Role of elastography for downgrading BI-RADS category 4a breast lesions according to risk factors

Automatic Breast Volume Scanner and B-Ultrasound-Based Radiomics Nomogram for Clinician Management of BI-RADS 4A Lesions

RATIONALE AND OBJECTIVES

To develop and validate a nomogram for predicting the risk of malignancy of breast imaging reporting and data system (BI-RADS) 4A lesions to reduce unnecessary invasive examinations.

MATERIALS AND METHODS

From January 2017 to July 2021, 190 cases of 4A lesions included in this study were divided into training and validation sets in a ratio of 8:2. Radiomics features were extracted from sonograms by Automatic Breast Volume Scanner (ABVS) and B-ultrasound. We constructed the radiomics model and calculated the rad-scores. Univariate and multivariate logistic regressions were used to assess demographics and lesion elastography values (virtual touch tissue image, shear wave velocity) and to develop clinical model. A clinical radiomics model was developed using rad-score and independent clinical factors, and a nomogram was plotted. Nomogram performance was evaluated using discrimination, calibration, and clinical utility.

RESULTS

The nomogram included rad-score, age, and elastography, and showed good calibration. In the training set, the area under the receiver operating characteristic curve (AUC) of the clinical radiomics model (0.900, 95% confidence interval (CI): 0.843-0.958) was superior to that of the radiomics model (0.860, 95% CI: 0.799-0.921) and clinical model (0.816, 95% CI: 0.735-0.958) (p = 0.024 and 0.008, respectively). The decision curve analysis showed that the clinical radiomics model had the highest net benefit in most threshold probability ranges.

CONCLUSION

ABVS and B-ultrasound-based radiomics nomograms have satisfactory performance in differentiating benign and malignant 4A lesions. This can help clinicians make an accurate diagnosis of 4A lesions and reduce unnecessary biopsy.

Application of Deep Learning to Reduce the Rate of Malignancy Among BI-RADS 4A Breast Lesions Based on Ultrasonography

The aim of the work described here was to develop an ultrasound (US) image-based deep learning model to reduce the rate of malignancy among breast lesions diagnosed as category 4A of the Breast Imaging-Reporting and Data System (BI-RADS) during the pre-operative US examination. A total of 479 breast lesions diagnosed as BI-RADS 4A in pre-operative US examination were enrolled. There were 362 benign lesions and 117 malignant lesions confirmed by postoperative pathology with a malignancy rate of 24.4%. US images were collected from the database server. They were then randomly divided into training and testing cohorts at a ratio of 4:1. To correctly classify malignant and benign tumors diagnosed as BI-RADS 4A in US, four deep learning models, including MobileNet, DenseNet121, Xception and Inception V3, were developed. The performance of deep learning models was compared using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Meanwhile, the robustness of the models was evaluated by five-fold cross-validation. Among the four models, the MobileNet model turned to be the optimal model with the best performance in classifying benign and malignant lesions among BI-RADS 4A breast lesions. The AUROC, accuracy, sensitivity, specificity, PPV and NPV of the optimal model in the testing cohort were 0.897, 0.913, 0.926, 0.899, 0.958 and 0.784, respectively. About 14.4% of patients were expected to be upgraded to BI-RADS 4B in US with the assistance of the MobileNet model. The deep learning model MobileNet can help to reduce the rate of malignancy among BI-RADS 4A breast lesions in pre-operative US examinations, which is valuable to clinicians in tailoring treatment for suspicious breast lesions identified on US.

The development of breast radiology: the Acta Radiologica perspective

The encouraging results of modern breast cancer care builds on tremendous improvements in diagnostics and therapy during the 20th century. Scandinavian countries have made important footprints in the development of breast diagnostics regarding technical development of imaging, cell and tissue sampling methods and, not least, population screening with mammography. The multimodality approach in combination with multidisciplinary clinical work in breast cancer serve as a role model for the management of many cancer types worldwide. The development of breast radiology is well represented in the research published in this journal and this historical review will describe the most important steps.

Highlights of the development in ultrasound during the last 70 years: A historical review

This review looks at highlights of the development in ultrasound, ranging from interventional ultrasound and Doppler to the newest techniques like contrast-enhanced ultrasound and elastography, and gives reference to some of the valuable articles in Acta Radiologica. Ultrasound equipment is now available in any size and for any purpose, ranging from handheld devices to high-end devices, and the scientific societies include ultrasound professionals of all disciplines publishing guidelines and recommendations. Interventional ultrasound is expanding the field of use of ultrasound-guided interventions into nearly all specialties of medicine, from ultrasound guidance in minimally invasive robotic procedures to simple ultrasound-guided punctures performed by general practitioners. Each medical specialty is urged to define minimum requirements for equipment, education, training, and maintenance of skills, also for medical students. The clinical application of contrast-enhanced ultrasound and elastography is a topic often seen in current research settings.

A new nomogram for predicting the malignant diagnosis of Breast Imaging Reporting and Data System (BI-RADS) ultrasonography category 4A lesions in women with dense breast tissue in the diagnostic setting

Background

Biopsy has been recommended for Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions. However, the malignancy rate of category 4A lesions is very low (2-10%). Therefore, most biopsies of category 4A lesions are benign, and the results will generally cause additional health care costs and patient anxiety.

Methods

A prediction model was developed based on an analysis of 418 BI-RADS ultrasonography (US) category 4A patients at Sun Yat-sen Memorial Hospital. Univariate and multivariate logistic regression analyses were applied to identify significant variables for inclusion in the final nomogram. The predictive accuracy and discriminative ability were evaluated using the concordance index (C-index) and calibration curves. An independent cohort of 97 patients from the Second Affiliated Hospital of Guangzhou Medical University was used for external validation.

Results

The independent risk factors from the multivariate analysis for the training cohort were family history of breast cancer (OR =4.588, P=0.004), US features [margin (OR =2.916, P=0.019), shape (irregular vs. oval, OR =2.474, P=0.044; round vs. oval, OR =1.935, P=0.276), parallel orientation vs. not parallel (OR =2.204, P=0.040)], low suspicious lymph nodes (OR =7.664, P=0.019), and suspicious calcifications on mammography (MG) (OR =6.736, P=0.001). The C-index was good in the training [0.813, 95% confidence interval (95% CI), 0.733 to 0.893] and validation cohorts (0.765, 95% CI, 0.584 to 0.946). The calibration curves showed optimal agreement between the nomogram prediction and actual observations for the probability of malignancy. Also, the cutoff score was set to 100 for discriminating high and low risk. The model performed well in discerning different risk groups.

Conclusions

We developed a well-discriminated and calibrated nomogram to predict the malignancy of BI-RADS US category 4A lesions in dense breast tissue, which may help clinicians identify patients at lower or higher risk.

Diagnostic and Predictive Values of Strain Ratios in the Regions of Interests in Reference Tissue for Breast Tumor

PURPOSE

To investigate the diagnostic and predictive value of strain ratios in the regions of interests (ROIs) in reference tissue for breast tumor.

PATIENTS AND METHODS

A total of 707 lesions in 665 consecutive patients were examined with B-mode Breast Imaging-Reporting and Data System (BI-RADS) and Ultrasonic elastography (UE). Elasticity score (ES) and strain ratio (SR) in each lesion were calculated. Receiver operating characteristic (ROC) curves were used to assess the diagnostic value of BI-RADS, ES, SR1, SR2, BI-RADS combined with ES (BI-RADS+ES), BI-RADS combined with SR1 (BI-RADS+SR1), and BI-RADS combined with SR2 (BI-RADS+SR2). The sensitivity, specificity, and areas under the ROC curves (Az) were obtained. Scatter plots were generated to demonstrate the correlation between SR1 and SR2. Kruskal-Walls H-test, Mann-Whitney U-test and one-way ANOVA were performed to evaluate SRs and tumor-related variables. Multiple linear regression analysis was carried out to determine variables independently associated with SRs.

RESULTS

BI-RADS had high sensitivity and low specificity in the diagnosis of breast tumor. The specificity of BI-BADS combined with ES or SR was even higher. The Az value of BI-RADS+ES or BI-RADS+SRs was higher than that of BI-RADS (P < 0.001). The Az value of ES was higher than those of SR1 and SR2 (P < 0.001), and those of SR1 and SR2 were similar. SR1 and SR2 were highly positively correlated. There was no statistical difference between Az values of BI-RADS+ES, BI-RADS+SR1, and BI-RADS+SR2. Indistinct margin, high histologic grade, histological type, and negative human epidermal growth factor receptor (Her-2) were associated with SR1 and SR2. Progesterone receptor (PR) status and molecular subtype were associated with SR2. Histologic grade and tumor margin were significantly associated with SR1, and tumor margin was associated with SR2.

CONCLUSION

SRs in different ROIs in the reference tissue at the same depth showed no different diagnostic value for breast tumor. Both SR1 and SR2 could be useful in assessing the biological characteristics of invasive breast carcinoma.

Risk-predicted dual nomograms consisting of clinical and ultrasound factors for downgrading BI-RADS category 4a breast lesions - A multiple centre study

Purpose: To develop and to validate a risk-predicted nomogram for downgrading Breast Imaging Reporting and Data System (BI-RADS) category 4a breast lesions. Patients and Methods: We enrolled 680 patients with breast lesions that were diagnosed as BI-RADS category 4a by conventional ultrasound from December 2018 to June 2019. All 4a lesions were randomly divided into development and validation groups at the ratio of 3:1. In the development group consisting of 499 cases, the multiple clinical and ultrasound predicted factors were extracted, and dual-predicted nomograms were constructed by multivariable logistic regression analysis, named clinical nomogram and ultrasound nomogram, respectively. Patients were twice classified as either "high risk" or "low risk" in the two nomograms. The performance of these dual nomograms was assessed by an independent validation group of 181 cases. Receiver Operating Characteristic (ROC) curve and diagnostic value were calculated to evaluate the applicability of the new model. Results: After multiple logistic regression analysis, the clinical nomogram included 2 predictors: age and the first-degree family members with breast cancer. The area under the curve (AUC) value for the clinical nomogram was 0.661 and 0.712 for the development and validation groups, respectively. The ultrasound nomogram included 3 independent predictors (margins, calcification and strain ratio), and the AUC value in this nomogram was 0.782 and 0.747 in the development and validation groups, respectively. In the development group of 499 patients, approximately 50.90% (254/499) of patients were twice classified "low risk", with a malignancy rate of 1.18%. In the validation group of 181 patients, approximately 47.51% (86/181) of patients had been twice classified as "low risk", with a malignancy rate of 1.16%. Conclusions: A dual-predicted nomogram incorporating clinical factors and imaging characteristics is an applicable model for downgrading the low-risk lesions in BI-RADS category 4a and shows good stability and accuracy, which is useful for decreasing the rate of invasive examinations and surgery.

Reducing the number of unnecessary biopsies of US-BI-RADS 4a lesions through a deep learning method for residents-in-training: a cross-sectional study

OBJECTIVE

The aim of the study is to explore the potential value of S-Detect for residents-in-training, a computer-assisted diagnosis system based on deep learning (DL) algorithm.

METHODS

The study was designed as a cross-sectional study. Routine breast ultrasound examinations were conducted by an experienced radiologist. The ultrasonic images of the lesions were retrospectively assessed by five residents-in-training according to the Breast Imaging Report and Data System (BI-RADS) lexicon, and a dichotomic classification of the lesions was provided by S-Detect. The diagnostic performances of S-Detect and the five residents were measured and compared using the pathological results as the gold standard. The category 4a lesions assessed by the residents were downgraded to possibly benign as classified by S-Detect. The diagnostic performance of the integrated results was compared with the original results of the residents.

PARTICIPANTS

A total of 195 focal breast lesions were consecutively enrolled, including 82 malignant lesions and 113 benign lesions.

RESULTS

S-Detect presented higher specificity (77.88%) and area under the curve (AUC) (0.82) than the residents (specificity: 19.47%-48.67%, AUC: 0.62-0.74). A total of 24, 31, 38, 32 and 42 identified as BI-RADS 4a lesions by residents 1, 2, 3, 4 and 5 were downgraded to possibly benign lesions by S-Detect, respectively. Among these downgraded lesions, 24, 28, 35, 30 and 40 lesions were proven to be pathologically benign, respectively. After combining the residents' results with the results of the software in category 4a lesions, the specificity and AUC of the five residents significantly improved (specificity: 46.02%-76.11%, AUC: 0.71-0.85, p<0.001). The intraclass correlation coefficient of the five residents also increased after integration (from 0.480 to 0.643).

CONCLUSIONS

With the help of the DL software, the specificity, overall diagnostic performance and interobserver agreement of the residents greatly improved. The software can be used as adjunctive tool for residents-in-training, downgrading 4a lesions to possibly benign and reducing unnecessary biopsies.