e/ou ovário esteve presente em 162 pacientes (30,6%). As indicações mais comuns de ressonância magnética das mamas foram esclarecimento de achados inconclusivos na mamografia e/ou ultrassom (48,8%), avaliação de recorrência tumoral/cicatriz cirúrgica (15,1%), estadiamento/planejamento cirúrgico (11,7%) e rastreamento de pacientes de alto risco (8,5%). CONCLUSÃO: Apesar de achados inconclusivos nos exames convencionais serem a indicação mais comum de ressonância magnética das mamas, não há evidências que justifiquem esta conduta na literatura. Em razão da sua alta sensibilidade e percentual de falso-positivos, este exame deve ser adequadamente indicado, para evitar a realização de procedimentos desnecessários. Se bem indicada, a ressonância magnética pode contribuir para o processo de tomada de decisão e constitui uma ferramenta fundamental na avaliação de lesões mamárias.

Multidisciplinary care for patients with breast cancer

The care of patients with breast cancer has become increasingly complex with advancements in diagnostic modalities, surgical approaches, and adjuvant treatments. A multidisciplinary approach to breast cancer care is essential to the successful integration of available therapies. This article addresses the key components of multidisciplinary breast cancer care, with a special emphasis on new and emerging approaches over the past 10 years in the fields of diagnostics, surgery, radiation, medical oncology, and plastic surgery.