Diagnostic value of qualitative and quantitative enhancement parameters on contrast-enhanced mammography

PURPOSE

To determine whether qualitative and quantitative enhancement parameters obtained from contrast-enhanced mammography (CEM) can be used in predicting malignancy.

METHODS

After review board approval, consecutive 136 suspicious lesions with definite diagnosis were retrospectively analyzed on CEM. Acquisition was routinely started with craniocaudal view and ended with mediolateral oblique view of the affected breast. Lesion conspicuity (low, moderate, high), internal enhancement pattern (homogeneous, heterogeneous, rim), contrast-to-noise ratio (CNR), percentage of signal difference (PSD) and relative enhancement from early to late view were analyzed. PSD and relative enhancements were used to determine patterns of descending, steady or ascending enhancements. Receiver operating characteristic analysis, Cohen's kappa statistics and Spearman correlation tests were used.

RESULTS

There were 29 benign and 107 malignant lesions. 64% of the malignant lesions exhibited high conspicuity compared to 14% of the benign lesions (P < 0.001). CNR values were higher in malignant lesions compared to benign ones (P ≤ 0.004). CNR from early view yielded 82% sensitivity, 72% specificity and PSD yielded 79% sensitivity, 65% specificity. Descending pattern and rim enhancement observed in 44% and 21% of breast cancers, respectively, and both provided 96% positive predictive value for malignancy.

CONCLUSION

Diagnostic accuracy of quantitative parameters was higher than that of qualitative parameters. High CNR, rim enhancement, and descending pattern were features commonly seen in malignant lesions, while low CNR, homogeneous enhancement, and ascending pattern were commonly seen in benign lesions.

Breast Cancer Screening and BI-RADS Scoring Trends Before and During the COVID-19 Pandemic in an Academic Safety-Net Hospital

BACKGROUND

Little is known about how the COVID-19 pandemic affected screening mammography rates and Breast Imaging Reporting and Data Systems (BI-RADS) categorizations within populations facing social and economic inequities. Our study seeks to compare trends in breast cancer screening and BI-RADS assessments in an academic safety-net patient population before and during the COVID-19 pandemic.

PATIENTS AND METHODS

Our single-center retrospective study evaluated women ≥ 18 years old with no known breast cancer diagnosis who received breast cancer screening from March 2019-September 2020. The screening BI-RADS score, completion of recommended diagnostic imaging, and diagnostic BI-RADS scores were compared between the pre-COVID-19 era (from 1 March 2019 to 19 March 2020) and COVID-19 era (from 20 March 2020 to 30 September 2020).

RESULTS

Among the 11,798 patients identified, screened patients were younger (median age 57 versus 59 years, p < 0.001) and more likely covered by private insurance (35.9% versus 32.3%, p < 0.001) during the COVID-19 era compared with the pre-COVID-19 era. During the pandemic, there was an increase in screening mammograms categorized as BI-RADS 0 compared with the pre-COVID-19 era (20% versus 14.5%, p < 0.0001). There was no statistically significant difference in rates of completion of diagnostic imaging (81.6% versus 85.4%, p = 0.764) or assignment of suspicious BI-RADS scores (BI-RADS 4-5; 79.9% versus 80.8%, p = 0.762) between the two eras.

CONCLUSIONS

Although more patients were recommended to undergo diagnostic imaging during the pandemic, there were no significant differences in race, completion of diagnostic imaging, or proportions of mammograms categorized as suspicious between the two time periods. These findings likely reflect efforts to maintain equitable care among diverse racial groups served by our safety-net hospital.

Predictive value of contrast-enhanced ultrasonography and ultrasound elastography for management of BI-RADS category 4 nonpalpable breast masses

PURPOSE

The objective of this study was to investigate the independent risk factors and associated predictive values of contrast-enhanced ultrasound (CEUS), shear wave elastography (SWE), and strain elastography (SE) for high-risk lesions (HRL) and malignant tumors (MT) among nonpalpable breast masses classified as BI-RADS category 4 on conventional ultrasound.

METHODS

This prospective study involved consecutively admitted patients with breast tumors from January 2018, aiming to explore the management of BI-RADS category 4 breast tumors using CEUS and elastography. We conducted a retrospective review of patient data, focusing on those with a history of a nonpalpable mass as the primary complaint. Pathologic findings after surgical resection served as the gold standard. The CEUS arterial-phase indices were analyzed using contrast agent arrival-time parametric imaging processing mode, while quantitative and qualitative indices were examined on ES images. Independent risk factors were identified through binary logistic regression multifactorial analysis. The predictive efficacy of different modalities was compared using a receiver operating characteristics curve. Subsequently, a nomogram for predicting the risk of HRL/MT was established based on a multifactorial logistic regression model.

RESULTS

A total of 146 breast masses from 146 patients were included, comprising 80 benign tumors, 12 HRLs, and 54 MTs based on the final pathology. There was no significant difference in pathologic size between the benign and HRL/MT groups [8.00(6.25,10.00) vs. 9.00(6.00,10.00), P = 0.506]. The diagnostic efficacy of US plus CEUS exceeded that of US plus SWE/SE for BI-RADS 4 nonpalpable masses, with an AUC of 0.954 compared to 0.798/0.741 (P ＜ 0.001). Further stratified analysis revealed a more pronounced improvement for reclassification of BI-RADS 4a masses (AUC: 0.943 vs. 0.762/0.675, P ＜ 0.001) than BI-RADS 4b (AUC:0.950 vs. 0.885/0.796, P＞0.05) with the assistance of CEUS than SWE/SE. Employing downgrade CEUS strategies resulted in negative predictive values ranging from 95.2 % to 100.0 % for BI-RADS 4a and 4b masses. Conversely, using upgrade nomogram strategies, which included the independent predictive risk factors of irregular enhanced shape, poor defined enhanced margin, earlier enhanced time, increased surrounding vessels, and presence of contrast agent retention, the diagnostic performance achieved an AUC of 0.947 with good calibration.

CONCLUSION

After investigating the potential of CEUS and ES in improving risk assessment and diagnostic accuracy for nonpalpable BI-RADS category 4 breast masses, it is evident that CEUS has a more significant impact on enhancing classification compared to ES, particularly for BI-RADS 4a subgroup masses. This finding suggests that CEUS may offer greater benefits in improving risk assessment and diagnostic accuracy for this specific subgroup of breast masses.

Using Patient Navigation to Reduce Time to Diagnosis of Breast Cancer in Uganda

PURPOSE

The Ugandan Ministry of Health adopted BI-RADS as standard of care in 2016. The authors performed a medical audit of breast ultrasound practices at four tertiary-level hospitals to assess interpretive performance. The authors also determined the effect of a low-cost navigation program linking breast imaging and pathology on the percentage of patients completing diagnostic care.

METHODS

The authors retrieved 966 consecutive diagnostic breast ultrasound reports, with complete data, for studies performed on women aged >18 years presenting with symptoms of breast cancer between 2018 and 2020 from participating hospitals. Ultrasound results were linked to tumor registries and patient follow-up. A medical audit was performed according to the ACR's BI-RADS Atlas, fifth edition, and results were compared with those of a prior audit performed in 2013. At Mulago Hospital, an intervention was piloted on the basis of patient navigation, cost sharing, and same-day imaging, tissue sampling, and pathology.

RESULTS

In total, 888 breast ultrasound examinations (91.9%) were eligible for inclusion. Compared with 2013, the postintervention cancer detection rate increased from 38 to 148.7 cancers per 1,000 examinations, positive predictive value 2 from 29.6% to 48.9%, and positive predictive value 3 from 62.7% to 79.9%. Specificity decreased from 90.5% to 87.7% and sensitivity from 92.3% to 81.1%. The mean time from tissue sampling to receipt of a diagnosis decreased from 60 to 7 days. The intervention increased the percentage of patients completing diagnostic care from 0% to 100%.

CONCLUSIONS

Efforts to establish a culture of continuous quality improvement in breast ultrasound require robust data collection that links imaging results to pathology and patient follow-up. Interpretive performance met BI-RADS benchmarks for palpable masses, except sensitivity. This resource-appropriate strategy linking imaging, tissue sampling, and pathology interpretation decreased time to diagnosis and rates of loss to follow-up and improved the precision of the audit.

MRI Insights in Breast Imaging

In the world, breast cancer is the most commonly diagnosed cancer among women. Currently, MRI is the most sensitive breast imaging method for detecting breast cancer, although false positive rates are still an issue. To date, the accuracy of breast MRI is widely recognized across various clinical scenarios, in particular, staging of known cancer, screening for breast cancer in high-risk women, and evaluation of response to neoadjuvant chemotherapy. Since technical development and further clinical indications have expanded over recent years, dedicated breast radiologists need to constantly update their knowledge and expertise to remain confident and maintain high levels of diagnostic performance in breast MRI. This review aims to detail current and future applications of breast MRI, from technological requirements and advances to new multiparametric and abbreviated protocols, and ultrafast imaging, as well as current and future indications.

Combining Potential Strain Elastography and Radiomics for Diagnosing Breast Lesions in BI-RADS 4: Construction and Validation a Predictive Nomogram

RATIONALE AND OBJECTIVES

To develop a nomogram by integrating B-mode ultrasound (US), strain ratio (SR), and radiomics signature (RS) effectively differentiating between benign and malignant lesions in the Breast Imaging Reporting and Data System (BI-RADS) 4.

MATERIALS AND METHODS

We retrospectively recruited 709 consecutive patients who were assigned a BI-RADS 4 and underwent curative resection or biopsy between 2017 and 2022. US images were collected before surgery. A RS was developed through a multistep feature selection and construction process. Histology findings served as the gold standard. Univariate and multivariate regression analysis were employed to analyze the clinical and US characteristics and identify variables for developing a nomogram. The calibration and discrimination of the nomogram were conducted to evaluate its performance.

RESULTS

The study included a total of 709 patients, with 497 in the training set and 212 in the validation set. In the training set, the B-mode US had an AUC of 0.84 (95% confidence interval [CI], 0.80, 0.87). The SR demonstrated an AUC of 0.78 (95% CI, 0.74, 0.82), while the RS showed an AUC of 0.85 (95% CI, 0.81, 0.88). Notably, the nomogram exhibited superior performance compared to the conventional US, SR, and RS (AUC=0.93, both p < 0.05, as per the Delong test). The clinical usefulness of the nomogram was favorable.

CONCLUSION

The calibrated nomogram can be specifically designed to predict the malignancy of breast lesions in the BI-RADS 4 category.

Beyond BI-RADS: Nonmass Abnormalities on Breast Ultrasound

Abnormalities on breast ultrasound (US) images which do not meet the criteria for masses are referred to as nonmass lesions. These features and outcomes have been investigated in several studies conducted by Asian researchers. However, the term "nonmass" is not included in the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) 5th edition for US. According to the Japan Association of Breast and Thyroid Sonology guidelines, breast lesions are divided into mass and nonmass. US findings of nonmass abnormalities are classified into five subtypes: abnormalities of the ducts, hypoechoic areas in the mammary glands, architectural distortion, multiple small cysts, and echogenic foci without a hypoechoic area. These findings can be benign or malignant; however, focal or segmental distributions and presence of calcifications suggest malignancy. Intraductal, invasive ductal, and lobular carcinomas can present as nonmass abnormalities. For the nonmass concept to be included in the next BI-RADS and be widely accepted in clinical practice, standardized terminologies, an interpretation algorithm, and outcome-based evidence are required for both screening and diagnostic US.

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.

Subcategorization of suspicious non-mass-like enhancement lesions(BI-RADS-MRI Category4)

BACKGROUND

This study aims to providing a reliable method that has good compliance and is easy to master to improve the accuracy of NMLE diagnosis.

METHODS

This study retrospectively analyzed 122 cases of breast non-mass-like enhancement (NMLE) lesions confirmed by postoperative histology. MRI features and clinical features of benign and malignant non-mass enhancement breast lesions were compared by using independent sample t test, χ2test and Fisher exact test. P < 0.05 was considered statistically significant. Statistically significant parameters were then included in logistic regression analysis to build a multiparameter differential diagnosis modelto subdivide the BI-RADS Category 4.

RESULTS

The distribution (odds ratio (OR) = 8.70), internal enhancement pattern (OR = 6.29), ADC value (OR = 5.56), and vascular sign (OR = 2.84) of the lesions were closely related to the benignity and malignancy of the lesions. These signs were used to build the MRI multiparameter model for differentiating benign and malignant non-mass enhancement breast lesions. ROC analysis revealed that its optimal diagnostic cut-off value was 5. The diagnostic specificity and sensitivity were 87.01% and 82.22%, respectively. Lesions with 1-6 points were considered BI-RADS category 4 lesions, and the positive predictive values of subtypes 4a, 4b, and 4c lesions were15.79%, 31.25%, and 77.78%, respectively.

CONCLUSIONS

Comprehensively analyzing the features of MRI of non-mass enhancement breast lesions and building the multiparameter differential diagnosis model could improve the differential diagnostic performance of benign and malignant lesions.

Prospective assessment of breast lesions AI classification model based on ultrasound dynamic videos and ACR BI-RADS characteristics

Introduction

AI-assisted ultrasound diagnosis is considered a fast and accurate new method that can reduce the subjective and experience-dependent nature of handheld ultrasound. In order to meet clinical diagnostic needs better, we first proposed a breast lesions AI classification model based on ultrasound dynamic videos and ACR BI-RADS characteristics (hereafter, Auto BI-RADS). In this study, we prospectively verify its performance.

Methods

In this study, the model development was based on retrospective data including 480 ultrasound dynamic videos equivalent to 18122 static images of pathologically proven breast lesions from 420 patients. A total of 292 breast lesions ultrasound dynamic videos from the internal and external hospital were prospectively tested by Auto BI-RADS. The performance of Auto BI-RADS was compared with both experienced and junior radiologists using the DeLong method, Kappa test, and McNemar test.

Results

The Auto BI-RADS achieved an accuracy, sensitivity, and specificity of 0.87, 0.93, and 0.81, respectively. The consistency of the BI-RADS category between Auto BI-RADS and the experienced group (Kappa:0.82) was higher than that of the juniors (Kappa:0.60). The consistency rates between Auto BI-RADS and the experienced group were higher than those between Auto BI-RADS and the junior group for shape (93% vs. 80%; P = .01), orientation (90% vs. 84%; P = .02), margin (84% vs. 71%; P = .01), echo pattern (69% vs. 56%; P = .001) and posterior features (76% vs. 71%; P = .0046), While the difference of calcification was not significantly different.

Discussion

In this study, we aimed to prospectively verify a novel AI tool based on ultrasound dynamic videos and ACR BI-RADS characteristics. The prospective assessment suggested that the AI tool not only meets the clinical needs better but also reaches the diagnostic efficiency of experienced radiologists.

Impact of Imaging Biomarkers and AI on Breast Cancer Management: A Brief Review

Breast cancer stands out as the most frequently identified malignancy, ranking as the fifth leading cause of global cancer-related deaths. The American College of Radiology (ACR) introduced the Breast Imaging Reporting and Data System (BI-RADS) as a standard terminology facilitating communication between radiologists and clinicians; however, an update is now imperative to encompass the latest imaging modalities developed subsequent to the 5th edition of BI-RADS. Within this review article, we provide a concise history of BI-RADS, delve into advanced mammography techniques, ultrasonography (US), magnetic resonance imaging (MRI), PET/CT images, and microwave breast imaging, and subsequently furnish comprehensive, updated insights into Molecular Breast Imaging (MBI), diagnostic imaging biomarkers, and the assessment of treatment responses. This endeavor aims to enhance radiologists' proficiency in catering to the personalized needs of breast cancer patients. Lastly, we explore the augmented benefits of artificial intelligence (AI), machine learning (ML), and deep learning (DL) applications in segmenting, detecting, and diagnosing breast cancer, as well as the early prediction of the response of tumors to neoadjuvant chemotherapy (NAC). By assimilating state-of-the-art computer algorithms capable of deciphering intricate imaging data and aiding radiologists in rendering precise and effective diagnoses, AI has profoundly revolutionized the landscape of breast cancer radiology. Its vast potential holds the promise of bolstering radiologists' capabilities and ameliorating patient outcomes in the realm of breast cancer management.

A comparative study on the features of breast sclerosing adenosis and invasive ductal carcinoma via ultrasound and establishment of a predictive nomogram

Objective

To analyze the clinical and ultrasonic characteristics of breast sclerosing adenosis (SA) and invasive ductal carcinoma (IDC), and construct a predictive nomogram for SA.

Materials and methods

A total of 865 patients were recruited at the Second Hospital of Shandong University from January 2016 to November 2022. All patients underwent routine breast ultrasound examinations before surgery, and the diagnosis was confirmed by histopathological examination following the operation. Ultrasonic features were recorded using the Breast Imaging Data and Reporting System (BI-RADS). Of the 865 patients, 203 (252 nodules) were diagnosed as SA and 662 (731 nodules) as IDC. They were randomly divided into a training set and a validation set at a ratio of 6:4. Lastly, the difference in clinical characteristics and ultrasonic features were comparatively analyzed.

Result

There was a statistically significant difference in multiple clinical and ultrasonic features between SA and IDC (P<0.05). As age and lesion size increased, the probability of SA significantly decreased, with a cut-off value of 36 years old and 10 mm, respectively. In the logistic regression analysis of the training set, age, nodule size, menopausal status, clinical symptoms, palpability of lesions, margins, internal echo, color Doppler flow imaging (CDFI) grading, and resistance index (RI) were statistically significant (P<0.05). These indicators were included in the static and dynamic nomogram model, which showed high predictive performance, calibration and clinical value in both the training and validation sets.

Conclusion

SA should be suspected in asymptomatic young women, especially those younger than 36 years of age, who present with small-size lesions (especially less than 10 mm) with distinct margins, homogeneous internal echo, and lack of blood supply. The nomogram model can provide a more convenient tool for clinicians.

Combining b2500 diffusion-weighted imaging with BI-RADS improves the specificity of breast MRI

PURPOSE

The purpose of this study was to evaluate the diagnostic performance of visual assessment of diffusion-weighted images (DWI) obtained with a b value of 2500 s/mm2 in addition to a conventional magnetic resonance imaging (MRI) protocol to characterize breast lesions.

MATERIALS AND METHODS

This single-institution retrospective study included participants who underwent clinically indicated breast MRI and breast biopsy from May 2017 to February 2020. The examination included a conventional MRI protocol including DWI obtained with a b value of 50 s/mm2 (b50DWI) and a b value of 800 s/mm2 (b800DWI) and DWI obtained with a b value of 2500 s/mm2 (b2500DWI). Lesions were classified using Breast Imaging Reporting and Data Systems (BI-RADS) categories. Three independent radiologists assessed qualitatively the signal intensity within the breast lesions relative to breast parenchyma on b2500DW and b800DWI and measured the b50-b800-derived apparent diffusion coefficient (ADC) value. The diagnostic performances of BI-RADS, b2500DWI, b800DWI, ADC and of a model combining b2500DWI and BI-RADS were evaluated using receiver operating characteristic (ROC) curves analysis.

RESULTS

A total of 260 patients with 212 malignant and 100 benign breast lesions were included. There were 259 women and one man with a median age of 53 years (Q1, Q3: 48, 66 years). b2500DWI was assessable in 97% of the lesions. Interobserver agreement for b2500DWI was substantial (Fleiss kappa = 0.77). b2500DWI yielded larger area under the ROC curve (AUC, 0.81) than ADC with a 1 × 10-3 mm2/s threshold (AUC, 0.58; P = 0.005) and than b800DWI (AUC, 0.57; P = 0.02). The AUC of the model combining b2500DWI and BI-RADS was 0.84 (95% CI: 0.79-0.88). Adding b2500DWI to BI-RADS resulted in a significant increase in specificity from 25% (95% CI: 17-35) to 73% (95% CI: 63-81) (P < 0.001) with a decrease in sensitivity from 100% (95% CI: 97-100) to 94% (95% CI: 90-97), (P < 0.001).

CONCLUSION

Visual assessment of b2500DWI has substantial interobserver agreement. Visual assessment of b2500DWI offers better diagnostic performance than ADC and b800DWI. Adding visual assessment of b2500DWI to BI-RADS improves the specificity of breast MRI and could avoid unnecessary biopsies.

Knowledge Tensor-Aided Breast Ultrasound Image Assistant Inference Framework

Breast cancer is one of the most prevalent cancers in women nowadays, and medical intervention at an early stage of cancer can significantly improve the prognosis of patients. Breast ultrasound (BUS) is a widely used tool for the early screening of breast cancer in primary care hospitals but it relies heavily on the ability and experience of physicians. Accordingly, we propose a knowledge tensor-based Breast Imaging Reporting and Data System (BI-RADS)-score-assisted generalized inference model, which uses the BI-RADS score of senior physicians as the gold standard to construct a knowledge tensor model to infer the benignity and malignancy of breast tumors and axes the diagnostic results against those of junior physicians to provide an aid for breast ultrasound diagnosis. The experimental results showed that the diagnostic AUC of the knowledge tensor constructed using the BI-RADS characteristics labeled by senior radiologists achieved 0.983 (95% confidential interval (CI) = 0.975-0.992) for benign and malignant breast cancer, while the diagnostic performance of the knowledge tensor constructed using the BI-RADS characteristics labeled by junior radiologists was only 0.849 (95% CI = 0.823-0.876). With the knowledge tensor fusion, the AUC is improved to 0.887 (95% CI = 0.864-0.909). Therefore, our proposed knowledge tensor can effectively help reduce the misclassification of BI-RADS characteristics by senior radiologists and, thus, improve the diagnostic performance of breast-ultrasound-assisted diagnosis.

Magnetic resonance imaging diagnosis of non-mass enhancement of the breast

Breast Imaging Reporting and Data System magnetic resonance imaging (BI-RADS-MRI) classifies lesions as mass, non-mass enhancement (NME), or focus. BI-RADS ultrasound does not currently have the concept of non-mass. Additionally, knowing the concept of NME in MRI is significant. Thus, this study aimed to provide a narrative review of NME diagnosis in breast MRI. Lexicons are defined with distribution (focal, linear, segmental, regional, multiple regions, and diffuse) and internal enhancement patterns (homogenous, heterogeneous, clumped, and clustered ring) in the case of NME. Among these, linear, segmental, clumped, clustered ring, and heterogeneous are the terms that suggest malignancy. Hence, a hand search was conducted for reports of malignancy frequencies. The malignancy frequency in NME is widely distributed, ranging from 25 to 83.6%, and the frequency of each finding varies. Latest techniques, such as diffusion-weighted imaging and ultrafast dynamic MRI, are attempted to differentiate NME. Additionally, attempts are made in the preoperative setting to determine the concordance of lesion spread based on findings and the presence of invasion.

Non-mass lesions on breast ultrasound: why does not the ACR BI-RADS breast ultrasound lexicon add the terminology?

The definition of a non-mass lesion on breast ultrasound (US) is designed for everyday practice to provide unambiguous clinical management and to assist physicians and sonographers as they interpret breast US images. The field of breast imaging research requires consistent and standardized terminology for non-mass lesions identified on breast US, especially when differentiating benign from malignant lesions. Physicians and sonographers should be aware of the benefits and limitations of the terminology and use them precisely. I am hopeful that the next edition of the Breast Imaging Reporting and Data System (BI-RADS) lexicon will include standardized terminology for describing non-mass lesions detected on breast US.

The value of MRI for downgrading of breast suspicious lesions detected on ultrasound

BACKGROUND

Most of suspicious lesions classified as breast imaging reporting and data system (BI-RADS) 4A and 4B categories on ultrasound (US) were benign, resulting in unnecessary biopsies. MRI has a high sensitivity to detect breast cancer and high negative predictive value (NPV) to exclude malignancy. The purpose of this study was to investigate the value of breast MRI for downgrading of suspicious lesions with BI-RADS 4A and 4B categories on US.

METHODS

Patients who underwent breast MRI for suspicious lesions classified as 4A and 4B categories were included in this retrospective study. Two radiologists were aware of the details of suspicious lesions detected on US and evaluated MR images. MRI BI-RADS categories were given by consensus on the basis on dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted imaging (DWI). Pathological results and imaging follow-up at least 12 months were used as a reference standard. Sensitivity, specificity, positive predictive value (PPV), NPV and their 95% confidence interval (CI) were calculated for MRI findings.

RESULTS

One sixty seven patients with 186 lesions (US 4A category: 145, US 4B category: 41) consisted of the study cohort. The malignancy rate was 34.9% (65/186). On MRI, all malignancies showed true-positive results and 92.6% (112/121) benign lesions were correctly diagnosed. MRI increased PPV from 34.9% (65/186) to 87.8% (65/74) and reduced the false-positive biopsies by 92.6% (112/121). The sensitivity, specificity, PPV and NPV of MRI were 100% (95% CI: 94.5%-100%), 92.6% (95% CI: 86.3%-96.5%), 87.8% (95% CI: 78.2%-94.3%) and 100% (95% CI: 96.8%-100%), respectively. 2.2% (4/186) of suspicious lesions were additionally detected on MRI, 75% (3/4) of which were malignant.

CONCLUSION

MRI could downgrade suspicious lesions classified as BI-RADS 4A and 4B categories on US and avoided unnecessary benign biopsies without missing malignancy. Additional suspicious lesions detected on MRI needed further work-up.

Association between ultrasound BI-RADS signs and molecular typing of invasive breast cancer

Objective

To explore the correlation between ultrasound images and molecular typing of invasive breast cancer, so as to analyze the predictive value of preoperative ultrasound for invasive breast cancer.

Methods

302 invasive breast cancer patients were enrolled in Heping Hospital affiliated to Changzhi Medical College in Shanxi, China during 2020 to 2022. All patients accepted ultrasonic and pathological examination, and all pathological tissues received molecular typing with immunohistochemical (IHC) staining. The relevance between different molecular typings and ultrasonic image, pathology were evaluated.

Results

Univariate analysis: among the four molecular typings, there were significant differences in tumor size, shape, margin, lymph node and histological grade (P<0.05). 1. Size: Luminal A tumor was smaller (69.4%), Basal -like type tumors are mostly larger (60.9%); 2. Shape: Basal-like type is more likely to show regular shape (45.7%); 3. Margin: Luminal A and Luminal B mostly are not circumscribed (79.6%, 74.8%), Basal -like type shows circumscribed(52.2%); 4. Lymph nodes: Luminal A type tends to be normal (87.8%), Luminal B type,Her-2+ type and Basal-like type tend to be abnormal (35.6%,36.4% and 39.1%). There was no significant difference in mass orientation, echo pattern, rear echo and calcification (P>0.05). Multivariate analysis: Basal-like breast cancer mostly showed regular shape, circumscribed margin and abnormal lymph nodes (P<0.05).

Conclusion

There are differences in the ultrasound manifestations of different molecular typings of breast cancer, and ultrasound features can be used as a potential imaging index to provide important information for the precise diagnosis and treatment of breast cancer.

Effect of contraceptive hormonal therapy on mammographic breast density: A longitudinal cohort study

PURPOSE

Evaluate the longitudinal relationship between mammographic density and hormonal contraceptive use in late reproductive-aged women.

METHODS

Patients aged 35-50 years old who underwent 5 or more screening mammograms within a 7.5-year period between 2004 and 2019 in a single urban tertiary care center were randomly selected. Patients were categorized into four cohorts based on hormonal contraceptive exposure during a 2-year lead-in period and a 7.5-year study period: 1) never exposed, 2) always exposed, 3) interval hormonal contraceptive start, and 4) interval hormonal contraceptive stop. The primary outcome was difference in BI-RADS breast density category between initial and final mammograms.

RESULTS

Of the 708 patients included, long-term use of combined oral contraceptives or a levonorgestrel intrauterine device were not associated with an increase in breast density category over the 7.5-year study period, compared to those with no hormonal contraceptive exposure. Initiation of combined oral contraceptives was associated with an increase in breast density category (β = 0.31, P = 0.045); however, no difference in initial density category was noted between those exposed and those never exposed to combined oral contraceptives during the 2-year lead-in period, and discontinuation was not associated with a decrease in breast density category when compared to those with continuous exposure.

CONCLUSION(S)

Long-term use of combined oral contraceptives or a levonorgestrel intrauterine device was not associated with an increase in BI-RADS breast density category. Initiation of a combined oral contraceptive was associated with an increase in breast density category, although this may be a transient effect.

Comparison of malignant calcification identification between breast cone-beam computed tomography and digital mammography

BACKGROUND

Calcifications are important abnormal findings in breast imaging and help in the diagnosis of breast cancer.

PURPOSE

To compare breast cone-beam computed tomography (CBCT) with digital mammography (DM) in terms of the ability to identify malignant calcifications.

MATERIAL AND METHODS

In total, 115 paired examinations were performed utilizing breast CBCT and DM; 86 pathology-proven malignant lesions with calcifications detected on DM and 29 randomly selected breasts without calcifications were reviewed by three radiologists. The ability to detect calcifications was assessed on CBCT images. The characterization agreement of two imaging modalities was evaluated by the kappa coefficient. For breast CBCT images, the parameters for the display of calcifications were recorded. The Kruskal-Wallis test was used to compare the preferred slice thickness chosen by each of the three radiologists. The degree of calcification clarity was compared between two modalities using the Mann-Whitney U-test.

RESULTS

The combined sensitivity and specificity of three radiologists in 85 DM-detected calcifications detection on breast CBCT images were 98.43% (251/255) and 98.85% (86/87), respectively. CBCT images showed substantial agreement with mammograms in terms of the characterization of calcifications morphology (k = 0.703; P < 0.05) and distribution (k = 0.629; P < 0.05). CBCT images with a slice thickness of 0.273 mm and three-dimensional maximum-intensity projection (3D-MIP) were more beneficial for calcifications identification. No statistically significant difference was found between standard DM views and CBCT images for three radiologists on calcification display clarity.

CONCLUSION

CBCT images were comparable to mammograms in calcification identification and may be sufficient for malignant calcifications detection and characterization.

How to optimize MRI breast protocol? The value of combined analysis of ultrafast and diffusion-weighted MRI sequences

PURPOSE

The purpose of this retrospective study was to demonstrate the validity of early enhancement criteria on ultrafast magnetic resonance imaging (MRI) sequence to predict malignancy in a large population, and the benefit of diffusion-weighted imaging (DWI) to improve the performance of breast MRI.

MATERIAL AND METHODS

Women who underwent breast MRI examination between April 2018 and September 2020 and further breast biopsy were retrospectively included. Two readers quoted the different conventional features and classified the lesion according to the BI-RADS classification based on the conventional protocol. Then, the readers checked for the presence of early enhancement (≤ 30 s) on ultrafast sequence and the presence of an apparent diffusion coefficient (ADC) ≥ 1.5 × 10^-3 mm²/s to classify the lesions based on morphology and these two functional criteria only.

RESULTS

Two hundred fifty-seven women (median age: 51 years; range: 16-92 years) with 436 lesions (157 benign, 11 borderline and 268 malignant) were included. A MRI protocol plus two simple functional features, early enhancement (≤ 30 s) and an ADC value ≥ 1.5 × 10^-3 mm²/s, had a greater accuracy than the conventional protocol to distinguish benign from malignant breast lesions with or without ADC value (P = 0.01 and P = 0.001, respectively) on MRI, mainly due to better classification of benign lesions (increased specificity) with increasing diagnostic confidence of 3.7% and 7.8% respectively.

CONCLUSION

BI-RADS analysis based on a simple short MRI protocol plus early enhancement on ultrafast sequence and ADC value has a greaterr diagnostic accuracy than a conventional protocol and may avoid unnecessary biopsy.

AI-assisted Method for Efficiently Generating Breast Ultrasound Screening Reports

BACKGROUND

Ultrasound is one of the preferred choices for early screening of dense breast cancer. Clinically, doctors have to manually write the screening report, which is time-consuming and laborious, and it is easy to miss and miswrite.

AIM

We proposed a new pipeline to automatically generate AI breast ultrasound screening reports based on ultrasound images, aiming to assist doctors in improving the efficiency of clinical screening and reducing repetitive report writing.

METHODS

AI efficiently generated personalized breast ultrasound screening preliminary reports, especially for benign and normal cases, which account for the majority. Doctors then make simple adjustments or corrections based on the preliminary AI report to generate the final report quickly. The approach has been trained and tested using a database of 4809 breast tumor instances.

RESULTS

Experimental results indicate that this pipeline improves doctors' work efficiency by up to 90%, greatly reducing repetitive work.

CONCLUSION

Personalized report generation is more widely recognized by doctors in clinical practice than non-intelligent reports based on fixed templates or options to fill in the blanks.

Evaluating breast ultrasound S-detect image analysis for small focal breast lesions

Background

S-Detect is a computer-assisted, artificial intelligence-based system of image analysis that has been integrated into the software of ultrasound (US) equipment and has the capacity to independently differentiate between benign and malignant focal breast lesions. Since the revision and upgrade in both the breast imaging-reporting and data system (BI-RADS) US lexicon and the S-Detect software in 2013, evidence that supports improved accuracy and specificity of radiologists' assessment of breast lesions has accumulated. However, such assessment using S-Detect technology to distinguish malignant from breast lesions with a diameter no greater than 2 cm requires further investigation.

Methods

The US images of focal breast lesions from 295 patients in our hospital from January 2019 to June 2022 were collected. The BI-RADS data were evaluated by the embedded program and as manually modified prior to the determination of a pathological diagnosis. The receiver operator characteristic (ROC) curves were constructed to compare the diagnostic accuracy between the assessments of the conventional US images, the S-Detect classification, and the combination of the two.

Results

There were 326 lesions identified in 295 patients, of which pathological confirmation demonstrated that 239 were benign and 87 were malignant. The sensitivity, specificity, and accuracy of the conventional imaging group were 75.86%, 93.31%, and 88.65%. The sensitivity, specificity, and accuracy of the S-Detect classification group were 87.36%, 88.28%, and 88.04%, respectively. The assessment of the amended combination of S-Detect with US image analysis (Co-Detect group) was improved with a sensitivity, specificity, and accuracy of 90.80%, 94.56%, and 93.56%, respectively. The diagnostic accuracy of the conventional US group, the S-Detect group, and the Co-Detect group using area under curves was 0.85, 0.88 and 0.93, respectively. The Co-Detect group had a better diagnostic efficiency compared with the conventional US group (Z = 3.882, p = 0.0001) and the S-Detect group (Z = 3.861, p = 0.0001). There was no significant difference in distinguishing benign from malignant small breast lesions when comparing conventional US and S-Detect techniques.

Conclusions

The addition of S-Detect technology to conventional US imaging provided a novel and feasible method to differentiate benign from malignant small breast nodules.

Clinical use and adjustment of ultrasound elastography for breast lesions followed WFUMB guidelines and recommendations in the real world

Objective

This study aimed to explore the value of strain elastography (SE) and shear wave elastography (SWE) following the World Federation of Ultrasound in Medicine and Biology (WFUMB) guidelines and recommendations in the real world in distinguishing benign and malignant breast lesions and reducing biopsy of BI-RADS (Breast Imaging Reporting and Data System) 4a lesions.

Methods

This prospective study included 274 breast lesions. The elastography score (ES) by the Tsukuba score, the strain ratio (SR) for SE, and Emax for SWE of the lesion(A) and the regions(A') included the lesion and the margin (0.5-5 mm) surrounding the lesion were measured. The sensitivity, specificity, and AUC were calculated and compared by the cutoff values recommended by WFUMB guidelines.

Results

When scores of 1 to 3 were classified as probably benign by WFUMB recommendation, the ES was significantly higher in malignant lesions compared to benign lesions (p < 0.05) in all lesions. For the cohort by size >20 mm, the sensitivity was 100%, and the specificity was 45.5%. ES had the highest AUC: 0.79(95% CI 0.72-0.86) with a sensitivity of 96.2%, and a specificity of 61.8% for the cohort by size ≤20 mm. For the Emax-A'-S2.5mm, when the high stiffness would be considered with Emax above 80 kPa in SWE, the malignant lesions were diagnosed with a sensitivity of 95.8%, a specificity of 43.3% for all lesions, a sensitivity of 88.5% for lesions with size ≤20 mm, and sensitivity of 100.0% for lesions with size >20 mm. In 84 lesions of BI-RADS category 4a, if category 4a lesions with ES of 1-3 points or Emax-A'-S2.5 less than 80 kPa could be downgraded to category 3, 52 (61.9%) lesions could be no biopsy, including two malignancies. If category 4a lesions with ES of 1-3 points and Emax-A'-S2.5 less than 80kPa could be downgraded to category 3, 23 (27.4%) lesions could be no biopsy, with no malignancy.

Conclusions

The elastography score for SE and Emax-A' for SWE after our modification were beneficial in the diagnosis of breast cancer. The combination of SWE and SE could effectively reduce the biopsy rate of BI-RADS category 4a lesions.

Accuracy and Upgrading of CNB and BI-RADS Diagnoses Compared to Excision: A Clinicopathological-Radiological Correlation of Papillary Breast Lesions and Neoplasms

BACKGROUND

Papillary breast lesions and neoplasms (PBLs/Ns) are diagnostically challenging lesions in both core needle biopsy (CNB) and radiology.

AIM

To determine the accuracy and upgrade rate of CNB and BI-RADS diagnosis of PBLs/Ns compared to final excision diagnosis and the factors linked to upgrade.

METHODS

The favored CNB diagnosis and BI-RADS category for 82 PBLs/Ns were assessed based on histopathology, myoepithelial marker immunohistochemistry, mammographic/ultrasonographic findings. The radiological findings were compared to the pathological diagnoses. The accuracies of CNB and BI-RADS were compared to the excision diagnosis of the corresponding PBLs/Ns. The upgrade rates to malignancy were evaluated for both CNB and BI-RADS.

RESULTS

The presence of solid, irregular masses in breasts with composition A/B with calcification in radiology was significantly associated with the diagnosis of suspicious/malignant CNB, and malignant excision specimens (p<0.05). CNB was more accurate (90%), sensitive and specific with high positive and negative predictive values than BI-RADS. Combined CNB/BI-RADS accuracy was 90.2%. Overall upgrade rate came up to 9.8%. Upgrade rates to carcinoma were 7.3% for CNB and 8.5% for BI-RADS. Factors linked to upgrade were the age, lesion-size, BI-RADS category 4A and C, and histopathological/radiological discordance. All the upgraded PBLs/Ns were diagnosed as benign lesions in CNB with present/focally present myoepithelial diagnosis reflecting a sampling error.

CONCLUSION

Up to 9.8% of PBLs/Ns diagnosed on CNB and BI-RADS undergo upgrading upon final excision, despite the high diagnostic accuracy. These evidences should be considered for final decision on whether to excise the lesion or not.

Identification of the Benignity and Malignancy of BI-RADS 4 Breast Lesions Based on a Combined Quantitative Model of Dynamic Contrast-Enhanced MRI and Intravoxel Incoherent Motion

The aim of this study was to explore whether intravoxel incoherent motion (IVIM) combined with a dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) quantitative model can improve the ability to distinguish between benign and malignant BI-RADS 4 breast lesions. We enrolled 100 patients who underwent breast MRI at our institution and extracted the quantitative parameters of lesions with a post-processing workstation. Statistical differences in these parameters between benign and malignant BI-RADS 4 lesions were assessed using a two independent samples t-test or a Mann-Whitney U test. Binary logistic regression analysis was performed to establish five diagnostic models (model_{_ADC}, model_{_IVIM}, model_{_DCE}, model_{_DCE+ADC}, and model_{_DCE+IVIM}). Receiver operating characteristic (ROC) curves, leave-one-out cross-validation, and the Delong test were used to assess and compare the diagnostic performance of these models. The model_{_DCE+IVIM} showed the highest area under the curve (AUC) of 0.903 (95% confidence interval (CI): 0.828-0.953, sensitivity: 87.50%, specificity: 85.00%), which was significantly higher than that of model_{_ADC} (p = 0.014) and model_{_IVIM} (p = 0.033). The model_{_ADC} had the lowest diagnostic performance (AUC = 0.768, 95%CI: 0.672-0.846) but was not significantly different from model_{_IVIM} (p = 0.168). The united quantitative model with DCE-MRI and IVIM could improve the ability to evaluate the malignancy in BI-RADS 4 lesions, and unnecessary breast biopsies may be obviated.

Opinions on the Assessment of Breast Density Among Members of the Society of Breast Imaging

OBJECTIVE

Dense breast decreases the sensitivity and specificity of mammography and is associated with an increased risk of breast cancer. We conducted a survey to assess the opinions of Society of Breast Imaging (SBI) members regarding density assessment.

METHODS

An online survey was sent to SBI members twice in September 2020. The survey included active members who were practicing radiologists, residents, and fellows. Mammograms from three patients were presented for density assessment based on routine clinical practice and BI-RADS fourth and fifth editions. Dense breasts were defined as heterogeneously or extremely dense. Frequencies were calculated for each survey response. Pearson's correlation coefficient was used to evaluate the correlation of density assessments by different definitions.

RESULTS

The survey response rate was 12.4% (357/2875). For density assessments, the Pearson correlation coefficients between routine clinical practice and BI-RADS fourth edition were 0.05, 0.43, and 0.12 for patients 1, 2, and 3, respectively; these increased to 0.65, 0.65, and 0.66 between routine clinical practice and BI-RADS fifth edition for patients 1, 2, and 3, respectively. For future density grading, 79.0% (282/357) of respondents thought it should reflect both potential for masking and overall dense tissue for risk assessment. Additionally, 47.1% (168/357) of respondents thought quantitative methods were of use.

CONCLUSION

Density assessment varied based on routine clinical practice and BI-RADS fourth and fifth editions. Most breast radiologists agreed that density assessment should capture both masking and overall density. Moreover, almost half of respondents believed computer or artificial intelligence-assisted quantitative methods may help refine density assessment.

Mammographic breast density and the risk of breast cancer: A systematic review and meta-analysis

OBJECTIVES

Mammographic density is a well-defined risk factor for breast cancer and having extremely dense breast tissue is associated with a one-to six-fold increased risk of breast cancer. However, it is questioned whether this increased risk estimate is applicable to current breast density classification methods. Therefore, the aim of this study was to further investigate and clarify the association between mammographic density and breast cancer risk based on current literature.

METHODS

Medline, Embase and Web of Science were systematically searched for articles published since 2013, that used BI-RADS lexicon 5th edition and incorporated data on digital mammography. Crude and maximally confounder-adjusted data were pooled in odds ratios (ORs) using random-effects models. Heterogeneity regarding breast cancer risks were investigated using I² statistic, stratified and sensitivity analyses.

RESULTS

Nine observational studies were included. Having extremely dense breast tissue (BI-RADS density D) resulted in a 2.11-fold (95% CI 1.84-2.42) increased breast cancer risk compared to having scattered dense breast tissue (BI-RADS density B). Sensitivity analysis showed that when only using data that had adjusted for age and BMI, the breast cancer risk was 1.83-fold (95% CI 1.52-2.21) increased. Both results were statistically significant and homogenous.

CONCLUSIONS

Mammographic breast density BI-RADS D is associated with an approximately two-fold increased risk of breast cancer compared to having BI-RADS density B in general population women. This is a novel and lower risk estimate compared to previously reported and might be explained due to the use of digital mammography and BI-RADS lexicon 5th edition.

Solitary Dilated Ducts Revisited: Malignancy Rate and Implications for Management

RATIONALE AND OBJECTIVES

A solitary dilated duct (SDD) is a single asymmetrically dilated breast duct with diameter more than 2 mm. The Breast Imaging Reporting and Data System (BI-RADS) fifth edition recommends additional imaging and biopsy for SDDs without demonstrated benign etiology, however management of this rare entity remains controversial. This study describes practice patterns, malignancy rate, and features associated with high-risk/malignant SDDs to better stratify patients requiring biopsy versus follow-up.

MATERIALS AND METHODS

This IRB-approved retrospective study identified mammographic, sonographic and MRI exams utilizing the term "solitary dilated duct" at a multisite academic institution between 1/1/2010 and 12/31/2020. Clinical and imaging features, BI-RADS assessments, and outcomes were analyzed. Univariate and multivariate analyses identified predictors of high-risk/malignant histology.

RESULTS

SDDs identified in 49 women (mean age 56.1 years) were assessed as BI-RADS 4/5 (31/49, 63%), BI-RADS 3 (9/49, 18%), or BI-RADS 2 (9/49, 18%). Most sampled lesions were benign (16/31, 52%) and the remaining were high-risk (15/31, 48%, all papillary lesions). The only papilloma with atypia on core biopsy upgraded to grade 2 DCIS on excision (malignancy rate 1/49, 2%). All anechoic SDDs were benign (n=13), and all benign SDDs lacked internal vascularity. SDDs with associated masses were associated with malignant/high-risk outcomes on multivariate analysis (p < .001).

CONCLUSION

The BI-RADS fifth edition recommends biopsy for SDDs without demonstrated benign etiology. In our 11-year study period, practice patterns were variable with a low malignancy rate of 2%. Our findings suggest that anechoic SDDs may be followed, and SDDs with associated masses or internal vascularity require biopsy.

Sonographic features of primary breast lymphoma: An analysis of 10 cases

BACKGROUND

Primary breast lymphoma (PBL) is a rare malignant breast tumor. The literature concerning PBL ultrasound is based primarily on case reports, with only a few case series reported to date.

PURPOSE

This study aimed to elucidate the sonographic characteristics of PBL and explore the value of ultrasonography in the preoperative diagnosis of PBL using the Breast Imaging Reporting and Data System (BI-RADS).

METHODS

A retrospective review of files involving a diagnosis of PBL (2013-2020) was conducted in the Department of Pathology, Zhejiang Provincial People's Hospital, Hangzhou, and the First Affiliated Hospital of Wenzhou Medical University, Wenzhou. The clinical characteristics and sonographic features of 12 lesions in 10 patients were analyzed and discussed in light of the literature.

RESULTS

All patients, aged 50.40 ± 14.31 years (range 30-66 years), had clinically palpable lumps. Most cases were on the right breast and were unilateral. Only one patient had mucosa-associated lymphoma. The histological type of the other patients was diffuse large B-cell lymphoma (DLBCL). Ultrasonography revealed nodular and diffuse PBL lesions without internal calcification. The nodular PBL was hypoechoic or mixed hypo- to hyperechoic, with a differential lobulated shape and horizontal growth. Although color Doppler flow imaging (CDFI) showed no significant features, the ultrasound findings were categorized as BI-RADS 4 in 10 of the 12 lesions and BI-RADS 5 in two lesions. All patients were suspected of having malignancies (BI-RADS 4 or 5).

CONCLUSION

PBL was mostly found in middle-aged and elderly women, and the right breast was more prone to the development of malignancies. PBL lesions were classified as either nodular or diffuse, based on the boundaries of the tumors in the ultrasound images. Typical PBL was characterized by hypoechoic or heterogeneous lesions with circumscribed or microlobulated margins and horizontal growth. The sonographic features of the PBL lesions and the BI-RADS categorizations of the lesions analyzed suggested malignancy.

Establishment of a deep-learning system to diagnose BI-RADS4a or higher using breast ultrasound for clinical application

Although the categorization of ultrasound using the Breast Imaging Reporting and Data System (BI‐RADS) has become widespread worldwide, the problem of inter‐observer variability remains. To maintain uniformity in diagnostic accuracy, we have developed a system in which artificial intelligence (AI) can distinguish whether a static image obtained using a breast ultrasound represents BI‐RADS3 or lower or BI‐RADS4a or higher to determine the medical management that should be performed on a patient whose breast ultrasound shows abnormalities. To establish and validate the AI system, a training dataset consisting of 4028 images containing 5014 lesions and a test dataset consisting of 3166 images containing 3656 lesions were collected and annotated. We selected a setting that maximized the area under the curve (AUC) and minimized the difference in sensitivity and specificity by adjusting the internal parameters of the AI system, achieving an AUC, sensitivity, and specificity of 0.95, 91.2%, and 90.7%, respectively. Furthermore, based on 30 images extracted from the test data, the diagnostic accuracy of 20 clinicians and the AI system was compared, and the AI system was found to be significantly superior to the clinicians (McNemar test, p < 0.001). Although deep‐learning methods to categorize benign and malignant tumors using breast ultrasound have been extensively reported, our work represents the first attempt to establish an AI system to classify BI‐RADS3 or lower and BI‐RADS4a or higher successfully, providing important implications for clinical actions. These results suggest that the AI diagnostic system is sufficient to proceed to the next stage of clinical application.

Ultrasound features of pregnancy-associated breast cancer: A retrospective observational analysis

Pregnancy-associated breast cancer (PABC) is a poor prognosis in women, and the mortality rate is higher in this subgroup of patients than in non-PABC. This study aims to assess clinicopathological and ultrasound features of patients with PABC. Of 75 patients with breast cancer, 31 cases were in lactating, or pregnancy phase and 44 patients had no recent history of pregnancy/lactation at the time of cancer detection. The available pathological characteristics and ultrasound findings of the PABC and non-PABC groups were compared. The analysis of ultrasound findings demonstrated that the percentages of antiparallel orientation (p = 0.04) and heterogeneous internal echo pattern (p = 0.002) were higher in the PABC group. The final Breast Imaging Reporting and Data System (BI-RADS) assessment in the two groups was significantly different (p = 0.008). In this study, most PABCs were BI-RADS 4c or 5; compared with age-matched non-PABC cases. There were significant differences in ER (p = 0.03), receptor groups (p = 0.007), and tumor grade (p = 0.02) in PABC compared to non-PABC group. To conclude, radiologists should be careful about ultrasound findings of PABC and recommend core needle biopsy in suspected cases.

Comparative study of breast core needle biopsy (CNB) findings with ultrasound BI-RADS subtyping

&lt;b&gt; Introduction:&lt;/b&gt; Given the high prevalence of breast cancer, developing quick and accessible diagnostics solutions is critical. The BIRADS classification is a reliable method for assessing and estimating the risk of malignancy in breast lesions. &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Aim:&lt;/b&gt; The aim of this study was to compare the results of core needle biopsy of breast lesions and sonographic findings based on the BIRADS category in Yazd. &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Materials and methods:&lt;/b&gt; This retrospective analytical study was done on all core needle biopsy specimens referred to Mortaz hospital, Yazd, Iran from 2010 to 2019. Demographic data such as age, laterality of the lesion, BIRADS category, and pathology reports were extracted from patients&apos; hospital folders. Data were analyzed by SPSS version 21. P &lt; 0.05 was considered statistically significant. &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Results:&lt;/b&gt; In total, 514 cases with a mean age of 43.9 9.4 years were studied. Among them, 104 cases (20.2%) were malignant and 410 cases (79.8%) were benign. The most common benign and malignant lesions were fibroadenoma (24.9%), and infiltrative ductal carcinoma (83.7%) respectively. The most common BIRADS was class 4A (54.9%). Patients with benign lesions were mostly in the 3rd and 4th decade of life, while malignant lesions were more in the 4th and 5th decades, and this difference was statistically significant (P = 0.001). The correlation between ultrasound diagnoses (BIRADS) and pathology findings was statistically significant (P &lt; 0.001). &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Conclusion&lt;/b&gt;: Based on the results, there is a significant correlation between ultrasound outcomes according to BIRADS and pathology results, and the radiology-pathology accordance, owing to its high accuracy, can be very helpful in correctly diagnosing, monitoring, and managing the lesion.

Correlation of Sonographic Findings and Histopathological Diagnoses in Women Presenting With Breast Masses

BACKGROUND

Breast lumps have been reported as the most common breast symptom among adult females in Western Nigeria and are benign in 60% of cases. In South-Eastern Nigeria, fibroadenoma has been reported as the most common breast disease (47.5%), followed by carcinoma (30.4%) and fibrocystic disease. The aim of this study was to determine the correlation between sonographic and histopathologic findings in women who presented with breast masses.

MATERIALS AND METHODS

This was a cross-sectional study conducted among 160 consecutive female patients who presented with breast masses. A breast ultrasound scan was carried out to categorize the masses using the American College of Radiology Breast Imaging Reporting and Data System classification, and the histopathological diagnoses of the masses were obtained. The correlation of the sonographic findings and histopathological diagnoses was determined using the Statistical Package for Social Sciences (SPSS) IBM version 23.0.

RESULTS

Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were found to be 79.5%, 98.3%, 93.9%, 93.7%, and 93.8%, respectively. There was a positive correlation between the sonographic findings and histopathological diagnoses of the breast masses, which was statistically significant (P = 0.000, r = 0.846).

CONCLUSION

This study found a statistically significant positive correlation between sonographic findings and histopathological diagnoses of breast masses.

Comparison of Diagnostic Accuracies of USG, MG and MRI Modalities Defined with BI-RADS Classification System

BACKGROUND

BI-RADS classification provides facilitating information in diagnosis for radiologists. It allows radiologists to interpret mammograms accurately Objective: We aimed to compare the diagnostic accuracy of the modalities with the BI-RADS classification system made with imaging findings accompanied by USG, MG and MRI, which are a total of 3 modalities.

METHODS

This study included 82 patients who underwent Tru-Cut biopsy under the guidance of USG, MG, and MRI. Mammography, sonography and MRI were performed in the prone position.

RESULTS

Of the patients, 46.3%, 14.6%, and 39.0% were assessed in 4A, 4B, and 5 MRI BI-RADS categories, respectively. Based on the variable surgical/pathological diagnosis, 50%, 28.0%, and 22.0% of the patients were categorized as malignant findings, benign findings, and infection-inflammation-mastitis, respectively. The determination of the endpoints for the parameter of long-axis diameter (mm) was found to be statistically significant according to ROC analysis as a gold standard performed based on specificity levels of benign and malignant findings (p<0.05). A significant correlation was detected between the gold standard and the categorical variable MRI BI-RADS (χ^2=46.380, p<0.01).

CONCLUSION

When specificity and sensitivity of all three modalities in surgical/pathological diagnosis were compared, it was concluded that MRI was superior to the other modalities, and a valuable method in prediction of lesion malignancy and determination of biopsy prediction and priority.

The diagnostic value of contrast-enhanced ultrasound and superb microvascular imaging in differentiating benign from malignant solid breast lesions: A systematic review and meta-analysis

OBJECTIVE

To investigate the added value of contrast-enhanced ultrasound (CEUS) and superb microvascular imaging (SMI) to the conventional ultrasound (US) in the diagnosis of breast lesions.

METHODS

PubMed, EMBASE, Web of Science, Chinese national knowledge infrastructure databases, Chinese biomedical literature databases, and Wanfang were searched for relevant studies from November 2015 to November 2021. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Studies (QUADAS) tool. Meta-Disc version 1.4 was used to calculate sensitivity (SEN), specificity (SPE), positive likelihood ratio (LR +), negative likelihood ratio (LR-), area under curve (AUC), and diagnostic odds ratio (DOR). Meta-regression analysis was performed using STATA 16.0 software to compare the diagnostic accuracy of the two techniques.

RESULTS

In the five studies included, 530 patients were eligible for this meta-analysis. For SMI, the pooled SEN and SPE were 0.75 (95% confidence interval [CI]: 0.69-0.91) and 0.88 (95% CI: 0.83-0.91), respectively, LR + was 5.75 (95% CI: 4.26-7.78), LR- was 0.29 (95% CI: 0.23-0.36), DOR was 21.42 (95% CI, 13.61-33.73), and AUC was 0.8871. For CEUS, the pooled SEN and SPE were 0.87 (95% CI: 0.82-0.91) and 0.86 (95% CI: 0.82-0.89), respectively, LR + was 5.92 (95% CI: 4.21-8.33), LR- was 0.16 (95% CI: 0.11-0.25), DOR was 38.27 (95% CI: 18.73-78.17), and AUC was 0.9210.

CONCLUSIONS

Adding CEUS and (or) SMI to conventional US could improve its diagnostic performance in differentiating benign from malignant solid breast lesions.

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.

MRI radiogenomics for intelligent diagnosis of breast tumors and accurate prediction of neoadjuvant chemotherapy responses-a review

BACKGROUND AND OBJECTIVE

This paper aims to overview multidimensional mining algorithms in relation to Magnetic Resonance Imaging (MRI) radiogenomics for computer aided detection and diagnosis of breast tumours. The work also aims to address a new problem in radiogenomics mining: how to combine structural radiomics information with non-structural genomics information for improving the accuracy and efficacy of Neoadjuvant Chemotherapy (NAC).

METHODS

This requires the automated extraction of parameters from non-structural breast radiomics data, and finding feature vectors with diagnostic value, which then are combined with genomics data. In order to address the problem of weakly labelled tumour images, a Generative Adiversarial Networks (GAN) based deep learning strategy is proposed for the classification of tumour types; this has significant potential for providing accurate real-time identification of tumorous regions from MRI scans. In order to efficiently integrate in a deep learning framework different features from radiogenomics datasets at multiple spatio-temporal resolutions, pyramid structured and multi-scale densely connected U-Nets are proposed. A bidirectional gated recurrent unit (BiGRU) combined with an attention based deep learning approach is also proposed.

RESULTS

The aim is to accurately predict NAC responses by combining imaging and genomic datasets. The approaches discussed incorporate some of the latest developments in of current signal processing and artificial intelligence and have significant potential in advancing and provide a development platform for future cutting-edge biomedical radiogenomics analysis.

CONCLUSIONS

The association of genotypic and phenotypic features is at the core of the emergent field of Precision Medicine. It makes use of advances in biomedical big data analysis, which enables the correlation between disease-associated phenotypic characteristics, genetics polymorphism and gene activation to be revealed.

A New Practical Decision Rule to Better Differentiate BI-RADS 3 or 4 Breast Masses on Breast Ultrasound

OBJECTIVES

The BI-RADS classification provides a standardized way to describe ultrasound findings in breast cancer diagnostics. However, there is little information regarding which BI-RADS descriptors are most strongly associated with malignancy, to better distinguish BI-RADS 3 (follow-up imaging) and 4 (diagnostic biopsy) breast masses.

METHODS

Patients were recruited as part of an international, multicenter trial (NCT02638935). The trial enrolled 1294 women (6 excluded) categorized as BI-RADS 3 or 4 upon routine B-mode ultrasound examination. Ultrasound images were evaluated by three expert physicians according to BI-RADS. All patients underwent histopathological confirmation (reference standard). We performed univariate and multivariate analyses (chi-square test, logistic regression, and Krippendorff's alpha).

RESULTS

Histopathologic evaluation showed malignancy in 368 of 1288 masses (28.6%). Upon performing multivariate analysis, the following descriptors were significantly associated with malignancy (P < .05): age ≥50 years (OR 8.99), non-circumscribed indistinct (OR 4.05) and microlobulated margin (OR 2.95), nonparallel orientation (OR 2.69), and calcification (OR 2.64). A clinical decision rule informed by these results demonstrated a 97% sensitivity and missed fewer cancers compared to three physician experts (range of sensitivity 79-95%) and a previous decision rule (sensitivity 59%). Specificity was 44% versus 22-83%, respectively. The inter-reader reliability of the BI-RADS descriptors and of the final BI-RADS score was fair-moderate.

CONCLUSIONS

A patient should undergo a diagnostic biopsy (BI-RADS 4) instead of follow-up imaging (BI-RADS 3) if the patient is 50 years or older or exhibits at least one of the following features: calcification, nonparallel orientation of mass, non-circumscribed margin, or posterior shadowing.

Imaging and pathological discordance amongst the plethora of breast lesions in breast biopsies

INTRODUCTION

Imaging-guided breast tissue biopsy has become an acceptable alternative to open surgical biopsy for nonpalpable breast lesions. Discussion of abnormal results of the correlation between imaging and pathological findings can be very challenging as it can assist in decision-making with regard to the further treatment options by arriving at a comprehensive diagnosis.

MATERIALS AND METHODS

This was a retrospective study. Radiological data from imaging-guided breast biopsies of 500 patients during a 6-year period was collected and classified by a specialist radiologist as per the BI-RADS format. Histopathology reports were studied and discordance analyzed.

RESULTS

A total of 500 cases were reviewed. Approximately 33% (168) cases fell into the BI-RADS 3 category, 24.4% (122) into the BI-RADS 4, and 37% (187) into BI-RADS 5 categories. Approximately 50% (n = 250) cases were benign, 2.6% (13) belonged to the high-risk category, and 47.4% (237) were malignant. The number of discordant cases was 12 (2.4%), mostly due to technical factors. Sensitivity of biopsies to detect malignancy was 85%, specificity was 96%, and accuracy of biopsy in diagnosing cancer was 90%.

DISCUSSION

The "triple assessment" is the most sensitive method for detecting early breast cancer. An effective communication pathway must be established between a clinician, radiologist, and pathologist for surgical excision in discordance as it carries a high prevalence of carcinoma in these lesions.

CONCLUSION

In discordant cases, either due to abnormal results of imaging or of abnormal pathological findings, the final decision is based on two concordant findings, out of the three parameters. This involves a multidisciplinary breast conference and an active participation by the pathologist.

Color-map virtual touch tissue imaging (CMV) combined with BI-RADS for the diagnosis of breast lesions

OBJECTIVE

To investigate the importance of color-map virtual touch tissue imaging (CMV) in assisting Breast Imaging Reporting and Data Systems (BI-RADS) in diagnosing malignant breast lesions.

METHODS

A dataset included 134 patients and 146 breast lesions was assembled. All patients underwent biopsy or surgical excision of breast lesions, and pathological results were obtained. All patients with breast lesions also underwent conventional ultrasound (US) and CMV. Each lesion was assigned a CMV score based on the color pattern of the lesion and surrounding breast tissue and a BI-RADS classification rating based on US characteristics. We compared the diagnostic performance of using BI-RADS and CMV separately and their combination.

RESULTS

BI-RADS (odds ratio [OR]: 3.665; 95% confidence interval [CI]: 2.147, 6.258) and CMV (OR: 6.616; 95% CI: 2.272, 19.270) were independent predictors of breast malignancy (all P < 0.05). The area under the receiver operating characteristic curves (AUC) for either CMV or BI-RADS alone was inferior to that of the combination (0.877 vs. 0.962; 0.938 vs. 0.962; all P < 0.05).

CONCLUSIONS

The performance of BI-RADS in diagnosing breast lesions is significantly improved by combining CMV. Therefore, we recommend CMV as an adjunct to BI-RADS.

A Comparative Assessment of MR BI-RADS 4 Breast Lesions With Kaiser Score and Apparent Diffusion Coefficient Value

Objectives

To investigate the diagnostic performance of the Kaiser score and apparent diffusion coefficient (ADC) to differentiate Breast Imaging Reporting and Data System (BI-RADS) Category 4 lesions at dynamic contrast-enhanced (DCE) MRI.

Methods

This was a single-institution retrospective study of patients who underwent breast MRI from March 2020 to June 2021. All image data were acquired with a 3-T MRI system. Kaiser score of each lesion was assigned by an experienced breast radiologist. Kaiser score+ was determined by combining ADC and Kaiser score. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of Kaiser score+, Kaiser score, and ADC. The area under the curve (AUC) values were calculated and compared by using the Delong test. The differences in sensitivity and specificity between different indicators were determined by the McNemar test.

Results

The study involved 243 women (mean age, 43.1 years; age range, 18-67 years) with 268 MR BI-RADS 4 lesions. Overall diagnostic performance for Kaiser score (AUC, 0.902) was significantly higher than for ADC (AUC, 0.81; p = 0.004). There were no significant differences in AUCs between Kaiser score and Kaiser score+ (p = 0.134). The Kaiser score was superior to ADC in avoiding unnecessary biopsies (p < 0.001). Compared with the Kaiser score alone, the specificity of Kaiser score+ increased by 7.82%, however, at the price of a lower sensitivity.

Conclusion

For MR BI-RADS category 4 breast lesions, the Kaiser score was superior to ADC mapping regarding the potential to avoid unnecessary biopsies. However, the combination of both indicators did not significantly contribute to breast cancer diagnosis of this subgroup.

The potential of combined shear wave and strain elastography to reduce unnecessary biopsies in breast cancer diagnostics - An international, multicentre trial

BACKGROUND

Shear wave elastography (SWE) and strain elastography (SE) have shown promising potential in breast cancer diagnostics by evaluating the stiffness of a lesion. Combining these two techniques could further improve the diagnostic performance. We aimed to exploratorily define the cut-offs at which adding combined SWE and SE to B-mode breast ultrasound could help reclassify Breast Imaging Reporting and Data System (BI-RADS) 3-4 lesions to reduce the number of unnecessary breast biopsies.

METHODS

We report the secondary results of a prospective, multicentre, international trial (NCT02638935). The trial enrolled 1288 women with BI-RADS 3 to 4c breast masses on conventional B-mode breast ultrasound. All patients underwent SWE and SE (index test) and histopathologic evaluation (reference standard). Reduction of unnecessary biopsies (biopsies in benign lesions) and missed malignancies after recategorising with SWE and SE were the outcome measures.

RESULTS

On performing histopathologic evaluation, 368 of 1288 breast masses were malignant. Following the routine B-mode breast ultrasound assessment, 53.80% (495 of 920 patients) underwent an unnecessary biopsy. After recategorising BI-RADS 4a lesions (SWE cut-off ≥3.70 m/s, SE cut-off ≥1.0), 34.78% (320 of 920 patients) underwent an unnecessary biopsy corresponding to a 35.35% (320 versus 495) reduction of unnecessary biopsies. Malignancies in the new BI-RADS 3 cohort were missed in 1.96% (12 of 612 patients).

CONCLUSION

Adding combined SWE and SE to routine B-mode breast ultrasound to recategorise BI-RADS 4a patients could help reduce the number of unnecessary biopsies in breast diagnostics by about 35% while keeping the rate of undetected malignancies below the 2% ACR BI-RADS 3 definition.

Combination of shear wave elastography and BI-RADS in identification of solid breast masses

BACKGROUND

To explore the value of quantitative shear wave elastography (SWE) plus the Breast Imaging Reporting and Data System (BI-RADS) in the identification of solid breast masses.

METHODS

A total of 108 patients with 120 solid breast masses admitted to our hospital from January 2019 to January 2020 were enrolled in this study. The pathological examination served as the gold standard for definitive diagnosis. Both SWE and BI-RADS grading were performed.

RESULTS

Out of the 120 solid breast masses in 108 patients, 75 benign and 45 malignant masses were pathologically confirmed. The size, shape, margin, internal echo, microcalcification, lateral acoustic shadow, and posterior acoustic enhancement of benign and malignant masses were significantly different (all P < 0.05). The E mean, E max, SD, and E ratio of benign and malignant masses were significantly different (all P < 0.05). The E min was similar between benign and malignant masses (P > 0.05). The percentage of Adler grade II-III of the benign masses was lower than that of the malignant masses (P < 0.05). BI-RADS plus SWE yielded higher diagnostic specificity and positive predictive value than either BI-RADS or SWE; BI-RADS plus SWE yielded the highest diagnostic accuracy among the three methods (all P < 0.05).

CONCLUSION

SWE plus routine ultrasonography BI-RADS has a higher value in differentiating benign from malignant breast masses than color doppler or SWE alone, which should be further promoted in clinical practice.

Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms

OBJECTIVES

To evaluate the performance of interpretable machine learning models in predicting breast cancer molecular subtypes.

METHODS

We retrospectively enrolled 600 patients with invasive breast carcinoma between 2012 and 2019. The patients were randomly divided into a training (n = 450) and a testing (n = 150) set. The five constructed models were trained based on clinical characteristics and imaging features (mammography and ultrasonography). The model classification performances were evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity. Shapley additive explanation (SHAP) technique was used to interpret the optimal model output. Then we choose the optimal model as the assisted model to evaluate the performance of another four radiologists in predicting the molecular subtype of breast cancer with or without model assistance, according to mammography and ultrasound images.

RESULTS

The decision tree (DT) model performed the best in distinguishing triple-negative breast cancer (TNBC) from other breast cancer subtypes, yielding an AUC of 0.971; accuracy, 0.947; sensitivity, 0.905; and specificity, 0.941. The accuracy, sensitivity, and specificity of all radiologists in distinguishing TNBC from other molecular subtypes and Luminal breast cancer from other molecular subtypes have significantly improved with the assistance of DT model. In the diagnosis of TNBC versus other subtypes, the average sensitivity, average specificity, and average accuracy of less experienced and more experienced radiologists increased by 0.090, 0.125, 0.114, and 0.060, 0.090, 0.083, respectively. In the diagnosis of Luminal versus other subtypes, the average sensitivity, average specificity, and average accuracy of less experienced and more experienced radiologists increased by 0.084, 0.152, 0.159, and 0.020, 0.100, 0.048.

CONCLUSIONS

This study established an interpretable machine learning model to differentiate between breast cancer molecular subtypes, providing additional values for radiologists.

KEY POINTS

• Interpretable machine learning model (MLM) could help clinicians and radiologists differentiate between breast cancer molecular subtypes. • The Shapley additive explanations (SHAP) technique can select important features for predicting the molecular subtypes of breast cancer from a large number of imaging signs. • Machine learning model can assist radiologists to evaluate the molecular subtype of breast cancer to some extent.

Incorporating diffusion-weighted imaging in a diagnostic algorithm for multiparametric MR mammography

BACKGROUND

Apparent diffusion coefficient (ADC) measurements are not incorporated in BI-RADS classification.

PURPOSE

To assess the probability of malignancy of breast lesions at magnetic resonance mammography (MRM) at 3 T, by combining ADC measurements with the BI-RADS score, in order to improve the specificity of MRM.

MATERIAL AND METHODS

A total of 296 biopsy-proven breast lesions were included in this prospective study. MRM was performed at 3 T, using a standard protocol with dynamic sequence (DCE-MRI) and an extra echo-planar diffusion-weighted sequence. A freehand region of interest was drawn inside the lesion, and ADC values were calculated. Each lesion was categorized according to the BI-RADS classification. Logistic regression analysis was employed to predict the probability of malignancy of a lesion. The model combined the BI-RADS classification and the ADC value. Sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy were calculated.

RESULTS

In total, 153 malignant and 143 benign lesions were analyzed; 257 lesions were masses and 39 lesions were non-mass-like enhancements. The sensitivity and specificity of the combined method were 96% and 86%, respectively, in contrast to 95% and 81% with BI-RADS classification alone.

CONCLUSION

We propose a method of assessing the probability of malignancy in breast lesions by combining BI-RADS score and ADC values into a single formula, increasing sensitivity and specificity compared to BI-RADS classification alone.

BI-RADS-NET: AN EXPLAINABLE MULTITASK LEARNING APPROACH FOR CANCER DIAGNOSIS IN BREAST ULTRASOUND IMAGES

In healthcare, it is essential to explain the decision-making process of machine learning models to establish the trustworthiness of clinicians. This paper introduces BI-RADS-Net, a novel explainable deep learning approach for cancer detection in breast ultrasound images. The proposed approach incorporates tasks for explaining and classifying breast tumors, by learning feature representations relevant to clinical diagnosis. Explanations of the predictions (benign or malignant) are provided in terms of morphological features that are used by clinicians for diagnosis and reporting in medical practice. The employed features include the BI-RADS descriptors of shape, orientation, margin, echo pattern, and posterior features. Additionally, our approach predicts the likelihood of malignancy of the findings, which relates to the BI-RADS assessment category reported by clinicians. Experimental validation on a dataset consisting of 1,192 images indicates improved model accuracy, supported by explanations in clinical terms using the BI-RADS lexicon.