Shear-Wave Elastography: Could it be Helpful for the Diagnosis of Non-Mass-Like Breast Lesions?

The kinetic quantitative characteristics of non-mass breast lesions with contrast-enhanced ultrasound: a prospective study

OBJECTIVE

To characterize non-mass breast lesions (NML) quantitatively by contrast-enhanced ultrasound (CEUS) and to evaluate its additional diagnostic value based on the Breast Imaging Reporting and Data System (BI-RADS) categories.

METHODS

A prospective study was performed among consecutive patients with NMLs. All lesions were examined by grayscale ultrasound and CEUS and diagnosed on pathology. Standard mammograms were obtained in the patients over 30 years old. Three independent radiologists assessed the features on grayscale ultrasound and mammograms and classified NMLs according to BI-RADS categories. Combined with the quantitative analysis in CEUS, the BI-RADS categories were reassessed, and the sensitivity, specificity, positive-predictive value, negative-predictive value and area under the receiver operating characteristic curve (AUC) were calculated for the evaluation of the diagnostic performance.

RESULTS

30 benign and 24 malignant NMLs were finally enrolled in this study, with ductal carcinoma in situ being the majority of malignant (15/24). Average contrast signal intensity (AI), wash-in rate (WiR) and enhancement intensity at 40 s (I40) were found to be the most efficient kinetic parameters to diagnose malignant NMLs. Combined with the cut-off values of 205.2 for AI, 127.8 for WiR and 136.4 for I40, the diagnostic accuracy was improved (AUC = 0.904), with the sensitivity of 95.8% and the specificity of 70.0%.

CONCLUSION

The results suggested that hyperenhancement and rapid wash-in and wash-out are the characteristics of malignant NMLs. The kinetic analysis using CEUS can reflect hypervascular nature of malignant NMLs, thus improving the diagnostic performance combined with grayscale ultrasound.

ADVANCES IN KNOWLEDGE

In this study, we quantified the enhancement characteristics of non-mass breast lesions with CEUS. We revealed that the combination of CEUS and conventional ultrasound provided higher sensitivity for diagnosing malignant NMLs.

Comparison of the diagnostic value of contrast-enhanced ultrasound combined with conventional ultrasound versus magnetic resonance imaging in malignant non-mass breast lesions

OBJECTIVE

To compare the diagnostic value of contrast-enhanced ultrasound (CEUS)+conventional ultrasound vs MRI for malignant non-mass breast lesions (NMLs).

METHODS

A total of 109 NMLs detected by conventional ultrasound and examined by both CEUS and MRI were retrospectively analysed. The characteristics of NMLs in CEUS and MRI were noted, and agreement between the two modalities was analysed. Sensitivity, specificity, positive-predictive value (PPV), negative-predictive value (NPV), and area under the curve (AUC) of the two methods for diagnosing malignant NMLs were calculated in the overall sample and subgroups of different sizes(<10 mm, 10-20 mm, >20 mm).

RESULTS

A total of 66 NMLs detected by conventional ultrasound showed non-mass enhancement in MRI. Agreement between ultrasound and MRI was 60.6%. Probability of malignancy was higher when there was agreement between the two modalities. In the overall group, the sensitivity, specificity, PPV, and NPV of the two methods were 91.3%, 71.4%, 60%, 93.4% and 100%, 50.4%, 59.7%, 100%, respectively. The diagnostic performance of CEUS+conventional ultrasound was better than that of MRI (AUC: 0.825 vs 0.762, p = 0.043). The specificity of both methods decreased as lesion size increased, but sensitivity did not change. There was no significant difference between the AUCs of the two methods in the size subgroups (p > 0.05).

CONCLUSION

The diagnostic performance of CEUS+conventional ultrasound may be better than that of MRI for NMLs detected by conventional ultrasound. However, the specificity of both methods decrease significantly as lesion size increases.

ADVANCES IN KNOWLEDGE

This is the first study to compare the diagnostic performance of CEUS+conventional ultrasound vs that of MRI for malignant NMLs detected by conventional ultrasound. While CEUS+conventional ultrasound appears to be superior to MRI, subgroup analysis suggests that diagnostic performance is poorer for larger NMLs.

Diagnostic value of multimodal ultrasound strategies in the differentiation of non-mass-like breast lesions

PURPOSE

The study aims to assess the diagnostic performance of convention ultrasound (US), Angio PLUS microvascular US imaging (AP), and shear-wave elastography (SWE) in differentiating malignant and benign non-mass-like (NML) breast lesions.

METHODS

Sixty patients aged 21-70 years with 60 NML lesions were recruited. All patients were examined by conventional US, AP, and SWE. According to the pathological results, the performances of the multimodal US strategies were analyzed, while the diagnostic efficiency of AP and SWE in serial and parallel was also explored.

RESULTS

Age, together with posterior features, microcalcification, and architectural distortion were considered significant in evaluating NML lesions. The sensitivity, specificity, PPV, NPV, and accuracy of AP combined SWE in serial were 72.7, 96.3, 96.0, 74.3, and 83.3%, while those in parallel were 90.9, 63.0, 75.0, 85.0, and 78.3%, respectively. The two in serial indicated the highest specificity, PPV, accuracy, and AUC value, which could increase the true positive rate and reduce the chance of misdiagnosis, while the two in parallel exhibited the best sensitivity and NPV, which might serve as an effective tool to avoid excessive or nonessential biopsy.

CONCLUSION

The multimodal US strategies could provide precise and reliable diagnostic results for NML breast lesions.

Comparison of diagnostic potential of shear wave elastography between breast mass lesions and non-mass-like lesions

BACKGROUND

Shear wave elastography (SWE) can improve the specificity of B-mode ultrasound (US) without reducing the sensitivity for breast cancer diagnosis. Existing research on SWE includes both mass lesions and non‑mass‑like (NML) lesions or only NML lesions; however, there are no studies comparing the diagnostic potential of SWE in the detection of mass and NML lesions in the same trial.

OBJECTIVE

This study aimed to compare the diagnostic performance of SWE in detecting mass lesions and NML lesions and determine the different individualised thresholds of the SWE parameters according to the lesion type.

METHODS

This Study included 623 breast lesions of 562 consecutive women, who were scheduled for conventional US and SWE between January 2021 and December 2021. The diagnostic performances of conventional US and each quantitative SWE parameter (maximum elastic modulus [Emax], mean elastic modulus [Emean], and elastic modulus standard deviation [Esd]) were assessed. Histological diagnosis for all Breast Imaging Reporting and Database System (BI-RADS) category 4/5 patients and some BI-RADS category 3 patients and the follow-up results of other BI-RADS category 3 patients were used as the reference standard.

RESULTS

In this study, 281 benign lesions and 342 malignant lesions were identified. The diagnostic performance of conventional US and SWE was better in the mass lesion group than in the NML lesion group. Every SWE parameter had a different threshold in each group, and the thresholds of the SWE parameters were higher in the mass lesion group than in the NML lesion group. In the mass lesion group, Esd had the highest Az value, whereas in the NML lesion group, Emax had the highest Az value. In both the mass and NML lesion groups, the diagnostic specificity of the combination of conventional US and SWE was significantly higher than that of conventional US alone (P < 0.05), without a significantly decrease in the diagnosticsensitivity.

CONCLUSIONS

SWE could increase the confidence of breast ultrasound diagnosis, especially for NML lesions. NML lesions had lower thresholds of SWE parameters than did the mass lesions.

Ultrasound classification of non-mass breast lesions following BI-RADS presents high positive predictive value

PURPOSE

To investigate the positive predictive value of ultrasound classification of non-mass breast lesions (NMLs) following breast imaging reporting and data system (BI-RADS), and enhance understanding of NMLs.

MATERIALS AND METHODS

Fifty-nine women with 59 ultrasound-detected breast NMLs were finally enrolled. The ultrasound (US) features of breast NMLs were analyzed; the incidence of malignant NMLs was calculated; the malignancy risk stratification of US for breast NMLs was established using BI-RADS.

RESULTS

The incidence of malignant NMLs was 4.59% of all breast carcinoma. Non-ductal hypoechoic area, microcalcifications and posterior shadowing are the main US features of malignant NMLs, and there were significant differences between malignant and benign NMLs for microcalcifications and posterior shadowing. Taking BI-RADS 4B as a cutoff value, the sensitivity, specificity, area under the receiver operating characteristic curve (AUC), positive and negative predictive values, and odds ratio of the BI-RADS category were 82.98%,41.67%,0.62,84.78%,38.46% and 3.48, respectively.

CONCLUSIONS

Stratifying the malignancy risk of breast NMLs using the BI-RADS the sensitivity and positive and predictive value are promising, but the likelihood of malignancy of malignant NMLs is underestimated, and that of benign NMLs is overestimated. The solution may be that to separate NMLs from breast masses and use different malignancy risk stratification protocols.

Non-mass Breast Lesions: Could Multimodal Ultrasound Imaging Be Helpful for Their Diagnosis?

Objective: To develop a prediction model for discriminating malignant from benign breast non-mass-like lesions (NMLs) using conventional ultrasound (US), strain elastography (SE) of US elastography and contrast-enhanced ultrasound (CEUS). Methods: A total of 101 NMLs from 100 patients detected by conventional US were enrolled in this retrospective study. The characteristics of NMLs in conventional US, SE and CEUS were compared between malignant and benign NMLs. Histopathological results were used as the reference standard. Binary logistic regression analysis was performed to identify the independent risk factors. A multimodal method to evaluate NMLs based on logistic regression was developed. The diagnostic performance of conventional US, US + SE, US + CEUS and the combination of these modalities was evaluated and compared. Results: Among the 101 lesions, 50 (49.5%) were benign and 51 (50.5%) were malignant. Age ≥45 y, microcalcifications in the lesion, elasticity score >3, earlier enhancement time and hyper-enhancement were independent diagnostic indicators included to establish the multimodal prediction method. The area under the receiver operating characteristic curve (AUC) of US + SE + CEUS was significantly higher than that of US (p < 0.0001) and US + SE (p < 0.0001), but there was no significant difference between the AUC of US + SE + CEUS and the AUC of US + CEUS (p = 0.216). Conclusion: US + SE + CEUS and US + CEUS could significantly improve the diagnostic efficiency and accuracy of conventional US in the diagnosis of NMLs.

Diagnostic value of Doppler imaging for malignant non-mass breast lesions: with different diagnostic criteria for older and younger women: first results

OBJECTIVE

To evaluate and optimize the additional diagnostic value of Doppler imaging for malignant NMLs detected by US.

MATERIALS AND METHODS

The characteristics of 233 NMLs in Doppler imaging were analyzed, and different Adler grades of intralesional vessels were selected as the diagnostic cutoffs on Doppler imaging: grade 1 in the full cohort and in women < 40 years, and grade 0 in women ≥40 years. The diagnostic performance of US and US + Doppler imaging were calculated and compared with that of mammography.

RESULTS

The AUC of US + Doppler was larger than that of US alone in each group (P < 0.001). In the full cohort, addition of Doppler imaging increased specificity of US, but decreased sensitivity. However, by use of different diagnostic cutoffs in the two subgroups, it was possible to achieve high sensitivity and specificity simultaneously, which were 100% and 75.8% in women < 40 years, 94.7% and 69.5% in women ≥40 years, respectively. The AUC + Doppler was comparable to that of mammography in the full cohort and in women ≥40 years. In women < 40 years, the AUC of the combination was larger than that of mammography (P < 0.001).

CONCLUSION

Doppler imaging, with different Adler grades used as cutoffs in older versus younger women, can improve the specificity of US for the diagnosis of malignant NMLs without losing sensitivity. In younger women, US + Doppler imaging may be better than mammography.

Can shear wave elastography be utilized as an additional tool for the assessment of non-mass breast lesions?

INTRODUCTION

We aimed to describe shear wave elastography parameters of non-mass lesions of the breast and to assess the measures of diagnostic accuracy of shear wave elastography in the differentiation of non-mass lesions compared with conventional ultrasound, using histopathologic results as the reference standard.

METHODS

This retrospective study included breast ultrasound-detected non-mass lesions with a confirmed pathologic diagnosis during a two-year study period. B-mode ultrasound and shear wave elastography were performed for all lesions before biopsy. Ultrasound features, shear wave elastography parameters (mean elasticity and maximum stiffness color), as well as Breast Imaging-Reporting and Data System categories were recorded for each lesion. Measures of diagnostic accuracy of ultrasound and ultrasound + shear wave elastography were also assessed.

RESULTS

From a total of 567 breast lesions requiring core-needle biopsy, 49 (8.6%) were considered as non-mass lesions. Based on histopathologic reports, 32 patients (65.3%) had non-high-risk benign lesions, five (10.2%) had high-risk benign lesions, five (10.2%) had ductal carcinoma in situ, and seven (14.3%) had invasive carcinoma. There was no significant difference in patients' age and palpability between benign and malignant lesions (p = 0.16 and p = 0.12, respectively). Mean elasticity values and Breast Imaging-Reporting and Data System categories were significantly higher among malignant lesions compared with benign non-mass lesions (both p < 0.001). Furthermore, the addition of shear wave elastography to grayscale ultrasound increased the specificity, positive predictive value, and diagnostic accuracy.

CONCLUSION

The complementary use of shear wave elastography with conventional ultrasound might help in the differentiation of non-mass breast lesions and has the potential to decrease the frequency of unnecessary biopsies performed for benign non-mass lesions.

Diagnostic performance of elastography for breast non-mass lesions: A systematic review and meta-analysis

PURPOSE

This systematic review and meta-analysis aimed to evaluate the diagnostic performance of ultrasound elastography in the differentiation of benign and malignant breast non-mass lesions (NMLs).

METHODS

PubMed, Cochrane Library, and Embase databases were searched for eligible studies up to end of June 2021. The diagnostic performance of elastography for NMLs was investigated using pooled sensitivity and specificity, likelihood ratio, diagnostic odds ratio (DOR), post-test probability, and the area under hierarchical summary receiver operating characteristic curve (HSROC).

RESULTS

Eleven studies involving 812 NMLs (malignant 414) were included. The pooled sensitivity, specificity, DOR, positive likelihood ratio, and negative likelihood of elastography for the differentiation of benign and malignant breast NMLs were 79% (95 %CI: 71-85), 86% (95 %CI: 79-91), 23.32 (95 %CI: 13.38-40.66), 5.67 (95 %CI: 3.79-8.47), and 0.24 (95 %CI: 0.17-0.34), respectively. No significant publication bias existed. The area under the HSROC curve was 90% (95 %CI: 87-92). Fagan plots demonstrated good clinical utility. However, substantial heterogeneity existed. Country, measurement index, and number of lesions served as potential sources of heterogeneity.

CONCLUSIONS

The results of this study suggest that elastography has high diagnostic accuracy in differentiating between malignant and benign NMLs. Elastography can be a feasible and non-invasive tool for breast NMLs.

3-D Res-CapsNet convolutional neural network on automated breast ultrasound tumor diagnosis

PURPOSE

We propose a 3-D tumor computer-aided diagnosis (CADx) system with U-net and a residual-capsule neural network (Res-CapsNet) for ABUS images and provide a reference for early tumor diagnosis, especially non-mass lesions.

METHODS

A total of 396 patients with 444 tumors (226 malignant and 218 benign) were retrospectively enrolled from Sun Yat-sen University Cancer Center. In our CADx, preprocessing was performed first to crop and resize the tumor volumes of interest (VOIs). Then, a 3-D U-net and postprocessing were applied to the VOIs to obtain tumor masks. Finally, a 3-D Res-CapsNet classification model was executed with the VOIs and the corresponding masks to diagnose the tumors. Finally, the diagnostic performance, including accuracy, sensitivity, specificity, and area under the curve (AUC), was compared with other classification models and among three readers with different years of experience in ABUS review.

RESULTS

For all tumors, the accuracy, sensitivity, specificity, and AUC of the proposed CADx were 84.9 %, 87.2 %, 82.6 %, and 0.9122, respectively, outperforming other models and junior reader. Next, the tumors were subdivided into mass and non-mass tumors to validate the system performance. For mass tumors, our CADx achieved an accuracy, sensitivity, specificity, and AUC of 85.2 %, 88.2 %, 82.3 %, and 0.9147, respectively, which was higher than that of other models and junior reader. For non-mass tumors, our CADx achieved an accuracy, sensitivity, specificity, and AUC of 81.6 %, 78.3 %, 86.7 %, and 0.8654, respectively, outperforming the two readers.

CONCLUSION

The proposed CADx with 3-D U-net and 3-D Res-CapsNet models has the potential to reduce misdiagnosis, especially for non-mass lesions.

The role of contrast-enhanced ultrasound in the diagnosis of malignant non-mass breast lesions and exploration of diagnostic criteria

OBJECTIVES

To assess the value of contrast-enhanced ultrasound (CEUS) for diagnosing malignant non-mass breast lesions (NMLs) and to explore the CEUS diagnostic criteria.

METHODS

A total of 116 patients with 119 NMLs detected by conventional US were enrolled. Histopathological results were used as the reference standard. The enhancement characteristics of NMLs in CEUS were compared between malignant and benign NMLs. The CEUS diagnostic criteria for malignant NMLs were established using independent diagnostic indicators identified by binary logistic regression analysis. The diagnostic performance of Breast Imaging Reporting and Data System-US (BI-RADS-US), CEUS, and BI-RADS-US combined with CEUS was evaluated and compared.

RESULTS

Histopathological results showed 63 and 56 benign and malignant NMLs. Enhancement degree (OR = 5.75, p = 0.003), enhancement area (OR = 4.25, p = 0.005), and radial or penetrating vessels (OR = 7.54, p = 0.003) were independent diagnostic indicators included to establish the CEUS diagnostic criteria. The sensitivity and specificity of BI-RADS-US, CEUS, and BI-RADS-US combined with CEUS were 100 and 30.2%, 80.4 and 74.6%, and 94.6 and 77.8%, respectively; the corresponding areas under the receiver operating characteristic curve (AUC) were 0.819, 0.775, and 0.885, respectively.

CONCLUSIONS

CEUS has a high specificity in malignant NML diagnosis based on the diagnostic criteria including enhancement degree, enhancement area, and radial or penetrating vessels, but with lower sensitivity than BI-RADS-US. The combination of CEUS and BI-RADS-US is an effective diagnostic tool with both high sensitivity and specificity for the diagnosis of malignant NMLs.

ADVANCES IN KNOWLEDGE

In this study, we assessed the diagnostic value of CEUS for malignant NMLs and constructed a feasible diagnostic criterion. We further revealed that the combination of CEUS and BI-RADS-US has a high diagnostic value for malignant NMLs.

Ultrasonographic features of ductal carcinoma in situ: analysis of 219 lesions

Background

The purpose of this paper is to clarify the ultrasonographic features and classification of ductal carcinoma in situ (DCIS), and to evaluate the ability of ultrasonography in the prediction of DCIS.

Methods

The clinical data, gray-scale ultrasound images and pathological results of 219 DCIS lesions that detected in 203 consecutive patients who underwent ultrasonography and surgery in our hospital from January 1, 2014 to December 31, 2019 were collected retrospectively. Ultrasonographic features and classification of DCIS were summarized, and the accuracy of ultrasonography in predicting different ultrasonographic findings of DCIS were compared.

Results

Among the 219 DCIS lesions, 91 (41.6%) presented as mass-like lesions and 128 (58.4%) were non-mass-like lesions. For the 91 mass-like DCIS lesions, 79 were hypoechoic solid masses, 12 were cystic-solid structures. For the 128 non-mass-like DCIS lesions, 114 were hypoechoic areas, 10 were ductal dilatation accompanied with intraductal solid components, and 4 were multiple punctate echogenic foci only. The diagnostic accuracy of ultrasound for the 219 DCIS lesions was 81.7% (179/219). The diagnostic accuracy of mass-like DCIS lesions was 90.1% (82/91), which was significantly higher than that in non-mass-like DCIS lesions [75.8% (97/128), P=0.007]. The diagnostic accuracy of hypoechoic solid masses was significantly higher than those of the other ultrasonographic findings (P=0.002). Ducts abnormalities were detected in 45 (20.5%) lesions and punctate echogenic foci in 134 (61.2%) lesions. The diagnostic accuracy of lesions with ducts abnormalities was 93.3% (42/45), which was significantly higher than that in lesions without ducts abnormalities [78.7% (137/174), P=0.024]. The diagnostic accuracy of lesions with punctate echogenic foci was 92.5% (124/134), which was significantly higher than that in lesions without punctate echogenic foci [64.7% (55/85), P=0.000].

Conclusions

DCIS lesions can effectively be recognized as mass-like lesions and non-mass-like lesions by ultrasound. Hypoechoic areas and hypoechoic solid masses were the most common ultrasonographic features of DCIS. Ducts abnormalities and punctate echogenic foci were helpful for the diagnosis of DCIS.

Evaluation of internal and shell stiffness in the differential diagnosis of breast non-mass lesions by shear wave elastography

BACKGROUND

The diagnostic specificity of conventional ultrasound for breast non-mass lesions (NMLs) is low at approximately 21%-43%. Shear wave elastography (SWE) can distinguish benign from malignant lesions by evaluating the internal and peripheral stiffness. SWE has good reproducibility and high diagnostic efficacy. However, there are very few independent studies on the diagnostic value of SWE in breast NMLs.

AIM

To determine the value of SWE in the differential diagnosis of breast NMLs.

METHODS

This study enrolled a total of 118 patients with breast NMLs who underwent SWE examinations in the Beijing Shijitan Hospital Affiliated to Capital Medical University and The Second Hospital of Shandong University from January 2019 to January 2020. The internal elastic parameters of the lesions were recorded, including maximum (Emax), mean (Emean) and minimum elastic values and the standard deviation. The following peripheral parameters were noted: Presence of a “stiff rim” sign; Emax, and Emean elasticity values within 1 mm, 1.5 mm, 2 mm, 2.5 mm and 3 mm from the edge of NMLs. The receiver operating characteristic curve of each parameter was drawn, and the areas under the curve were calculated.

RESULTS

Emax, Emean and elastic values, and the standard deviation of the internal elastic values in malignant NMLs were significantly higher than those in benign NMLs (P < 0.05). The percentage with the “stiff rim” sign in malignant NMLs was significantly higher than that in the benign group (P < 0.05), and Emax and Emean at the shell of 1 mm, 1.5 mm, 2 mm, 2.5 mm and 3 mm in the malignant group were all higher than those in the benign group (P < 0.05). Of the surrounding elasticity values, Emax of the shell at 2.5 mm in malignant NMLs had maximum areas under the curve of 0.900, and the corresponding sensitivity and specificity were 94.57% and 85.86%, respectively.

CONCLUSION

The “stiff rim” sign and multiple quantitative elastic values within and around the lesion had good diagnostic performance in the differential diagnosis of breast NMLs. Emax in peripheral tissue had better diagnostic efficiency than other parameters.

Real-time ultrasound elastographic evaluation of extraocular muscle involvement in Graves' ophthalmopathy

Purpose: To evaluate the affected extraocular muscles (EOMs) of patients with Graves' ophthalmopathy (GO) using real-time ultrasound elastography (UE) and to compare these results with those of healthy subjects.Methods: This prospective, comparative case series included 70 eyes of 35 patients with moderate-to-severe GO with type 2 orbitopathy (myogenic variant) according to their computed tomography (CT) scans. Forty-six eyes of 23 healthy subjects were evaluated as the control group. The strain ratio of orbital fat to medial rectus was calculated as the ratio of the medial rectus to orbital fat tissue, and the strain ratio of orbital fat to lateral rectus was calculated as the ratio of lateral rectus to orbital fat tissue.Results: The strain ratio of orbital fat to medial rectus was 3.03 ± 1.25 (range: 1.05-5.07) in the GO group, and 0.54 ± 0.20 (range: 0.14-1.08) in the control group (p = .0001). The strain ratio of orbital fat to lateral rectus was 0.97 ± 0.29 (range: 0.56-1.55) in the GO group, and 0.63 ± 0.23 (range: 0.18-1.09) in the control group (p = .0001).Conclusion: By using real-time UE, we found the medial and the lateral recti of GO patients to be stiffer compared to those of healthy subjects.

Sonographic Features of Flat Epithelial Atypia Manifesting as a Non-Mass-Like Lesion: A Case Report

Patient: Female, 47

Final Diagnosis: Flat epithelial atypia of the breast

Symptoms: —

Medication: —

Clinical Procedure: —

Specialty: Radiology

Machine learning for medical ultrasound: status, methods, and future opportunities

Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant challenges and opportunities. Challenges include high inter- and intra-operator variability and limited image quality control. Tremendous opportunities have arisen in the last decade as a result of exponential growth in available computational power coupled with progressive miniaturization of US devices. As US devices become smaller, enhanced computational capability can contribute significantly to decreasing variability through advanced image processing. In this paper, we review leading machine learning (ML) approaches and research directions in US, with an emphasis on recent ML advances. We also present our outlook on future opportunities for ML techniques to further improve clinical workflow and US-based disease diagnosis and characterization.