Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Detection Software for Automated Breast Ultrasound

RATIONALE AND OBJECTIVES

This study aimed to evaluate the diagnostic performance of radiologists following the utilization of artificial intelligence (AI)-based computer-aided detection software (CAD) in detecting suspicious lesions in automated breast ultrasounds (ABUS).

MATERIALS AND METHODS

ABUS-detected 262 breast lesions (histopathological verification; January 2020 to December 2022) were included. Two radiologists reviewed the images and assigned a Breast Imaging Reporting and Data System (BI-RADS) category. ABUS images were classified as positive or negative using AI-CAD. The BI-RADS category was readjusted in four ways: the radiologists modified the BI-RADS category using the AI results (AI-aided 1), upgraded or downgraded based on AI results (AI-aided 2), only upgraded for positive results (AI-aided 3), or only downgraded for negative results (AI-aided 4). The AI-aided diagnostic performances were compared to radiologists. The AI-CAD-positive and AI-CAD-negative cancer characteristics were compared.

RESULTS

For 262 lesions (145 malignant and 117 benign) in 231 women (mean age, 52.2 years), the area under the receiver operator characteristic curve (AUC) of radiologists was 0.870 (95% confidence interval [CI], 0.832-0.908). The AUC significantly improved to 0.919 (95% CI, 0.890-0.947; P = 0.001) using AI-aided 1, whereas it improved without significance to 0.884 (95% CI, 0.844-0.923), 0.890 (95% CI, 0.852-0.929), and 0.890 (95% CI, 0.853-0.928) using AI-aided 2, 3, and 4, respectively. AI-CAD-negative cancers were smaller, less frequently exhibited retraction phenomenon, and had lower BI-RADS category. Among nonmass lesions, AI-CAD-negative cancers showed no posterior shadowing.

CONCLUSION

AI-CAD implementation significantly improved the radiologists' diagnostic performance and may serve as a valuable diagnostic tool.

Potential Usefulness a Coronal View using an Automated Breast Ultrasound System in Detecting Breast Lesions

Objective

An automated breast ultrasound system (ABUS) combined with screening mammography has increased cancer detection rates; however, supplemental ABUS use has increased recall rates. In this study, we aimed to identify an accurate and efficient method of ABUS interpretation and evaluate the potential usefulness of its coronal view versus the conventional transverse view.

Materials and Methods

This retrospective observer study included comprised 114 ABUS cases (40 normal, 35 benign, 39 malignant). Ten physicians from multiple institutions interpreted the anonymized coronal and transverse views independently. The observers scored their confidence in the lesion detection for each case using a continuous scale and recorded reading times for each coronal and transverse view interpretation. Free-response receiver operating characteristic analysis was employed to compare detection accuracies between views; a paired t-test was used to compare the average reading times.

Results

Detection accuracy did not differ significantly between the coronal and transverse views (figure of merit=0.740 and 0.745, respectively; p = 0.72). However, the average reading time for the coronal view was significantly shorter than that for the transverse view (149.7 vs. 200.3 seconds per case, p = 0.003).

Conclusion

The coronal view obtained with the ABUS was useful for interpretation and associated with significantly shorter reading times compared with the conventional transverse view while maintaining breast lesion detection accuracy.

Automated Breast Ultrasound Provides Comparable Diagnostic Performance in Opportunistic Screening and Diagnostic Assessment

OBJECTIVE

The aim of the work described here was to assess the performance of automated breast ultrasound (ABUS) as an adjunct to digital breast tomosynthesis (DBT) in the screening and diagnostic setting.

METHODS

This cross-sectional study of women who underwent DBT and ABUS from December 2019 to March 2022 included opportunistic and targeted screening cases, as well as symptomatic women. Breast density, Breast Imaging Reporting and Data System categories and histopathology reports were collected and compared. The PPV3 (proportion of examinations with abnormal findings that resulted in a tissue diagnosis of cancer), biopsy rate (percentage of biopsies performed) and cancer detection yield (number of malignancies found by the diagnostic test given to the study sample) were calculated.

RESULTS

A total of 1089 ABUS examinations were performed (age range: 29-85 y, mean: 51.9 y). Among these were 909 screening (83.5%) and 180 diagnostic (16.5%) examinations. A total of 579 biopsies were performed on 407 patients, with a biopsy rate of 53.2%. There were 100 (9.2%) malignant lesions, 30 (5.2%) atypical/B3 lesions and 414 (71.5%) benign cases. In 9 cases (0.08%), ABUS alone detected malignancies, and in 19 cases (1.7%), DBT alone detected malignancies. The PPV3 in the screening group was 14.6%.

CONCLUSION

ABUS is useful as an adjunct to DBT in the opportunistic screening and diagnostic setting.

Evaluating Efficiency of Time Use and Operational Costs in a Breast Clinic Workflow: A Comparative Analysis Between Automated Breast Ultrasound and Handheld Ultrasound

Objective

The aim of this study was to evaluate efficiency of time use for radiologists and operational costs of automated breast ultrasound (ABUS) versus handheld breast ultrasound (HHUS).

Materials and Methods

This study was approved by the Institutional Review Board, and informed consent was waived. One hundred and fifty-three patients, aged 21-81 years, underwent both ABUS and HHUS. The time required for the ABUS scanning and radiologist interpretation and the combined scanning and interpretation time for HHUS were recorded for screening and diagnostic exams. One-Way ANOVA test was used to compare the methods, and Cohen Kappa statistics were used to achieve the agreement levels. Finally, the cost of the methods and return of interest were compared by completing a cost analysis.

Results

The overall mean ± standard deviation examination time required for ABUS examination was 676.2±145.42 seconds while mean scan time performed by radiographers was 411.76±67.79 seconds, and the mean radiologist time was 234.01±81.88 seconds. The overall mean examination time required for HHUS was 452.52±171.26 seconds, and the mean scan time and radiologist time were 419.62±143.24 seconds. The reduced time translated into savings of 7.369 TL/month, and savings of 22% in operational costs was achieved with ABUS.

Conclusion

The radiologist's time was reduced with ABUS in both screening and diagnostic scenarios. Although a second-look HHUS is required for diagnostic cases, ABUS still saves radiologists time by enabling a focused approach instead of a complete evaluation of both breasts. Thus, ABUS appears to save both medical staff time and operational costs.

Integration of Handheld Ultrasound or Automated Breast Ultrasound among Women with Negative Mammographic Screening Findings: A Multi-center Population-based Study in China

RATIONALE AND OBJECTIVES

This study assessed the role of second-look automated breast ultrasound (ABUS) adjunct to mammography (MAM) versus MAM alone in asymptomatic women and compared it with supplementing handheld ultrasound (HHUS).

MATERIALS AND METHODS

Women aged 45 to 64 underwent HHUS, ABUS, and MAM among six hospitals in China from 2018 to 2022. We compared the screening performance of three strategies (MAM alone, MAM plus HHUS, and MAM plus ABUS) stratified by age groups and breast density. McNemar's test was used to assess differences in the cancer detection rate (CDR), the false-positive biopsy rate, sensitivity, and specificity of different strategies.

RESULTS

Of 19,171 women analyzed (mean [SD] age, 51.54 [4.61] years), 72 cases of breast cancer (3.76 per 1000) were detected. The detection rates for both HHUS and ABUS combined with MAM were statistically higher than those for MAM alone (all p < 0.001). There was no significant difference in cancer yields between the two integration strategies. The increase in CRD of the integrated strategies was higher in women aged 45-54 years with denser breasts compared with MAM alone (all p < 0.0167). In addition, the false-positive biopsy rate of MAM plus ABUS was lower than that of MAM plus HHUS (p = 0.025). Moreover, the retraction in ABUS was more frequent in cases detected among MAM-negative results.

CONCLUSION

Integrated ABUS or HHUS into MAM provided similar CDRs that were significantly higher than those for MAM alone in younger women (45-54 years) with denser breasts. ABUS has the potential to avoid unnecessary biopsies and provides specific image features to distinguish malignant tumors from HHUS.

Early Prediction of Response to Neoadjuvant Chemotherapy Using Quantitative Parameters on Automated Breast Ultrasound Combined with Contrast-Enhanced Ultrasound in Breast Cancer

OBJECTIVE

This prospective study was aimed at evaluating the role of automated breast ultrasound (ABUS) and contrast-enhanced ultrasound (CEUS) in the early prediction of treatment response to neoadjuvant chemotherapy (NAC) in patients with breast cancer.

METHODS

Forty-three patients with pathologically confirmed invasive breast cancer treated with NAC were included. The standard for evaluation of response to NAC was based on surgery within 21 d of completing treatment. The patients were classified as having a pathological complete response (pCR) and a non-pCR. All patients underwent CEUS and ABUS 1 wk before receiving NAC and after two treatment cycles. The rising time (RT), time to peak (TTP), peak intensity (PI), wash-in slope (WIS) and wash-in area under the curve (Wi-AUC) were measured on the CEUS images before and after NAC. The maximum tumor diameters in the coronal and sagittal planes were measured on ABUS, and the tumor volume (V) was calculated. The difference (∆) in each parameter between the two treatment time points was compared. Binary logistic regression analysis was used to identify the predictive value of each parameter.

RESULTS

∆V, ∆TTP and ∆PI were independent predictors of pCR. The CEUS-ABUS model achieved the highest AUC (0.950), followed by those based on CEUS (0.918) and ABUS (0.891) alone.

CONCLUSION

The CEUS-ABUS model could be used clinically to optimize the treatment of patients with breast cancer.

Breast imaging: Beyond the detection

Breast cancer is a heterogeneous disease nowadays, including different biological subtypes with a variety of possible treatments, which aim to achieve the best outcome in terms of response to therapy and overall survival. In recent years breast imaging has evolved considerably, and the ultimate goal is to predict these strong phenotypic differences noninvasively. Indeed, breast cancer multiparametric studies can highlight not only qualitative imaging parameters, as the presence/absence of a likely malignant finding, but also quantitative parameters, suggesting clinical-pathological features through the evaluation of imaging biomarkers. A further step has been the introduction of artificial intelligence and in particular radiogenomics, that investigates the relationship between breast cancer imaging characteristics and tumor molecular, genomic and proliferation features. In this review, we discuss the main techniques currently in use for breast imaging, their respective fields of use and their technological and diagnostic innovations.

First proof-of-concept evaluation of the FUSION-X-US-II prototype for the performance of automated breast ultrasound in healthy volunteers

Purpose

The FUSION-X-US-II prototype was developed to combine 3D-automated breast ultrasound (ABUS) and digital breast tomosynthesis in a single device without decompressing the breast. We evaluated the technical function, feasibility of the examination workflow, image quality, breast tissue coverage and patient comfort of the ABUS device of the new prototype.

Methods

In this prospective feasibility study, the FUSION-X-US-II prototype was used to perform ABUS in 30 healthy volunteers without history of breast cancer. The ABUS images of the prototype were interpreted by a physician with specialization in breast diagnostics. Any detected lesions were measured and classified using BI-RADS^® scores. Image quality was rated subjectively by the physician and coverage of the breast was measured. Patient comfort was evaluated by a questionnaire after the examination.

Results

One hundred and six scans were performed (61 × CC, 23 × ML, 22 × MLO) in 60 breasts. Image acquisition and processing by the prototype was fast and accurate. Breast coverage by ABUS was approximately 90.8%. Sixteen breast lesions (all benign, classified as BIRADS^® 2) were identified. The examination was tolerated by all patients.

Conclusion

The FUSION-X-US-II prototype allows a rapid ABUS scan with mostly high patient comfort. Technical developments resulted in an improvement of quality and coverage compared to previous prototype versions. The results are encouraging for a test of the prototype in a clinical setting in combination with tomosynthesis.

Tumor classification in automated breast ultrasound (ABUS) based on a modified extracting feature network

People can get consistent Automated Breast Ultrasound (ABUS) images due to the imaging mechanism of scanning. Therefore, it has unique advantages in breast tumor classification using artificial intelligence technology. This paper proposes a method for classifying benign and malignant breast tumors using ABUS sequence based on deep learning. First, Images of Interest (IOI) will be extracted and Region of Interest (ROI) will be cropped in ABUS sequence by two preprocessing deep learning models, Extracting-IOI model and Cropping-ROI model. Then, we propose a Shallowly Dilated Convolutional Branch Network (SDCB-Net). We combine this network with the VGG16 transfer learning network to construct a brand-new Shared Extracting Feature Network (SEF-Net) to extract ROI sequence features. Finally, the correlation features of ABUS images are extracted and integrated by using GRU Classified Network (GRUC-Net) to achieve the accurate breast tumors classification. The final results show that the accuracy of the test set for classifying benign and malignant ABUS sequence is 92.86 %. This method not only has high accuracy but also greatly improves the speed and efficiency of breast tumor classification. It has high clinical application significance that more women can discover breast tumors timely.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

Automated breast ultrasound: Supplemental screening for average-risk women with dense breasts

OBJECTIVE

We review ultrasound (US) options for supplemental breast cancer screening of average risk women with dense breasts.

CONCLUSION

Performance data of physician-performed handheld US (HHUS), technologist-performed HHUS, and automated breast ultrasound (AUS) indicate that all are appropriate for adjunctive screening. Volumetric 3D acquisitions, reduced operator dependence, protocol standardization, reliable comparison with previous studies, independence of performance and interpretation, and whole breast depiction on coronal view may favor selection of AUS. Important considerations are workflow adjustments for physicians and staff.

Automated Breast Ultrasound Screening for Dense Breasts

Mammography is the primary screening method for breast cancers. However, the sensitivity of mammographic screening is lower for dense breasts, which are an independent risk factor for breast cancers. Automated breast ultrasound (ABUS) is used as an adjunct to mammography for screening breast cancers in asymptomatic women with dense breasts. It is an effective screening modality with diagnostic accuracy comparable to that of handheld ultrasound (HHUS). Radiologists should be familiar with the unique display mode, imaging features, and artifacts in ABUS, which differ from those in HHUS. The purpose of this study was to provide a comprehensive review of the clinical significance of dense breasts and ABUS screening, describe the unique features of ABUS, and introduce the method of use and interpretation of ABUS.

The value of coronal view as a stand-alone assessment in women undergoing automated breast ultrasound

BACKGROUND

Aim of the study was to evaluate the value of automated breast ultrasound (AUS) in women with dense breast, in terms of reading times, diagnostic performance and interobserver agreement. The assessment of coronal images alone versus the complete multiplanar (MPR) views was evaluated.

METHODS

Between August and October 2017, consecutive patients with dense breast that were referred to our Institute, for post-mammography ultrasound assessment, pre-operative assessment or follow-up of known benign lesions, were invited to undergo an additional study with AUS. Three radiologists, (5, 15 and 25 years of experience in breast imaging), reviewed the exams twice: first assessing reconstructed coronal images alone, second the complete MPR views. Reading times, diagnostic performance and interobserver agreement were assessed.

RESULTS

One hundred eighty-eight women were included, for a total of 67 breast lesions, 25 (37%) malignant and 42 (63%) benign. Compared to MPR, coronal view was associated with: lower reading times, respectively, for the three readers: 83 ± 37, 84 ± 43 and 76 ± 30 versus 163 ± 109, 131 ± 57, 151 ± 42 s (p < 0.035); lower sensitivity: 44.8%, 62.1%, 55.2% versus 69.0% (p = 0.059), 65.5% (p = 0.063), 72.4% (p = 0.076), respectively; better specificity: 94.1%, 93.7%, 94.2% versus 89.5% (p = 0.093), 87.4% (p = 0.002), 91.6% (p = 0.383), respectively. Agreement between the most and the least experienced reader was fair to moderate for categorical variables and significant for continuous ones.

CONCLUSION

The coronal view allows significantly lower reading times, a valuable feature in the screening setting, but its diagnostic performance makes the complete multiplanar assessment mandatory.

Computer-aided tumor detection in automated breast ultrasound using a 3-D convolutional neural network

BACKGROUND AND OBJECTIVES

Automated breast ultrasound (ABUS) is a widely used screening modality for breast cancer detection and diagnosis. In this study, an effective and fast computer-aided detection (CADe) system based on a 3-D convolutional neural network (CNN) is proposed as the second reader for the physician in order to decrease the reviewing time and misdetection rate.

METHODS

Our CADe system uses the sliding window method, a CNN-based determining model, and a candidate aggregation algorithm. First, the sliding window method is performed to split the ABUS volume into volumes of interest (VOIs). Afterward, VOIs are selected as tumor candidates by our determining model. To achieve higher performance, focal loss and ensemble learning are used to solve data imbalance and reduce false positive (FP) and false negative (FN) rates. Because several selected candidates may be part of the same tumor and they may overlap each other, a candidate aggregation method is applied to merge the overlapping candidates into the final detection result.

RESULTS

In the experiments, 165 and 81 cases are utilized for training the system and evaluating system performance, respectively. On evaluation with the 81 cases, our system achieves sensitivities of 100% (81/81), 95.3% (77/81), and 90.9% (74/81) with FPs per pass (per case) of 21.6 (126.2), 6.0 (34.8), and 4.6 (27.1) respectively. According to the results, the number of FPs per pass (per case) can be diminished by 56.8% (57.1%) at a sensitivity of 95.3% based on our tumor detection model.

CONCLUSIONS

In conclusion, our CADe system using 3-D CNN with the focal loss and ensemble learning may have the capability of being a tumor detection system in ABUS image.

Comparison between execution and reading time of 3D ABUS versus HHUS

BACKGROUND

Breast density is an independent risk factor for breast cancer. Mammography is supplemented with handheld ultrasound (HHUS) to increase sensitivity. Automatic breast ultrasound (ABUS) is an alternative to HHUS. Our study wanted to assess the difference in execution and reading time between ABUS and HHUS.

METHODS AND MATERIALS

N = 221 women were evaluated consecutively between January 2019 and June 2019 (average age 53 years; range 24-89). The execution and reading time of ABUS and HHUS was calculated with an available stopwatch. Time started for both procedures when the patient was ready on the examination table to be examined to the end of image acquisition and interpretation.

RESULTS

No patients interrupted the exam due to pain or discomfort. N = 221 women underwent ABUS and HHUS; N = 11 patients refused to undergo both procedures due to time constraints and refused ABUS; therefore, 210 patients were enrolled with both ABUS and HHUS available. The average time to perform and read the exam was 5 min for HHUS (DS ± 1.5) with a maximum time of 11 min and a minimum of 2 min. The average time with ABUS was 17 min (DS ± 3.8, with a maximum time of 31 min and a minimum time of 9 min). The ABUS technique took longer to be performed in all patients, with an average difference of 11 min (range 3-23 min) per patient, P < 0,001. Separating ABUS execution from reading time we highlighted as ABUS execution is more time-consuming respect HHUS. In addition, we can underline that time required by radiologists is longer for ABUS even only considering the interpretation time of the exam.

CONCLUSION

A significant difference was observed in the execution and reading time of the two exams, where the HHUS method was more rapid and tolerated.

Breast Cancer Classification in Automated Breast Ultrasound Using Multiview Convolutional Neural Network with Transfer Learning

To assist radiologists in breast cancer classification in automated breast ultrasound (ABUS) imaging, we propose a computer-aided diagnosis based on a convolutional neural network (CNN) that classifies breast lesions as benign and malignant. The proposed CNN adopts a modified Inception-v3 architecture to provide efficient feature extraction in ABUS imaging. Because the ABUS images can be visualized in transverse and coronal views, the proposed CNN provides an efficient way to extract multiview features from both views. The proposed CNN was trained and evaluated on 316 breast lesions (135 malignant and 181 benign). An observer performance test was conducted to compare five human reviewers' diagnostic performance before and after referring to the predicting outcomes of the proposed CNN. Our method achieved an area under the curve (AUC) value of 0.9468 with five-folder cross-validation, for which the sensitivity and specificity were 0.886 and 0.876, respectively. Compared with conventional machine learning-based feature extraction schemes, particularly principal component analysis (PCA) and histogram of oriented gradients (HOG), our method achieved a significant improvement in classification performance. The proposed CNN achieved a >10% increased AUC value compared with PCA and HOG. During the observer performance test, the diagnostic results of all human reviewers had increased AUC values and sensitivities after referring to the classification results of the proposed CNN, and four of the five human reviewers' AUCs were significantly improved. The proposed CNN employing a multiview strategy showed promise for the diagnosis of breast cancer, and could be used as a second reviewer for increasing diagnostic reliability.

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

Purpose

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

Methods

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

Results

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

Conclusion

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

Deformable Mapping Method to Relate Lesions in Dedicated Breast CT Images to Those in Automated Breast Ultrasound and Digital Breast Tomosynthesis Images

This work demonstrates the potential for using a deformable mapping method to register lesions between dedicated breast computed tomography (bCT) and both automated breast ultrasound (ABUS) and digital breast tomosynthesis (DBT) images (craniocaudal [CC] and mediolateral oblique [MLO] views). Two multi-modality breast phantoms with external fiducial markers attached were imaged by the three modalities. The DBT MLO view was excluded for the second phantom. The automated deformable mapping algorithm uses biomechanical modeling to determine corresponding lesions based on distances between their centers of mass (d_COM) in the deformed bCT model and the reference model (DBT or ABUS). For bCT to ABUS, the mean d_COM was 5.2 ± 2.6 mm. For bCT to DBT (CC), the mean d_COM was 5.1 ± 2.4 mm. For bCT to DBT (MLO), the mean d_COM was 4.7 ± 2.5 mm. This application could help improve a radiologist's efficiency and accuracy in breast lesion characterization, using multiple imaging modalities.

3D Automated Breast Ultrasound System: Comparison of Interpretation Time of Senior Versus Junior Radiologist

Objective

This study aimed to compare the automated breast ultrasound system (ABUS) reading time of breast radiologist to a radiology resident independent of the clinical outcomes.

Materials and Methods

One hundred women who underwent screening ABUS between July and August 2017 were reviewed retrospectively. Each study was examined sequentially by a breast radiologist who has more than 20 years of experience in breast radiology and third year resident who has 6 months of experience in breast radiology. Data were analyzed with Spearman' correlation, Wilcoxon Signed Ranks Test and Kruskal-Wallis Test and was recorded.

Results

The mean age of patients was 42.02±11.423 years (age range16-66). The average time for senior radiologist was 223.36±84.334 seconds (min 118 max 500 seconds). The average time for junior radiologist was 269.48±82.895 seconds (min 150 max 628 seconds). There was a significant difference between the mean time of two radiologists (p=0.00001). There was a significant difference regarding the decrease in the reading time throughout study with the increase of number of cases read by the breast radiologist (p<0.05); but not with the resident radiologist (p=0.687). There was a correlation between BI-RADS category and reading time for both the breast radiologist and the resident (p=0.002, p=0.00043 respectively) indicating that patients who had findings caused longer reading times.

Conclusion

ABUS reading time may differ according to the experience of the user, however the times of an experienced and non-experienced user is comparable.

Double reading of automated breast ultrasound with digital mammography or digital breast tomosynthesis for breast cancer screening

PURPOSE

To evaluate the impact of double reading automated breast ultrasound (ABUS) when added to full field digital mammography (FFDM) or digital breast tomosynthesis (DBT) for breast cancer screening.

METHODS

From April 2014 to June 2015, 124 women with dense breasts and intermediate to high breast cancer risk were recruited for screening with FFDM, DBT, and ABUS. Readers used FFDM and DBT in clinical practice and received ABUS training prior to study initiation. FFDM or DBT were first interpreted alone by two independent readers and then with ABUS. All recalled women underwent diagnostic workup with at least one year of follow-up. Recall rates were compared using the sign test; differences in outcomes were evaluated using Fisher's exact test.

RESULTS

Of 121 women with complete follow-up, all had family (35.5%) or personal (20.7%) history of breast cancer, or both (43.8%). Twenty-four women (19.8%) were recalled by at least one modality. Recalls increased from 5.0% to 13.2% (p = 0.002) when ABUS was added to FFDM and from 3.3% to 10.7% (p = 0.004) when ABUS was added to DBT. Findings recalled by both readers were more likely to result in a recommendation for short term follow-up imaging or tissue biopsy compared to findings recalled by only one reader (100% vs. 42.1%, p = 0.041). The cancer detection rate was 8.3 per 1000 screens (1/121); mode of detection: FFDM and DBT.

CONCLUSIONS

Adding ABUS significantly increased the recall rate of both FFDM and DBT screening. Double reading of ABUS during early phase adoption may reduce false positive recalls.

Reliability of automated versus handheld breast ultrasound examinations of suspicious breast masses

PURPOSE

The purpose of this study was to assess the reliability of automated breast ultrasound (ABUS) examinations of suspicious breast masses in comparison to handheld breast ultrasound (HHUS) with regard to Breast Imaging Reporting and Data System (BI-RADS) category assessment, and to investigate the factors affecting discrepancies in categorization.

METHODS

A total of 135 masses that were assessed as BI-RADS categories 4 and 5 on ABUS that underwent ultrasound (US)-guided core needle biopsy from May 2017 to December 2017 were included in this study. The BI-RADS categories were re-assessed using HHUS. Agreement of the BI-RADS categories was evaluated using kappa statistics, and the positive predictive value of each examination was calculated. Logistic regression analysis was performed to identify the mammography and US findings associated with discrepancies in the BI-RADS categorization.

RESULTS

The overall agreement between ABUS and HHUS in all cases was good (79.3%, kappa=0.61, P<0.001). Logistic regression analysis revealed that accompanying suspicious microcalcifications on mammography (odds ratio [OR], 4.63; 95% confidence interval [CI], 1.83 to 11.71; P=0.001) and an irregular shape on US (OR, 5.59; 95% CI, 1.43 to 21.83; P=0.013) were associated with discrepancies in the BI-RADS categorization.

CONCLUSION

The agreement between ABUS and HHUS examinations in the BI-RADS categorization of suspicious breast masses was good. The presence of suspicious microcalcifications on mammography and an irregular shape on US were factors associated with ABUS yielding a lower level of suspicion than HHUS in terms of the BI-RADS category assessment.

Automated Breast Ultrasonography (ABUS) in the Screening and Diagnostic Setting: Indications and Practical Use

Automated breast ultrasonography (ABUS) is a new imaging technology for automatic breast scanning through ultrasound. It was first developed to overcome the limitation of operator dependency and lack of standardization and reproducibility of handheld ultrasound. ABUS provides a three-dimensional representation of breast tissue and allows images reformatting in three planes, and the generated coronal plane has been suggested to improve diagnostic accuracy. This technique has been first used in the screening setting to improve breast cancer detection, especially in mammographically dense breasts. In recent years, numerous studies also evaluated its use in the diagnostic setting: they showed its suitability for breast cancer staging, evaluation of tumor response to neoadjuvant chemotherapy, and second-look ultrasound after magnetic resonance imaging. The purpose of this article is to provide a comprehensive review of the current body of literature about the clinical performance of ABUS, summarize available evidence, and identify gaps in knowledge for future research.

Preliminary Clinical Experience with a Combined Automated Breast Ultrasound and Digital Breast Tomosynthesis System

We analyzed the performance of a mammographically configured, automated breast ultrasound (McABUS) scanner combined with a digital breast tomosynthesis (DBT) system. The GE Invenia ultrasound system was modified for integration with GE DBT systems. Ultrasound and DBT imaging were performed in the same mammographic compression. Our small preliminary study included 13 cases, six of whom had contained invasive cancers. From analysis of these cases, current limitations and corresponding potential improvements of the system were determined. A registration analysis was performed to compare the ease of McABUS to DBT registration for this system with that of two systems designed previously. It was observed that in comparison to data from an earlier study, the McABUS-to-DBT registration alignment errors for both this system and a previously built combined system were smaller than those for a previously built standalone McABUS system.

Breast cancer detection in automated 3D breast ultrasound using iso-contours and cascaded RUSBoosts

Automated 3D breast ultrasound (ABUS) is a new popular modality as an adjunct to mammography for detecting cancers in women with dense breasts. In this paper, a multi-stage computer aided detection system is proposed to detect cancers in ABUS images. In the first step, an efficient despeckling method called OBNLM is applied on the images to reduce speckle noise. Afterwards, a new algorithm based on isocontours is applied to detect initial candidates as the boundary of masses is hypo echoic. To reduce false generated isocontours, features such as hypoechoicity, roundness, area and contour strength are used. Consequently, the resulted candidates are further processed by a cascade classifier whose base classifiers are Random Under-Sampling Boosting (RUSBoost) that are introduced to deal with imbalanced datasets. Each base classifier is trained on a group of features like Gabor, LBP, GLCM and other features. Performance of the proposed system was evaluated using 104 volumes from 74 patients, including 112 malignant lesions. According to Free Response Operating Characteristic (FROC) analysis, the proposed system achieved the region-based sensitivity and case-based sensitivity of 68% and 76% at one false positive per image.

Whole-Breast Ultrasound for Breast Screening and Archiving

The incidence of breast cancer is increasing worldwide, reinforcing the importance of breast screening. Conventional hand-held ultrasound (HHUS) for breast screening is efficient and relatively easy to perform; however, it lacks systematic recording and localization. This study investigated an electromagnetic tracking-based whole-breast ultrasound (WBUS) system to facilitate the use of HHUS for breast screening. One-hundred nine breast masses were collected, and the detection of suspicious breast lesions was compared between the WBUS system, HHUS and a commercial automated breast ultrasound (ABUS) system. The positioning error between WBUS and ABUS (1.39 ± 0.68 cm) was significantly smaller than that between HHUS and ABUS (1.62 ± 0.91 cm, p = 0.014) and HHUS and WBUS (1.63 ± 0.9 cm, p = 0.024). WBUS is a practical clinical tool for breast screening that can be used instead of the often unavailable and costly ABUS.

Improved cancer detection in automated breast ultrasound by radiologists using Computer Aided Detection

OBJECTIVE

To investigate the effect of dedicated Computer Aided Detection (CAD) software for automated breast ultrasound (ABUS) on the performance of radiologists screening for breast cancer.

METHODS

90 ABUS views of 90 patients were randomly selected from a multi-institutional archive of cases collected between 2010 and 2013. This dataset included normal cases (n=40) with >1year of follow up, benign (n=30) lesions that were either biopsied or remained stable, and malignant lesions (n=20). Six readers evaluated all cases with and without CAD in two sessions. CAD-software included conventional CAD-marks and an intelligent minimum intensity projection of the breast tissue. Readers reported using a likelihood-of-malignancy scale from 0 to 100. Alternative free-response ROC analysis was used to measure the performance.

RESULTS

Without CAD, the average area-under-the-curve (AUC) of the readers was 0.77 and significantly improved with CAD to 0.84 (p=0.001). Sensitivity of all readers improved (range 5.2-10.6%) by using CAD but specificity decreased in four out of six readers (range 1.4-5.7%). No significant difference was observed in the AUC between experienced radiologists and residents both with and without CAD.

CONCLUSIONS

Dedicated CAD-software for ABUS has the potential to improve the cancer detection rates of radiologists screening for breast cancer.

Automated Breast Ultrasound: Dual-Sided Compared with Single-Sided Imaging

The design and performance of a mammographically configured, dual-sided, automated breast ultrasound (ABUS) 3-D imaging system are described. Dual-sided imaging (superior and inferior) is compared with single-sided imaging to aid decisions on clinical implementation of the more complex, but potentially higher-quality dual-sided imaging. Marked improvement in image quality and coverage of the breast is obtained in dual-sided ultrasound over single-sided ultrasound. Among hypo-echoic masses imaged, there are increases in the mean contrast-to-noise ratio of 57% and 79%, respectively, for spliced dual-sided versus superior or inferior single-sided imaging. The fractional breast volume coverage, defined as the percentage volume in the transducer field of view that is imaged with clinically acceptable quality, is improved from 59% in both superior and inferior single-sided imaging to 89% in dual-sided imaging. Applying acoustic coupling to the breast requires more effort or sophisticated methods in dual-sided imaging than in single-sided imaging.

Recent technological advancements in breast ultrasound

Ultrasound is becoming increasingly common as an imaging tool for the detection and characterization of breast tumors. This paper provides an overview of recent technological advancements, especially those that may have an impact in clinical applications in the field of breast ultrasound in the near future. These advancements include close to 100% fractional bandwidth high frequency (5-18MHz) 2D and 3D arrays, automated breast imaging systems to minimize the operator dependence and advanced processing techniques, such as those used for detection of microcalcifications. In addition, elastography and contrast-enhanced ultrasound examinations that are expected to further enhance the clinical importance of ultrasound based breast tumor screening are briefly reviewed. These techniques have shown initial promise in clinical trials and may translate to more comprehensive clinical adoption in the future.

Feasibility Testing: Three-dimensional Tumor Mapping in Different Orientations of Automated Breast Ultrasound

A tumor-mapping algorithm was proposed to identify the same regions in different passes of automated breast ultrasound (ABUS). A total of 53 abnormal passes with 41 biopsy-proven tumors and 13 normal passes were collected. After computer-aided tumor detection, a mapping pair was composed of a detected region in one pass and another region in another pass. Location criteria, including the radial position as on a clock, the relative distance and the distance to the nipple, were used to extract mapping pairs with close regions. Quantitative intensity, morphology, texture and location features were then combined in a classifier for further classification. The performance of the classifier achieved a mapping rate of 80.39% (41/51), with an error rate of 5.97% (4/67). The trade-offs between the mapping and error rates were evaluated, and Az = 0.9094 was obtained. The proposed tumor-mapping algorithm was capable of automatically providing location correspondence information that would be helpful in reviews of ABUS examinations.

Early prediction of pathological outcomes to neoadjuvant chemotherapy in breast cancer patients using automated breast ultrasound

OBJECTIVE

Early assessment of response to neoadjuvant chemotherapy (NAC) for breast cancer allows therapy to be individualized. The optimal assessment method has not been established. We investigated the accuracy of automated breast ultrasound (ABUS) to predict pathological outcomes after NAC.

METHODS

A total of 290 breast cancer patients were eligible for this study. Tumor response after 2 cycles of chemotherapy was assessed using the product change of two largest perpendicular diameters (PC) or the longest diameter change (LDC). PC and LDC were analyzed on the axial and the coronal planes respectively. Receiver operating characteristic (ROC) curves were used to evaluate overall performance of the prediction methods. Youden's indexes were calculated to select the optimal cut-off value for each method. Sensitivity, specificity, positive and negative predictive values (PPV and NPV) and the area under the ROC curve (AUC) were calculated accordingly.

RESULTS

ypT0/is was achieved in 42 patients (14.5%) while ypT0 was achieved in 30 patients (10.3%) after NAC. All four prediction methods (PC on axial planes, LDC on axial planes, PC on coronal planes and LDC on coronal planes) displayed high AUCs (all>0.82), with the highest of 0.89 [95% confidence interval (95% CI), 0.83-0.95] when mid-treatment ABUS was used to predict final pathological complete remission (pCR). High sensitivities (85.7%-88.1%) were observed across all four prediction methods while high specificities (81.5%-85.1%) were observed in two methods used PC. The optimal cut-off values defined by our data replicate the WHO and the RECIST criteria. Lower AUCs were observed when mid-treatment ABUS was used to predict poor pathological outcomes.

CONCLUSIONS

ABUS is a useful tool in early evaluation of pCR after NAC while less reliable when predicting poor pathological outcomes.