Ultrasonographic assessment of breast density

Preliminary study of standardized semiquantitative method for ultrasonographic breast composition assessment

PURPOSE

To develop a classification tree via semiquantitative analysis for ultrasonographic breast composition assessment using routine breast ultrasonography examination images.

METHODS

This study retrospectively enrolled 100 consecutive normal women who underwent screening mammography and supplemental ultrasonography. Based on sonographic breast composition, the patients' breasts were classified as nondense or dense, which were correlated with mammographic breast composition. Ultrasonographic breast composition was classified based on the fibroglandular tissue (FGT) thickness-to-subcutaneous fat and retromammary fat (FAT) thickness ratio. In addition, the presence of a high glandular tissue component (GTC) in FGT or the presence of evident fat lobules in FGT was investigated. The cutoff point between the nondense and dense breasts was calculated from the area under the curve (AUC).

RESULTS

All cases with a high GTC were dense breasts, and all cases with evident fat lobules in the FGT were nondense breasts. The AUC of the FGT thickness-to-FAT ratio of all cases, the group without a high GTC, the group without evident fat lobules in the FGT, and the group without a high GTC or evident fat lobules in the FGT were 0.93, 0.94, 0.99, and 1, respectively.

CONCLUSION

The presence of a high GTC indicated dense breasts, and the presence of evident fat lobules in the FGT represented nondense breasts. For the remaining cases, the cutoff point of the FGT thickness-to-FAT thickness ratio was 0.93 for ultrasonographic two-grade scale breast composition assessment with 100% accuracy.

Nonmass Lesions on Breast US: An International Perspective on Clinical Use and Outcomes

Nonmass lesions (NMLs) on breast US are defined as discrete areas of altered echotexture compared to surrounding breast tissue and lack the 3-dimensionality of a mass. They are not a component of American College of Radiology BI-RADS, but they are a finding type included in the Japan Association of Breast and Thyroid Sonology lexicon. Use of the NML finding is routine in many Asian practices, including the Samsung Medical Center and Seoul National University Hospital, and their features and outcomes have been investigated in multiple studies. Nonmass lesions are most often observed when US is used to evaluate mammographic asymmetries, suspicious calcifications, and nonmass enhancement on MRI and contrast-enhanced mammography. Nonmass lesions can be described by their echogenicity, distribution, presence or absence of associated calcifications, abnormal duct changes, architectural distortion, posterior shadowing, small cysts, and hypervascularity. Malignant lesions, especially ductal carcinoma in situ, can manifest as NMLs on US. There is considerable overlap between the US features of benign and malignant NMLs, and they also must be distinguished from normal variants. The literature indicates that NMLs with linear or segmental distribution, associated calcifications, abnormal duct changes, posterior shadowing, and hypervascularity are suggestive of malignancy, whereas NMLs with only interspersed small cysts are usually benign fibrocystic changes. In this article, we introduce the concepts of NMLs, illustrate US features suggestive of benign and malignant etiologies, and discuss our institutional approach for evaluating NMLs and an algorithm that we use to guide interpretation in clinical practice.

Analysis of background echotexture on automated breast ultrasound using BI-RADS and modified classification: Association with clinical features and mammographic density

PURPOSE

To analyze BE on ABUS using BI-RADS and a modified classification in association with mammographic density and clinical features.

METHODS

Menopausal status, parity, and family history of breast cancer were collected for 496 women who underwent ABUS and mammography. Three radiologists independently reviewed all ABUS BE and mammographic density. Statistical analyses including kappa statistics (κ) for interobserver agreement, Fisher's exact test, and univariate and multivariate multinomial logistic regression were performed.

RESULTS

BE distribution between the two classifications and between each classification and mammographic density were associated (P < 0.001). BI-RADS homogeneous-fibroglandular (76.8%) and modified heterogeneous BE (71.3%, 75.7%, and 87.5% of mild, moderate, and marked heterogeneous background echotexture, respectively) tended to be dense. BE was correlated between BI-RADS homogeneous-fat and modified homogeneous background (95.1%) and between BI-RADS homogeneous-fibroglandular or heterogeneous (90.6%) and modified heterogeneous (86.9%) (P < 0.001). In multinomial logistic regression, age < 50 years was independently associated with heterogeneous BE (OR, 8.89, P = 0.003, in BI-RADS; OR, 3.74; P = 0.020 in modified classification).

CONCLUSION

BI-RADS homogeneous-fat and modified homogeneous BE on ABUS was likely to be mammographically fatty. However, BI-RADS homogeneous-fibroglandular or heterogeneous BE might be classified as any modified BE. Younger age was independently associated with heterogeneous BE.

Beyond Breast Density: Risk Measures for Breast Cancer in Multiple Imaging Modalities

Breast density is an independent risk factor for breast cancer. In digital mammography and digital breast tomosynthesis, breast density is assessed visually using the four-category scale developed by the American College of Radiology Breast Imaging Reporting and Data System (5th edition as of November 2022). Epidemiologically based risk models, such as the Tyrer-Cuzick model (version 8), demonstrate superior modeling performance when mammographic density is incorporated. Beyond just density, a separate mammographic measure of breast cancer risk is parenchymal textural complexity. With advancements in radiomics and deep learning, mammographic textural patterns can be assessed quantitatively and incorporated into risk models. Other supplemental screening modalities, such as breast US and MRI, offer independent risk measures complementary to those derived from mammography. Breast US allows the two components of fibroglandular tissue (stromal and glandular) to be visualized separately in a manner that is not possible with mammography. A higher glandular component at screening breast US is associated with higher risk. With MRI, a higher background parenchymal enhancement of the fibroglandular tissue has also emerged as an imaging marker for risk assessment. Imaging markers observed at mammography, US, and MRI are powerful tools in refining breast cancer risk prediction, beyond mammographic density alone.

Performance of novel deep learning network with the incorporation of the automatic segmentation network for diagnosis of breast cancer in automated breast ultrasound

OBJECTIVE

To develop novel deep learning network (DLN) with the incorporation of the automatic segmentation network (ASN) for morphological analysis and determined the performance for diagnosis breast cancer in automated breast ultrasound (ABUS).

METHODS

A total of 769 breast tumors were enrolled in this study and were randomly divided into training set and test set at 600 vs. 169. The novel DLNs (Resent v2, ResNet50 v2, ResNet101 v2) added a new ASN to the traditional ResNet networks and extracted morphological information of breast tumors. The accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic (ROC) curve (AUC), and average precision (AP) were calculated. The diagnostic performances of novel DLNs were compared with those of two radiologists with different experience.

RESULTS

The ResNet34 v2 model had higher specificity (76.81%) and PPV (82.22%) than the other two, the ResNet50 v2 model had higher accuracy (78.11%) and NPV (72.86%), and the ResNet101 v2 model had higher sensitivity (85.00%). According to the AUCs and APs, the novel ResNet101 v2 model produced the best result (AUC 0.85 and AP 0.90) compared with the remaining five DLNs. Compared with the novice radiologist, the novel DLNs performed better. The F1 score was increased from 0.77 to 0.78, 0.81, and 0.82 by three novel DLNs. However, their diagnostic performance was worse than that of the experienced radiologist.

CONCLUSIONS

The novel DLNs performed better than traditional DLNs and may be helpful for novice radiologists to improve their diagnostic performance of breast cancer in ABUS.

KEY POINTS

• A novel automatic segmentation network to extract morphological information was successfully developed and implemented with ResNet deep learning networks. • The novel deep learning networks in our research performed better than the traditional deep learning networks in the diagnosis of breast cancer using ABUS images. • The novel deep learning networks in our research may be useful for novice radiologists to improve diagnostic performance.

Impact of a randomized weight loss trial on breast tissue markers in breast cancer survivors

Few trials have examined the effect of lifestyle behavioral interventions on tissue markers in patients with cancer. The purpose of this study was to examine the feasibility and impact of a 6-month weight loss intervention on breast tissue and serum biomarkers in women with breast cancer. Fifty-one women who completed breast cancer treatment and had a BMI ≥ 25.0 kg/m² were randomized to a weight loss intervention or usual care. Breast tissue biopsies, fasting blood draw and body composition were collected at baseline and 6 months, with between-group changes examined using analysis of covariance method. Baseline and post-intervention biopsies were conducted in 49 and 42 women, respectively, with pre- and post-epithelial tissue available from 25 tissue samples. Average 6-month weight loss was 6.7% for the weight loss group and 2.0% increase for the usual care group (p < 0.0001). At baseline, body fat and serum insulin levels were inversely associated with breast tissue insulin receptor levels and CD68 (p < 0.05). At 6 months, favorable changes were observed in serum leptin and adiponectin levels and tissue CD163 among women randomized to weight loss vs. adverse change in women randomized to usual care (p < 0.05). Breast tissue biopsies are feasible to collect in a clinical research setting among breast cancer survivors, with weight loss favorably impacting metabolic and inflammatory markers associated with breast cancer.

Automated breast US as the primary screening test for breast cancer among East Asian women aged 40-49 years: a multicenter prospective study

OBJECTIVES

To prospectively evaluate the diagnostic performance of screening ABUS as the primary screening test for breast cancer among Korean women aged 40-49 years.

METHODS

This prospective, multicenter study included asymptomatic Korean women aged 40-49 years from three academic centers between February 2017 and October 2019. Each participant underwent ABUS without mammography, and the ABUS images were interpreted at each hospital with double-reading by two breast radiologists. Biopsy and at least 1 year of follow-up was considered the reference standard. Diagnostic performance of ABUS screening and subgroup analyses according to patient and tumor characteristics were evaluated.

RESULTS

Reference standard data were available for 959 women. The recall rate was 9.8% (95% confidence interval [CI]: 7.9%, 11.7%; 94 of 959 women) and the cancer detection yield was 5.2 per 1000 women (95% CI: -0.6, 11.1; 5 of 959 women). There was only one interval cancer. The sensitivity was 83.3% (95% CI: 53.5%, 100%; 5 of 6 cancers) and the specificity was 90.7% (95% CI: 88.8%, 92.5%; 864 of 95. women). The positive predictive values of biopsies performed (PPV₃) was 20.0% (95% CI: 4.3%, 35.7%; 5 of 25 women). Women with heterogeneous background echotexture had a higher recall rate (p = .009) and lower specificity (p = .036). Women with body mass index values < 25 kg/m² had a higher mean recall rate (p = .046).

CONCLUSION

In East Asia, screening automated breast US may be an alternative to screening mammography for detecting breast cancers in women aged 40-49 years.

KEY POINTS

• Automated breast US screening for breast cancer in asymptomatic women aged 40-49 is effective with 5.2 per 1000 cancer detection yield. • Women with heterogeneous background echotexture had a higher recall rate and lower specificity. • Women with body mass index < 25 kg/m² had a higher recall rate.

False-negative results on computer-aided detection software in preoperative automated breast ultrasonography of breast cancer patients

Purpose

The purpose of this study was to measure the cancer detection rate of computer-aided detection (CAD) software in preoperative automated breast ultrasonography (ABUS) of breast cancer patients and to determine the characteristics associated with false-negative outcomes.

Methods

A total of 129 index lesions (median size, 1.7 cm; interquartile range, 1.2 to 2.4 cm) from 129 consecutive patients (mean age±standard deviation, 53.4±11.8 years) who underwent preoperative ABUS from December 2017 to February 2018 were assessed. An index lesion was defined as a breast cancer confirmed by ultrasonography (US)-guided core needle biopsy. The detection rate of the index lesions, positive predictive value (PPV), and false-positive rate (FPR) of the CAD software were measured. Subgroup analysis was performed to identify clinical and US findings associated with false-negative outcomes.

Results

The detection rate of the CAD software was 0.84 (109 of 129; 95% confidence interval, 0.77 to 0.90). The PPV and FPR were 0.41 (221 of 544; 95% CI, 0.36 to 0.45) and 0.45 (174 of 387; 95% CI, 0.40 to 0.50), respectively. False-negative outcomes were more frequent in asymptomatic patients (P<0.001) and were associated with the following US findings: smaller size (P=0.001), depth in the posterior third (P=0.002), angular or indistinct margin (P<0.001), and absence of architectural distortion (P<0.001).

Conclusion

The CAD software showed a promising detection rate of breast cancer. However, radiologists should judge whether CAD software-marked lesions are true- or false-positive lesions, considering its low PPV and high FPR. Moreover, it would be helpful for radiologists to consider the characteristics associated with false-negative outcomes when reading ABUS with CAD.

Semi-supervised segmentation of lesion from breast ultrasound images with attentional generative adversarial network

BACKGROUND AND OBJECTIVE

Automatic segmentation of breast lesion from ultrasound images is a crucial module for the computer aided diagnostic systems in clinical practice. Large-scale breast ultrasound (BUS) images remain unannotated and need to be effectively explored to improve the segmentation quality. To address this, a semi-supervised segmentation network is proposed based on generative adversarial networks (GAN).

METHODS

In this paper, a semi-supervised learning model, denoted as BUS-GAN, consisting of a segmentation base network-BUS-S and an evaluation base network-BUS-E, is proposed. The BUS-S network can densely extract multi-scale features in order to accommodate the individual variance of breast lesion, thereby enhancing the robustness of segmentation. Besides, the BUS-E network adopts a dual-attentive-fusion block having two independent spatial attention paths on the predicted segmentation map and leverages the corresponding original image to distill geometrical-level and intensity-level information, respectively, so that to enlarge the difference between lesion region and background, thus improving the discriminative ability of the BUS-E network. Then, through adversarial training, the BUS-GAN model can achieve higher segmentation quality because the BUS-E network guides the BUS-S network to generate more accurate segmentation maps with more similar distribution as ground truth.

RESULTS

The counterpart semi-supervised segmentation methods and the proposed BUS-GAN model were trained with 2000 in-house images, including 100 annotated images and 1900 unannotated images, and tested on two different sites, including 800 in-house images and 163 public images. The results validate that the proposed BUS-GAN model can achieve higher segmentation accuracy on both the in-house testing dataset and the public dataset than state-of-the-art semi-supervised segmentation methods.

CONCLUSIONS

The developed BUS-GAN model can effectively utilize the unannotated breast ultrasound images to improve the segmentation quality. In the future, the proposed segmentation method can be a potential module for the automatic breast ultrasound diagnose system, thus relieving the burden of a tedious image annotation process and alleviating the subjective influence of physicians' experiences in clinical practice. Our code will be made available on https://github.com/fiy2W/BUS-GAN.

Medical breast ultrasound image segmentation by machine learning

Breast cancer is the most commonly diagnosed cancer, which alone accounts for 30% all new cancer diagnoses for women, posing a threat to women's health. Segmentation of breast ultrasound images into functional tissues can aid tumor localization, breast density measurement, and assessment of treatment response, which is important to the clinical diagnosis of breast cancer. However, manually segmenting the ultrasound images, which is skill and experience dependent, would lead to a subjective diagnosis; in addition, it is time-consuming for radiologists to review hundreds of clinical images. Therefore, automatic segmentation of breast ultrasound images into functional tissues has received attention in recent years, amidst the more numerous studies of detection and segmentation of masses. In this paper, we propose to use convolutional neural networks (CNNs) for segmenting breast ultrasound images into four major tissues: skin, fibroglandular tissue, mass, and fatty tissue, on three-dimensional (3D) breast ultrasound images. Quantitative metrics for evaluation of segmentation results including Accuracy, Precision, Recall, and F1_measure, all reached over 80%, which indicates that the method proposed has the capacity to distinguish functional tissues in breast ultrasound images. Another metric called the Jaccard similarity index (JSI) yields an 85.1% value, outperforming our previous study using the watershed algorithm with 74.54% JSI value. Thus, our proposed method might have the potential to provide the segmentations necessary to assist the clinical diagnosis of breast cancer and improve imaging in other modes in medical ultrasound.

Breast density: why all the fuss?

The term "breast density" or mammographic density (MD) denotes those components of breast parenchyma visualised at mammography that are denser than adipose tissue. MD is composed of a mixture of epithelial and stromal components, notably collagen, in variable proportions. MD is most commonly assessed in clinical practice with the time-honoured method of visual estimation of area-based percent density (PMD) on a mammogram, with categorisation into quartiles. The computerised semi-automated thresholding method, Cumulus, also yielding area-based percent density, is widely used for research purposes; however, the advent of fully automated volumetric methods developed as a consequence of the widespread use of digital mammography (DM) and yielding both absolute and percent dense volumes, has resulted in an explosion of interest in MD recently. Broadly, the importance of MD is twofold: firstly, the presence of marked MD significantly reduces mammographic sensitivity for breast cancer, even with state-of-the-art DM. Recognition of this led to the formation of a powerful lobby group ('Are You Dense') in the US, as a consequence of which 32 states have legislated for mandatory disclosure of MD to women undergoing mammography. Secondly, it is now widely accepted that MD is in itself a risk factor for breast cancer, with a four-to sixfold increased relative risk in women with PMD in the highest quintile compared to those with PMD in the lowest quintile. Consequently, major research efforts are underway to assess whether use of MD could provide a major step forward towards risk-adapted, personalised breast cancer prevention, imaging, and treatment.

Background echotexture classification in breast ultrasound: inter-observer agreement study

Background According to the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS), background echotexture in breast ultrasound (US) can be categorized as homogeneous or heterogeneous. Purpose To prospectively evaluate the inter-observer agreement of a four-category classification in background echotexture assessments of breast US and to determine whether background echotexture is related to breast cancer risk factors, including mammography density. Material and Methods Thirty-eight healthy women (age range, 25-72) were recruited. Eleven radiologists performed breast US on all participants and classified each background echotexture into four categories (homogeneous, mild, moderate, and marked heterogeneous). The inter-observer agreement in the assessments was measured using kappa statistics (к). The association between background echotexture and breast cancer risk factors, including mammographic density, menopausal status, and parity, were evaluated using Spearman's correlation coefficient (ρ) and multiple linear regression analysis. Results There was moderate inter-observer agreement between the radiologists for the four categories of background echotexture (average к = 0.45). Heterogeneity of the background echotexture was positively correlated with mammographic density in both pre- and postmenopausal women (premenopausal, ρ = 0.42, P < 0.0001; postmenopausal, ρ = 0.56, P < 0.0001). Multiple linear regression analysis revealed that mammographic density and parity were significantly associated with background echotexture. Conclusion Background echotexture assessment of breast US using a four-category classification showed moderate inter-observer agreement, and more heterogeneous background echotexture was associated with denser breasts and lower parity.

Imaging Breast Density: Established and Emerging Modalities

Mammographic density has been proven as an independent risk factor for breast cancer. Women with dense breast tissue visible on a mammogram have a much higher cancer risk than women with little density. A great research effort has been devoted to incorporate breast density into risk prediction models to better estimate each individual’s cancer risk. In recent years, the passage of breast density notification legislation in many states in USA requires that every mammography report should provide information regarding the patient’s breast density. Accurate definition and measurement of breast density are thus important, which may allow all the potential clinical applications of breast density to be implemented. Because the two-dimensional mammography-based measurement is subject to tissue overlapping and thus not able to provide volumetric information, there is an urgent need to develop reliable quantitative measurements of breast density. Various new imaging technologies are being developed. Among these new modalities, volumetric mammographic density methods and three-dimensional magnetic resonance imaging are the most well studied. Besides, emerging modalities, including different x-ray–based, optical imaging, and ultrasound-based methods, have also been investigated. All these modalities may either overcome some fundamental problems related to mammographic density or provide additional density and/or compositional information. The present review article aimed to summarize the current established and emerging imaging techniques for the measurement of breast density and the evidence of the clinical use of these density methods from the literature.

Rapid breast density analysis of partial volumes of automated breast ultrasound images

Rapid volume density analysis (RVDA) for automated breast ultrasound (ABUS) has been proposed as a more efficient method for estimating breast density. In the current experiment, ABUS images were obtained for 67 breasts from 40 patients. For each case, three rectangular volumes of interest (VOIs) were extracted, including the VOIs located at the 6 and 12 o'clock positions relative to the nipple in the anterior to posterior pass and the lateral position relative to the nipple in the lateral pass. The centers of these VOIs were defined to align with the center of nipple, and the depths reached the retromammary fat boundary. The fuzzy c-means classifier was applied to differentiate the fibroglandular and fat tissues to estimate the density. The classification results of the three VOIs were averaged to obtain the breast density. The density correlations between the RVDA and the ABUS methods were 0.98 and 0.96 using Pearson's correlation and linear regression coefficients, respectively. The average computation times for RVDA and ABUS were 4.2 and 17.8 seconds, respectively, using an Intel Core2 2.66 GHz computer with 3.25 GB memory. In conclusion, the RVDA method offers a quantitative and efficient breast density estimation for ABUS.

Imperfect correlation of mammographic and clinical breast tissue density

BACKGROUND

Clinicians determine degree of mammographic density based on tissue firmness on breast examination. The study aimed to compare breast density in mammography and clinical breast examination.

MATERIALS AND METHODS

Six-hundred sixty three women 40 years of age or older were studied. The breast exam density was graded from 1 to 4 by two expert surgeons and the mammographic parenchymal density by two expert radiologists. Then for practical reasons, grades 1 and 2 were considered as low-density and grades 3 and 4 as high-density.

RESULTS

High and low densities were detected in 84.5% and 15.5% of clinical breast examinations and 59.7% and 40.3% of mammographies, respectively. The statistical analysis showed a significant difference between the breast tissue densities in breast examination with those in mammography.

CONCLUSIONS

A clinically dense breast does not necessarily imply a dense mammographic picture.