Should We Ignore, Follow, or Biopsy? AJR Am J Roentgenol. 2020;214:1445-1452. [PMID: 32319794 DOI: 10.2214/ajr.19.21872]

Impact of an artificial intelligence decision support system among radiologists with different levels of experience in breast ultrasound: A prospective study in a tertiary center

PURPOSE

To assess the impact of an artificial intelligence decision support system (Koios DS) on the diagnostic performance of radiologists with different experience in breast ultrasound and to evaluate its potential to reduce unnecessary biopsies.

METHODS

This observational, prospective, single-centre study included consecutive patients scheduled for ultrasound-guided core-needle biopsy of suspicious breast lesions. Three radiologists with different experience in breast ultrasound (senior breast radiologist: 20 years; junior breast radiologist: 3 years; general radiologist: less than 1 year) independently evaluated the lesions, assigning BI-RADS categories before and after Koios DS application. Biopsy reports served as the reference standard. AUCs and the number of unnecessary biopsies before and after implementing Koios DS were compared using DeLong and McNemar's tests.

RESULTS

A total of 222 patients (median age 58 years, interquartile range 46-72 years) with 226 lesions were included, 89/226 (39.4 %) benign and 137/226 (60.6 %) malignant. The application of Koios DS significantly improved (p < 0.001) the AUC of all radiologists, with a 0.078 AUC Δ for the junior breast radiologist (from 0.786 to 0.864), a 0.062 AUC Δ for the general radiologist (from 0.719 to 0.781), and a 0.045 AUC Δ for the senior breast radiologist (from 0.823 to 0.868). Koios DS would have significantly reduced the number of unnecessary biopsies recommended by the senior breast radiologist (from 41/89 [46.1 %] to 30/89 [33.7 %], p < 0.001) and by the junior breast radiologist (from 46/89 [51.7 %] to 29/89 [32.6 %], p = 0.001).

CONCLUSION

The application of Koios DS improved the radiologists' diagnostic performance, particularly for less experienced ones, and could potentially reduce unnecessary biopsies.

Integration of AI lesion classification, age, and BI-RADS assessment to reduce benign biopsies on breast ultrasound

OBJECTIVES

To develop and test AI-integrated biopsy avoidance strategies to improve the specificity of screening breast ultrasound (US).

MATERIALS AND METHODS

This retrospective study included consecutive asymptomatic women with BI-RADS 3, 4a, 4b, 4c, or 5 masses on screening breast US exams acquired from two hospitals between December 2019 and December 2020 (development cohort) and June 2020 and December 2020 (external validation cohort). If more than one lesion was present, the most suspicious lesion was analyzed. Logistic regression was used to develop the AI-integrated biopsy avoidance strategies in which BI-RADS 4a masses were downgraded to BI-RADS 3 if the AI classifications were "both planes benign" in all women or "benign and malignant" in the women ≤ 45 years of age. Diagnostic performance metrics were calculated for both cohorts and compared to initial assessments by radiologists using the Wilcoxon rank-sum test for noninferiority of sensitivity (relative noninferiority margin, 5%) and the McNemar test for specificity.

RESULTS

The development and external validation cohorts consisted of 393 women (median age, 45 years [IQR, 40-50 years]) with 101 malignancies and 166 women (median age, 47 years [IQR, 42-51 years]) with 31 malignancies, respectively. The developed strategy improved specificity from 53.3% (72/135; 95% CI: 45.0, 62.1) to 80.7% (109/135; [95% CI: 74.2, 87.5]; p < 0.001) while maintaining sensitivity (both 100% [31/31; 95% CI: 98.9, 100]), and would have avoided 61.7% (37/60 [95% CI: 48.2, 73.7]) of benign biopsies of BI-RADS 4a masses in the external validation cohort.

CONCLUSION

A strategy integrating AI classification in two orthogonal planes, age, and BI-RADS classification improved the specificity of screening breast US while maintaining non-inferior sensitivity.

KEY POINTS

Question How can integrating AI lesion classification, age, and BI-RADS assessment effectively reduce benign biopsies in screening breast ultrasound? Findings A strategy integrating AI classifications, age, and BI-RADS using multivariable logistic regression improved specificity while maintaining non-inferior sensitivity in breast ultrasound screening. Clinical relevance The integration of AI classification in two orthogonal planes, along with patient age and BI-RADS classification, shows potential for reducing benign breast biopsies without compromising sensitivity, leading to more efficient clinical decision-making, reduced patient anxiety, and decreased healthcare resource utilization.

Improving breast ultrasonography education: the impact of AI-based decision support on the performance of non-specialist medical professionals

PURPOSE

This study evaluated the educational impact of an artificial intelligence (AI)-based decision support system for breast ultrasonography (US) on medical professionals not specialized in breast imaging.

METHODS

In this multi-case, multi-reader study, educational materials, including American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) descriptors, were provided alongside corresponding AI results during training. The AI system presented results in the form of AIheatmaps, AI scores, and AI-provided BI-RADS assessment categories. Forty-two readers evaluated the test set in three sessions: the first session (S1) occurred before the educational intervention, the second session (S2) followed education without AI assistance, and the third session (S3) took place after education with AI assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and overall performance, were compared between the sessions.

RESULTS

The mean sensitivity increased from 66.5% (95% confidence interval [CI], 59.2% to 73.7%) to 88.7% (95% CI, 84.1% to 93.3%), with a statistically significant difference (P<0.001), and the AUC non-significantly increased from 0.664 (95% CI, 0.606 to 0.723) to 0.684 (95% CI, 0.620 to 0.748) (P=0.300). Both measures were higher in S2 than in S1. The AI-achieved AUC was comparable to that of the expert reader (0.747 [95% CI, 0.640 to 0.855] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.217). Additionally, with AI assistance, the mean AUC for inexperienced readers was not significantly different from that of the expert reader (0.745 [95% CI, 0.660 to 0.830] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.120).

CONCLUSION

The mean AUC and sensitivity improved after incorporating AI into breast US education and interpretation. AI systems with high-level performance for breast US can potentially be used as educational tools in the interpretation of breast US images.

Utilization of artificial intelligence to triage patients with delayed follow-up of probably benign breast ultrasound findings

PURPOSE

This study aimed to evaluate our institution's experience in using artificial intelligence (AI) decision support (DS) as part of the clinical workflow to triage patients with Breast Imaging Reporting and Data System (BI-RADS) 3 sonographic lesions whose follow-up was delayed during the coronavirus disease 2019 (COVID-19) pandemic, against subsequent imaging and/or pathologic follow-up results.

METHODS

This retrospective study included patients with a BI-RADS category 3 (i.e., probably benign) breast ultrasound assessment from August 2019-December 2019 whose follow-up was delayed during the COVID-19 pandemic and whose breast ultrasounds were re-reviewed using Koios DS Breast AI as part of the clinical workflow for triaging these patients. The output of Koios DS was compared with the true outcome of a presence or absence of breast cancer defined by resolution/stability on imaging follow-up for at least 2 years or pathology results.

RESULTS

The study included 161 women (mean age, 52 years) with 221 BI-RADS category 3 sonographic lesions. Of the 221 lesions, there were two confirmed cancers (0.9% malignancy rate). Koios DS assessed 112/221 lesions (50.7%) as benign, 42/221 lesions (19.0%) as probably benign, 64/221 lesions (29.0%) as suspicious, and 3/221 lesions (1.4%) as probably malignant. Koios DS had a sensitivity of 100% (2/2; 95% confidence interval [CI], 16% to 100%), specificity of 70% (154/219; 95% CI, 64% to 76%), negative predictive value of 100% (154/154; 95% CI, 98% to 100%), and false-positive rate of 30% (65/219; 95% CI, 24% to 36%).

CONCLUSION

When many follow-up appointments are delayed, e.g., natural disaster, or scenarios where resources are limited, breast ultrasound AI DS can help triage patients with probably benign breast ultrasounds.

Axillary lymph node metastasis in breast cancer: from historical axillary surgery to updated advances in the preoperative diagnosis and axillary management

Axillary lymph node status, which was routinely assessed by axillary lymph node dissection (ALND) until the 1990s, is a crucial factor in determining the stage, prognosis, and therapeutic strategy used for breast cancer patients. Axillary surgery for breast cancer patients has evolved from ALND to minimally invasive approaches. Over the decades, the application of noninvasive imaging techniques, machine learning approaches and emerging clinical prediction models for the detection of axillary lymph node metastasis greatly improves clinical diagnostic efficacy and provides optimal surgical selection. In this work, we summarize the historical axillary surgery and updated perspectives of axillary management for breast cancer patients.

Artificial intelligence reading digital mammogram: enhancing detection and differentiation of suspicious microcalcifications

OBJECTIVES

To investigate the impact of artificial intelligence (AI) on enhancing the sensitivity of digital mammograms in the detection and specification of grouped microcalcifications.

METHODS

The study is a retrospective analysis of grouped microcalcifications for 447 patients. Grouped microcalcifications detected were correlated with AI, which was applied to the initial mammograms. AI provided a heat map, demarcation, and quantitative evaluation for abnormalities according to the degree of suspicion of malignancy. Histopathology was the standard for confirmation of malignancy.

RESULTS

AI showed a high correlation percentage of 67.5% between the red colour of the colour hue bar and malignant microcalcifications (P-value <.001). The scoring of probable cancer was suggested (ie, more than 50% abnormality scoring) in 39.5% of true cancer lesions. The diagnostic performance of mammography for grouped microcalcifications revealed a sensitivity of 94.7% and a negative predictive value of 82.1%. False negatives were only 12 out of 228 that proved malignant calcifications. The agreement of cancer probability between standard mammograms and examinations read by AI presented a Kappa value of -0.094 and a P-value of <.001.

CONCLUSIONS

The used AI system enhanced the sensitivity of mammograms in detecting suspicious microcalcifications, yet an expert human reader is required for proper specification.

ADVANCES IN KNOWLEDGE

Grouped calcifications could be early breast cancer on a mammogram. The morphology and distribution are correlated with the nature of breast diseases. AI is a potential decision support for the detection and classification of grouped microcalcifications and thus positively affects the control of breast cancer.

Navigating the Uncertainty of B3 Breast Lesions: Diagnostic Challenges and Evolving Management Strategies

B3 breast lesions, classified as lesions of uncertain malignant potential, present a significant diagnostic and therapeutic challenge due to their heterogeneous nature and variable risk of progression to malignancy. These lesions, which include atypical ductal hyperplasia (ADH), papillary lesions (PLs), flat epithelial atypia (FEA), radial scars (RSs), lobular neoplasia (LN), and phyllodes tumors (PTs), occupy a "grey zone" between benign and malignant pathologies, making their management complex and often controversial. This article explores the diagnostic difficulties associated with B3 lesions, focusing on the limitations of current imaging techniques, including mammography, ultrasound, and magnetic resonance imaging (MRI), as well as the challenges in histopathological interpretation. Core needle biopsy (CNB) and vacuum-assisted biopsy (VAB) are widely used for diagnosis, but both methods have inherent limitations, including sampling errors and the inability to determine malignancy in some cases definitively. The therapeutic approach to B3 lesions is nuanced, with treatment decisions strongly influenced by factors such as the lesion size, radiological findings, histopathological characteristics, and patient factors. While some lesions can be safely monitored with watchful waiting, others may require vacuum-assisted excision (VAE) or surgical excision to rule out malignancy. The decision-making process is further complicated by the discordance between the BI-RADS score and biopsy results, as well as the presence of additional risk factors, such as microcalcifications. This review provides an in-depth analysis of the current diagnostic challenges and treatment strategies for B3 lesions, emphasizing the importance of a multidisciplinary approach to management. By synthesizing the most recent research, this article aims to provide clinicians with a clearer understanding of the complexities involved in diagnosing and treating B3 breast lesions while highlighting areas for future research, such as artificial intelligence and genomics, to improve the diagnostic accuracy and patient outcomes.

Artificial Intelligence in Diagnostic Breast Ultrasound: A Comparative Analysis of Decision Support Among Radiologists With Various Levels of Expertise

Objective

To investigate integrating an artificial intelligence (AI) system into diagnostic breast ultrasound (US) for improved performance.

Materials and Methods

Seventy suspicious breast mass lesions (53 malignant and 17 benign) from seventy women who underwent diagnostic breast US complemented with shear wave elastography, US-guided core needle biopsy and verified histopathology were enrolled. Two radiologists, one with 15 years of experience and the other with one year of experience, evaluated the images for breast imaging-reporting and data system (BI-RADS) scoring. The less-experienced radiologist re-evaluated the images with the guidance of a commercial AI system and the maximum elasticity from shear wave elastography. The BI-RADS scorings were processed to determine diagnostic performance and malignancy detections.

Results

The experienced reader demonstrated superior performance with an area under the curve (AUC) of 0.888 [95% confidence interval (CI): 0.793-0.983], indicating high diagnostic accuracy. In contrast, the Koios decision support (DS) system achieved an AUC of 0.693 (95% CI: 0.562-0.824). The less-experienced reader, guided by both Koios and elasticity, showed an AUC of 0.679 (95% CI: 0.534-0.823), while Koios alone resulted in an AUC of 0.655 (95% CI: 0.512-0.799). Without any guidance, the less-experienced reader exhibited the lowest performance, with an AUC of 0.512 (95% CI: 0.352-0.672). The experienced reader had a sensitivity of 98.1%, specificity of 58.8%, positive predictive value of 88.1%, negative predictive value of 90.9%, and overall accuracy of 88.6%. The Koios DS showed a sensitivity of 92.5%, specificity of 35.3%, and an accuracy of 78.6%. The less-experienced reader, when guided by both Koios and elasticity, achieved a sensitivity of 92.5%, specificity of 23.5%, and an accuracy of 75.7%. When guided by Koios alone, the less-experienced reader had a sensitivity of 90.6%, specificity of 17.6%, and an accuracy of 72.9%. Lastly, the less-experienced reader without any guidance showed a sensitivity of 84.9%, specificity of 17.6%, and an accuracy of 68.6%.

Conclusion

Diagnostic evaluation of the suspicious masses on breast US images largely depends on experience, with experienced readers showing good performances. AI-based guidance can help improve lower performances, and using the elasticity metric may further improve the performances of less experienced readers. This type of guidance may reduce unnecessary biopsies by increasing the detection rate for malignant lesions and deliver significant benefits for routine clinical practice in underserved areas where experienced readers may not be available.

Artificial Intelligence for Breast Ultrasound: AJR Expert Panel Narrative Review

Breast ultrasound is used in a wide variety of clinical scenarios, including both diagnostic and screening applications. Limitations of ultrasound, however, include its low specificity and, for automated breast ultrasound screening, the time necessary to review whole-breast ultrasound images. As of this writing, four AI tools that are approved or cleared by the FDA address these limitations. Current tools, which are intended to provide decision support for lesion classification and/or detection, have been shown to increase specificity among nonspecialists and to decrease interpretation times. Potential future applications include triage of patients with palpable masses in low-resource settings, preoperative prediction of axillary lymph node metastasis, and preoperative prediction of neoadjuvant chemotherapy response. Challenges in the development and clinical deployment of AI for ultrasound include the limited availability of curated training datasets compared with mammography, the high variability in ultrasound image acquisition due to equipment- and operator-related factors (which may limit algorithm generalizability), and the lack of postimplementation evaluation studies. Furthermore, current AI tools for lesion classification were developed based on 2D data, but diagnostic accuracy could potentially be improved if multimodal ultrasound data were used, such as color Doppler, elastography, cine clips, and 3D imaging.

Use of a commercial artificial intelligence-based mammography analysis software for improving breast ultrasound interpretations

OBJECTIVES

To evaluate the use of a commercial artificial intelligence (AI)-based mammography analysis software for improving the interpretations of breast ultrasound (US)-detected lesions.

METHODS

A retrospective analysis was performed on 1109 breasts that underwent both mammography and US-guided breast biopsy. The AI software processed mammograms and provided an AI score ranging from 0 to 100 for each breast, indicating the likelihood of malignancy. The performance of the AI score in differentiating mammograms with benign outcomes from those revealing cancers following US-guided breast biopsy was evaluated. In addition, prediction models for benign outcomes were constructed based on clinical and imaging characteristics with and without AI scores, using logistic regression analysis.

RESULTS

The AI software had an area under the receiver operating characteristics curve (AUROC) of 0.79 (95% CI, 0.79-0.82) in differentiating between benign and cancer cases. The prediction models that did not include AI scores (non-AI model), only used AI scores (AI-only model), and included AI scores (integrated model) had AUROCs of 0.79 (95% CI, 0.75-0.83), 0.78 (95% CI, 0.74-0.82), and 0.85 (95% CI, 0.81-0.88) in the development cohort, and 0.75 (95% CI, 0.68-0.81), 0.82 (95% CI, 0.76-0.88), and 0.84 (95% CI, 0.79-0.90) in the validation cohort, respectively. The integrated model outperformed the non-AI model in the development and validation cohorts (p < 0.001 for both).

CONCLUSION

The commercial AI-based mammography analysis software could be a valuable adjunct to clinical decision-making for managing US-detected breast lesions.

CLINICAL RELEVANCE STATEMENT

The commercial AI-based mammography analysis software could potentially reduce unnecessary biopsies and improve patient outcomes.

KEY POINTS

• Breast US has high rates of false-positive interpretations. • A commercial AI-based mammography analysis software could distinguish mammograms having benign outcomes from those revealing cancers after US-guided breast biopsy. • A commercial AI-based mammography analysis software may improve interpretations for breast US-detected lesions.

Enhancing Breast Cancer Detection through Advanced AI-Driven Ultrasound Technology: A Comprehensive Evaluation of Vis-BUS

This study aims to enhance breast cancer detection accuracy through an AI-driven ultrasound tool, Vis-BUS, developed by Barreleye Inc., Seoul, South Korea. Vis-BUS incorporates Lesion Detection AI (LD-AI) and Lesion Analysis AI (LA-AI), along with a Cancer Probability Score (CPS), to differentiate between benign and malignant breast lesions. A retrospective analysis was conducted on 258 breast ultrasound examinations to evaluate Vis-BUS's performance. The primary methods included the application of LD-AI and LA-AI to b-mode ultrasound images and the generation of CPS for each lesion. Diagnostic accuracy was assessed using metrics such as the Area Under the Receiver Operating Characteristic curve (AUROC) and the Area Under the Precision-Recall curve (AUPRC). The study found that Vis-BUS achieved high diagnostic accuracy, with an AUROC of 0.964 and an AUPRC of 0.967, indicating its effectiveness in distinguishing between benign and malignant lesions. Logistic regression analysis identified that 'Fatty' lesion density had an extremely high odds ratio (OR) of 27.7781, suggesting potential convergence issues. The 'Unknown' density category had an OR of 0.3185, indicating a lower likelihood of correct classification. Medium and large lesion sizes were associated with lower likelihoods of correct classification, with ORs of 0.7891 and 0.8014, respectively. The presence of microcalcifications showed an OR of 1.360. Among Breast Imaging-Reporting and Data System categories, category C5 had a significantly higher OR of 10.173, reflecting a higher likelihood of correct classification. Vis-BUS significantly improves diagnostic precision and supports clinical decision-making in breast cancer screening. However, further refinement is needed in areas like lesion density characterization and calcification detection to optimize its performance.

Prediction of heart failure and all-cause mortality using cardiac ultrasomics in patients with breast cancer

Breast cancer chemotherapy/immunotherapy can be associated with treatment-limiting cardiotoxicity. Radiomics techniques applied to ultrasound, known as ultrasomics, can be used in cardio-oncology to leverage echocardiography for added prognostic value. To utilize ultrasomics features collected prior to antineoplastic therapy to enhance prediction of mortality and heart failure (HF) in patients with breast cancer. Patients were retrospectively recruited in a study at the West Virginia University Cancer Institute. The final inclusion criteria were met by a total of 134 patients identified for the study. Patients were imaged using echocardiography in the parasternal long axis prior to receiving chemotherapy. All-cause mortality and HF, developed during treatment, were the primary outcomes. 269 features were assessed, grouped into four major classes: demographics (n = 21), heart function (n = 7), antineoplastic medication (n = 17), and ultrasomics (n = 224). Data was split into an internal training (60%, n = 81) and testing (40%, n = 53) set. Ultrasomics features augmented classification of mortality (area under the curve (AUC) 0.89 vs. 0.65, P = 0.003), when compared to demographic variables. When developing a risk prediction score for each feature category, ultrasomics features were significantly associated with both mortality (P = 0.031, log-rank test) and HF (P = 0.002, log-rank test). Further, only ultrasomics features provided significant improvement over demographic variables when predicting mortality (C-Index: 0.78 vs. 0.65, P = 0.044) and HF (C-Index: 0.77 vs. 0.60, P = 0.017), respectively. With further investigation, a clinical decision support tool could be developed utilizing routinely obtained patient data alongside ultrasomics variables to augment treatment regimens.

Artificial Intelligence in BI-RADS Categorization of Breast Lesions on Ultrasound: Can We Omit Excessive Follow-ups and Biopsies?

RATIONALE AND OBJECTIVES

Artificial intelligence (AI) systems have been increasingly applied to breast ultrasonography. They are expected to decrease the workload of radiologists and to improve diagnostic accuracy. The aim of this study is to evaluate the performance of an AI system for the BI-RADS category assessment in breast masses detected on breast ultrasound. MATERIALS AND METHODS: A total of 715 masses detected in 530 patients were analyzed. Three breast imaging centers of the same institution and nine breast radiologists participated in this study. Ultrasound was performed by one radiologist who obtained two orthogonal views of each detected lesion. These images were retrospectively reviewed by a second radiologist blinded to the patient's clinical data. A commercial AI system evaluated images. The level of agreement between the AI system and the two radiologists and their diagnostic performance were calculated according to dichotomic BI-RADS category assessment.

RESULTS

This study included 715 breast masses. Of these, 134 (18.75%) were malignant, and 581 (81.25%) were benign. In discriminating benign and probably benign from suspicious lesions, the agreement between AI and the first and second radiologists was moderate statistically. The sensitivity and specificity of radiologist 1, radiologist 2, and AI were calculated as 98.51% and 80.72%, 97.76% and 75.56%, and 98.51% and 65.40%, respectively. For radiologist 1, the positive predictive value (PPV) was 54.10%, the negative predictive value (NPV) was 99.58%, and the accuracy was 84.06%. Radiologist 2 achieved a PPV of 47.99%, NPV of 99.32%, and accuracy of 79.72%. The AI system exhibited a PPV of 39.64%, NPV of 99.48%, and accuracy of 71.61%. Notably, none of the lesions categorized as BI-RADS 2 by AI were malignant, while 2 of the lesions classified as BI-RADS 3 by AI were subsequently confirmed as malignant. By considering AI-assigned BI-RADS 2 as safe, we could potentially avoid 11% (18 out of 163) of benign lesion biopsies and 46.2% (110 out of 238) of follow-ups.

CONCLUSION

AI proves effective in predicting malignancy. Integrating it into the clinical workflow has the potential to reduce unnecessary biopsies and short-term follow-ups, which, in turn, can contribute to sustainability in healthcare practices.

New Frontiers in Breast Cancer Imaging: The Rise of AI

Artificial intelligence (AI) has been implemented in multiple fields of medicine to assist in the diagnosis and treatment of patients. AI implementation in radiology, more specifically for breast imaging, has advanced considerably. Breast cancer is one of the most important causes of cancer mortality among women, and there has been increased attention towards creating more efficacious methods for breast cancer detection utilizing AI to improve radiologist accuracy and efficiency to meet the increasing demand of our patients. AI can be applied to imaging studies to improve image quality, increase interpretation accuracy, and improve time efficiency and cost efficiency. AI applied to mammography, ultrasound, and MRI allows for improved cancer detection and diagnosis while decreasing intra- and interobserver variability. The synergistic effect between a radiologist and AI has the potential to improve patient care in underserved populations with the intention of providing quality and equitable care for all. Additionally, AI has allowed for improved risk stratification. Further, AI application can have treatment implications as well by identifying upstage risk of ductal carcinoma in situ (DCIS) to invasive carcinoma and by better predicting individualized patient response to neoadjuvant chemotherapy. AI has potential for advancement in pre-operative 3-dimensional models of the breast as well as improved viability of reconstructive grafts.

Development of image-based decision support systems utilizing information extracted from radiological free-text report databases with text-based transformers

OBJECTIVES

To investigate the potential and limitations of utilizing transformer-based report annotation for on-site development of image-based diagnostic decision support systems (DDSS).

METHODS

The study included 88,353 chest X-rays from 19,581 intensive care unit (ICU) patients. To label the presence of six typical findings in 17,041 images, the corresponding free-text reports of the attending radiologists were assessed by medical research assistants ("gold labels"). Automatically generated "silver" labels were extracted for all reports by transformer models trained on gold labels. To investigate the benefit of such silver labels, the image-based models were trained using three approaches: with gold labels only (MG), with silver labels first, then with gold labels (MS/G), and with silver and gold labels together (MS+G). To investigate the influence of invested annotation effort, the experiments were repeated with different numbers (N) of gold-annotated reports for training the transformer and image-based models and tested on 2099 gold-annotated images. Significant differences in macro-averaged area under the receiver operating characteristic curve (AUC) were assessed by non-overlapping 95% confidence intervals.

RESULTS

Utilizing transformer-based silver labels showed significantly higher macro-averaged AUC than training solely with gold labels (N = 1000: MG 67.8 [66.0-69.6], MS/G 77.9 [76.2-79.6]; N = 14,580: MG 74.5 [72.8-76.2], MS/G 80.9 [79.4-82.4]). Training with silver and gold labels together was beneficial using only 500 gold labels (MS+G 76.4 [74.7-78.0], MS/G 75.3 [73.5-77.0]).

CONCLUSIONS

Transformer-based annotation has potential for unlocking free-text report databases for the development of image-based DDSS. However, on-site development of image-based DDSS could benefit from more sophisticated annotation pipelines including further information than a single radiological report.

CLINICAL RELEVANCE STATEMENT

Leveraging clinical databases for on-site development of artificial intelligence (AI)-based diagnostic decision support systems by text-based transformers could promote the application of AI in clinical practice by circumventing highly regulated data exchanges with third parties.

KEY POINTS

• The amount of data from a database that can be used to develop AI-assisted diagnostic decision systems is often limited by the need for time-consuming identification of pathologies by radiologists. • The transformer-based structuring of free-text radiological reports shows potential to unlock corresponding image databases for on-site development of image-based diagnostic decision support systems. • However, the quality of image annotations generated solely on the content of a single radiology report may be limited by potential inaccuracies and incompleteness of this report.

Potential Applications and Impact of ChatGPT in Radiology

Radiology has always gone hand-in-hand with technology and artificial intelligence (AI) is not new to the field. While various AI devices and algorithms have already been integrated in the daily clinical practice of radiology, with applications ranging from scheduling patient appointments to detecting and diagnosing certain clinical conditions on imaging, the use of natural language processing and large language model based software have been in discussion for a long time. Algorithms like ChatGPT can help in improving patient outcomes, increasing the efficiency of radiology interpretation, and aiding in the overall workflow of radiologists and here we discuss some of its potential applications.

Artificial Intelligence Decision Support for Triple-Negative Breast Cancers on Ultrasound

OBJECTIVE

To assess performance of an artificial intelligence (AI) decision support software in assessing and recommending biopsy of triple-negative breast cancers (TNBCs) on US.

METHODS

Retrospective institutional review board-approved review identified patients diagnosed with TNBC after US-guided biopsy between 2009 and 2019. Artificial intelligence output for TNBCs on diagnostic US included lesion features (shape, orientation) and likelihood of malignancy category (benign, probably benign, suspicious, and probably malignant). Artificial intelligence true positive was defined as suspicious or probably malignant and AI false negative (FN) as benign or probably benign. Artificial intelligence and radiologist lesion feature agreement, AI and radiologist sensitivity and FN rate (FNR), and features associated with AI FNs were determined using Wilcoxon rank-sum test, Fisher's exact test, chi-square test of independence, and kappa statistics.

RESULTS

The study included 332 patients with 345 TNBCs. Artificial intelligence and radiologists demonstrated moderate agreement for lesion shape and orientation (k = 0.48 and k = 0.47, each P <.001). On the set of examinations using 6 earlier diagnostic US, radiologists recommended biopsy of 339/345 lesions (sensitivity 98.3%, FNR 1.7%), and AI recommended biopsy of 333/345 lesions (sensitivity 96.5%, FNR 3.5%), including 6/6 radiologist FNs. On the set of examinations using immediate prebiopsy diagnostic US, AI recommended biopsy of 331/345 lesions (sensitivity 95.9%, FNR 4.1%). Artificial intelligence FNs were more frequently oval (q < 0.001), parallel (q < 0.001), circumscribed (q = 0.04), and complex cystic and solid (q = 0.006).

CONCLUSION

Artificial intelligence accurately recommended biopsies for 96% to 97% of TNBCs on US and may assist radiologists in classifying these lesions, which often demonstrate benign sonographic features.

Artificial intelligence in breast ultrasound: application in clinical practice

Ultrasound (US) is a widely accessible and extensively used tool for breast imaging. It is commonly used as an additional screening tool, especially for women with dense breast tissue. Advances in artificial intelligence (AI) have led to the development of various AI systems that assist radiologists in identifying and diagnosing breast lesions using US. This article provides an overview of the background and supporting evidence for the use of AI in hand held breast US. It discusses the impact of AI on clinical workflow, covering breast cancer detection, diagnosis, prediction of molecular subtypes, evaluation of axillary lymph node status, and response to neoadjuvant chemotherapy. Additionally, the article highlights the potential significance of AI in breast US for low and middle income countries.

Exploring the Potential of Artificial Intelligence in Breast Ultrasound

Breast ultrasound has emerged as a valuable imaging modality in the detection and characterization of breast lesions, particularly in women with dense breast tissue or contraindications for mammography. Within this framework, artificial intelligence (AI) has garnered significant attention for its potential to improve diagnostic accuracy in breast ultrasound and revolutionize the workflow. This review article aims to comprehensively explore the current state of research and development in harnessing AI's capabilities for breast ultrasound. We delve into various AI techniques, including machine learning, deep learning, as well as their applications in automating lesion detection, segmentation, and classification tasks. Furthermore, the review addresses the challenges and hurdles faced in implementing AI systems in breast ultrasound diagnostics, such as data privacy, interpretability, and regulatory approval. Ethical considerations pertaining to the integration of AI into clinical practice are also discussed, emphasizing the importance of maintaining a patient-centered approach. The integration of AI into breast ultrasound holds great promise for improving diagnostic accuracy, enhancing efficiency, and ultimately advancing patient's care. By examining the current state of research and identifying future opportunities, this review aims to contribute to the understanding and utilization of AI in breast ultrasound and encourage further interdisciplinary collaboration to maximize its potential in clinical practice.

Validating racial and ethnic non-bias of artificial intelligence decision support for diagnostic breast ultrasound evaluation

Purpose

Breast ultrasound suffers from low positive predictive value and specificity. Artificial intelligence (AI) proposes to improve accuracy, reduce false negatives, reduce inter- and intra-observer variability and decrease the rate of benign biopsies. Perpetuating racial/ethnic disparities in healthcare and patient outcome is a potential risk when incorporating AI-based models into clinical practice; therefore, it is necessary to validate its non-bias before clinical use.

Approach

Our retrospective review assesses whether our AI decision support (DS) system demonstrates racial/ethnic bias by evaluating its performance on 1810 biopsy proven cases from nine breast imaging facilities within our health system from January 1, 2018 to October 28, 2021. Patient age, gender, race/ethnicity, AI DS output, and pathology results were obtained.

Results

Significant differences in breast pathology incidence were seen across different racial and ethnic groups. Stratified analysis showed that the difference in output by our AI DS system was due to underlying differences in pathology incidence for our specific cohort and did not demonstrate statistically significant bias in output among race/ethnic groups, suggesting similar effectiveness of our AI DS system among different races (p > 0.05 for all).

Conclusions

Our study shows promise that an AI DS system may serve as a valuable second opinion in the detection of breast cancer on diagnostic ultrasound without significant racial or ethnic bias. AI tools are not meant to replace the radiologist, but rather to aid in screening and diagnosis without perpetuating racial/ethnic disparities.

Current state and prospects of artificial intelligence in allergy

The field of medicine is witnessing an exponential growth of interest in artificial intelligence (AI), which enables new research questions and the analysis of larger and new types of data. Nevertheless, applications that go beyond proof of concepts and deliver clinical value remain rare, especially in the field of allergy. This narrative review provides a fundamental understanding of the core concepts of AI and critically discusses its limitations and open challenges, such as data availability and bias, along with potential directions to surmount them. We provide a conceptual framework to structure AI applications within this field and discuss forefront case examples. Most of these applications of AI and machine learning in allergy concern supervised learning and unsupervised clustering, with a strong emphasis on diagnosis and subtyping. A perspective is shared on guidelines for good AI practice to guide readers in applying it effectively and safely, along with prospects of field advancement and initiatives to increase clinical impact. We anticipate that AI can further deepen our knowledge of disease mechanisms and contribute to precision medicine in allergy.

Deep Learning-assisted Diagnosis of Breast Lesions on US Images: A Multivendor, Multicenter Study

Purpose

To evaluate the diagnostic performance of a deep learning (DL) model for breast US across four hospitals and assess its value to readers with different levels of experience.

Materials and Methods

In this retrospective study, a dual attention-based convolutional neural network was built and validated to discriminate malignant tumors from benign tumors by using B-mode and color Doppler US images (n = 45 909, March 2011-August 2018), acquired with 42 types of US machines, of 9895 pathologic analysis-confirmed breast lesions in 8797 patients (27 men and 8770 women; mean age, 47 years ± 12 [SD]). With and without assistance from the DL model, three novice readers with less than 5 years of US experience and two experienced readers with 8 and 18 years of US experience, respectively, interpreted 1024 randomly selected lesions. Differences in the areas under the receiver operating characteristic curves (AUCs) were tested using the DeLong test.

Results

The DL model using both B-mode and color Doppler US images demonstrated expert-level performance at the lesion level, with an AUC of 0.94 (95% CI: 0.92, 0.95) for the internal set. In external datasets, the AUCs were 0.92 (95% CI: 0.90, 0.94) for hospital 1, 0.91 (95% CI: 0.89, 0.94) for hospital 2, and 0.96 (95% CI: 0.94, 0.98) for hospital 3. DL assistance led to improved AUCs (P < .001) for one experienced and three novice radiologists and improved interobserver agreement. The average false-positive rate was reduced by 7.6% (P = .08).

Conclusion

The DL model may help radiologists, especially novice readers, improve accuracy and interobserver agreement of breast tumor diagnosis using US.Keywords: Ultrasound, Breast, Diagnosis, Breast Cancer, Deep Learning, Ultrasonography Supplemental material is available for this article. © RSNA, 2023.

Application of artificial intelligence in predicting malignancy risk in breast masses on ultrasound

Objective

To evaluate the results obtained with an artificial intelligence-based software for predicting the risk of malignancy in breast masses from ultrasound images.

Materials and Methods

This was a retrospective, single-center study evaluating 555 breast masses submitted to percutaneous biopsy at a cancer referral center. Ultrasonographic findings were classified in accordance with the BI-RADS lexicon. The images were analyzed by using Koios DS Breast software and classified as benign, probably benign, low to intermediate suspicion, high suspicion, or probably malignant. The histological classification was considered the reference standard.

Results

The mean age of the patients was 51 years, and the mean mass size was 16 mm. The radiologist evaluation had a sensitivity and specificity of 99.1% and 34.0%, respectively, compared with 98.2% and 39.0%, respectively, for the software evaluation. The positive predictive value for malignancy for the BI-RADS categories was similar between the radiologist and software evaluations. Two false-negative results were identified in the radiologist evaluation, the masses in question being classified as suspicious by the software, whereas four false-negative results were identified in the software evaluation, the masses in question being classified as suspicious by the radiologist.

Conclusion

In our sample, the performance of artificial intelligence-based software was comparable to that of a radiologist.

A role for breast ultrasound Artificial Intelligence decision support in the evaluation of small invasive lobular carcinomas

OBJECTIVE

To evaluate the diagnostic performance of an Artificial Intelligence (AI) decision support (DS) system in the ultrasound (US) assessment of invasive lobular carcinoma (ILC) of the breast, a cancer that can demonstrate variable appearance and present insidiously.

METHODS

Retrospective review was performed of 75 patients with 83 ILC diagnosed by core biopsy or surgery between November 2017 and November 2019. ILC characteristics (size, shape, echogenicity) were recorded. AI DS output (lesion characteristics, likelihood of malignancy) was compared to radiologist assessment.

RESULTS

The AI DS system interpreted 100% of ILCs as suspicious or probably malignant (100% sensitivity, and 0% false negative rate). 99% (82/83) of detected ILCs were initially recommended for biopsy by the interpreting breast radiologist, and 100% (83/83) were recommended for biopsy after one additional ILC was identified on same-day repeat diagnostic ultrasound. For lesions in which the AI DS output was probably malignant, but assigned a BI-RADS 4 assessment by the radiologist, the median lesion size was 1 cm, compared with a median lesion size of 1.4 cm for those given a BI-RADS 5 assessment (p = 0.006). These results suggest that AI may offer more useful DS in smaller sub-centimeter lesions in which shape, margin status, or vascularity is more difficult to discern. Only 20% of patients with ILC were assigned a BI-RADS 5 assessment by the radiologist.

CONCLUSION

The AI DS accurately characterized 100% of detected ILC lesions as suspicious or probably malignant. AI DS may be helpful in increasing radiologist confidence when assessing ILC on ultrasound.

Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer-aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA-approved AI applications for breast imaging, but adoption and utilization are widely variable and low overall. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer, and many of the most exciting research projects and available AI applications focus on cancer detection for mammography. There are, however, multiple additional potential applications for AI in breast imaging, including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization.

A new xAI framework with feature explainability for tumors decision-making in Ultrasound data: comparing with Grad-CAM

BACKGROUND AND OBJECTIVE

The value of implementing artificial intelligence (AI) on ultrasound screening for thyroid cancer has been acknowledged, with numerous early studies confirming AI might help physicians acquire more accurate diagnoses. However, the black box nature of AI's decision-making process makes it difficult for users to grasp the foundation of AI's predictions. Furthermore, explainability is not only related to AI performance, but also responsibility and risk in medical diagnosis. In this paper, we offer Explainer, an intrinsically explainable framework that can categorize images and create heatmaps highlighting the regions on which its prediction is based.

METHODS

A dataset of 19341 thyroid ultrasound images with pathological results and physician-annotated TI-RADS features is used to train and test the robustness of the proposed framework. Then we conducted a benign-malignant classification study to determine whether physicians perform better with the assistance of an explainer than they do alone or with Gradient-weighted Class Activation Mapping (Grad-CAM).

RESULTS

Reader studies show that the Explainer can achieve a more accurate diagnosis while explaining heatmaps, and that physicians' performances are improved when assisted by the Explainer. Case study results confirm that the Explainer is capable of locating more reasonable and feature-related regions than the Grad-CAM.

CONCLUSIONS

The Explainer offers physicians a tool to understand the basis of AI predictions and evaluate their reliability, which has the potential to unbox the "black box" of medical imaging AI.

Emerging uses of artificial intelligence in breast and axillary ultrasound

Breast ultrasound is a valuable adjunctive tool to mammography in detecting breast cancer, especially in women with dense breasts. Ultrasound also plays an important role in staging breast cancer by assessing axillary lymph nodes. However, its utility is limited by operator dependence, high recall rate, low positive predictive value and low specificity. These limitations present an opportunity for artificial intelligence (AI) to improve diagnostic performance and pioneer novel uses of ultrasound. Research in developing AI for radiology has flourished over the past few years. A subset of AI, deep learning, uses interconnected computational nodes to form a neural network, which extracts complex visual features from image data to train itself into a predictive model. This review summarizes several key studies evaluating AI programs' performance in predicting breast cancer and demonstrates that AI can assist radiologists and address limitations of ultrasound by acting as a decision support tool. This review also touches on how AI programs allow for novel predictive uses of ultrasound, particularly predicting molecular subtypes of breast cancer and response to neoadjuvant chemotherapy, which have the potential to change how breast cancer is managed by providing non-invasive prognostic and treatment data from ultrasound images. Lastly, this review explores how AI programs demonstrate improved diagnostic accuracy in predicting axillary lymph node metastasis. The limitations and future challenges in developing and implementing AI for breast and axillary ultrasound will also be discussed.

Toward AI-supported US Triage of Women with Palpable Breast Lumps in a Low-Resource Setting

Background Most low- and middle-income countries lack access to organized breast cancer screening, and women with lumps may wait months for diagnostic assessment. Purpose To demonstrate that artificial intelligence (AI) software applied to breast US images obtained with low-cost portable equipment and by minimally trained observers could accurately classify palpable breast masses for triage in a low-resource setting. Materials and Methods This prospective multicenter study evaluated participants with at least one palpable mass who were enrolled in a hospital in Jalisco, Mexico, from December 2017 through May 2021. Orthogonal US images were obtained first with portable US with and without calipers of any findings at the site of lump and adjacent tissue. Then women were imaged with standard-of-care (SOC) US with Breast Imaging Reporting and Data System assessments by a radiologist. After exclusions, 758 masses in 300 women were analyzable by AI, with outputs of benign, probably benign, suspicious, and malignant. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were determined. Results The mean patient age ± SD was 50.0 years ± 12.5 (range, 18-92 years) and mean largest lesion diameter was 13 mm ± 8 (range, 2-54 mm). Of 758 masses, 360 (47.5%) were palpable and 56 (7.4%) malignant, including six ductal carcinoma in situ. AI correctly identified 47 or 48 of 49 women (96%-98%) with cancer with either portable US or SOC US images, with AUCs of 0.91 and 0.95, respectively. One circumscribed invasive ductal carcinoma was classified as probably benign with SOC US, ipsilateral to a spiculated invasive ductal carcinoma. Of 251 women with benign masses, 168 (67%) imaged with SOC US were classified as benign or probably benign by AI, as were 96 of 251 masses (38%, P < .001) with portable US. AI performance with images obtained by a radiologist was significantly better than with images obtained by a minimally trained observer. Conclusion AI applied to portable US images of breast masses can accurately identify malignancies. Moderate specificity, which could triage 38%-67% of women with benign masses without tertiary referral, should further improve with AI and observer training with portable US. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Slanetz in this issue.

Prospective Multicenter Diagnostic Performance of Technologist-Performed Screening Breast Ultrasound After Tomosynthesis in Women With Dense Breasts (the DBTUST)

PURPOSE

To assess diagnostic performance of digital breast tomosynthesis (DBT) alone or combined with technologist-performed handheld screening ultrasound (US) in women with dense breasts.

METHODS

In an institutional review board-approved, Health Insurance Portability and Accountability Act-compliant multicenter protocol in western Pennsylvania, 6,179 women consented to three rounds of annual screening, interpreted by two radiologist observers, and had appropriate follow-up. Primary analysis was based on first observer results.

RESULTS

Mean participant age was 54.8 years (range, 40-75 years). Across 17,552 screens, there were 126 cancer events in 125 women (7.2/1,000; 95% CI, 5.9 to 8.4). In year 1, DBT-alone cancer yield was 5.0/1,000, and of DBT+US, 6.3/1,000, difference 1.3/1,000 (95% CI, 0.3 to 2.1; P = .005). In years 2 + 3, DBT cancer yield was 4.9/1,000, and of DBT+US, 5.9/1,000, difference 1.0/1,000 (95% CI, 0.4 to 1.5; P < .001). False-positive rate increased from 7.0% for DBT in year 1 to 11.5% for DBT+US and from 5.9% for DBT in year 2 + 3 to 9.7% for DBT+US (P < .001 for both). Nine cancers were seen only by double reading DBT and one by double reading US. Ten interval cancers (0.6/1,000 [95% CI, 0.2 to 0.9]) were identified. Despite reduction in specificity, addition of US improved receiver operating characteristic curves, with area under receiver operating characteristic curve increasing from 0.83 for DBT alone to 0.92 for DBT+US in year 1 (P = .01), with smaller improvements in subsequent years. Of 6,179 women, across all 3 years, 172/6,179 (2.8%) unique women had a false-positive biopsy because of DBT as did another 230/6,179 (3.7%) women because of US (P < .001).

CONCLUSION

Overall added cancer detection rate of US screening after DBT was modest at 19/17,552 (1.1/1,000; CI, 0.5- to 1.6) screens but potentially overcomes substantial increases in false-positive recalls and benign biopsies.

The feasibility of a novel computer-aided classification system for the characterisation and diagnosis of breast masses on ultrasound: a single-centre preliminary test study

AIM

To introduce a novel computer-aided classification (CAC) system and investigate the feasibility of characterising and diagnosing breast masses on ultrasound (US).

MATERIALS AND METHODS

A total of 246 breast masses were included. US features and the final assessment categories of the breast masses were analysed by a radiologist and the CAC system according to the Breast Imaging Reporting and Data System (BI-RADS) lexicon. The CAC system evaluated the BI-RADS assessment from the fusion of multi-view and colour Doppler US images without (SmartBreast) or with combining clinical variables (m-CAC system). The diagnostic performance and agreement of US characteristics between the radiologist and the CAC system were compared.

RESULTS

The agreement between the radiologist and the CAC system was substantial for mass shape (κ = 0.673), orientation (κ = 0.682), margin (κ = 0.622), posterior features (κ = 0.629), calcifications in a mass (κ = 0.709) and vascularity (κ = 0.745), fair for echo pattern (κ = 0.379), and moderate for BI-RADS assessment (κ = 0.575). With BI-RADS 4a as the cut-off value, the specificity (52.5% versus 25%, p<0.0001) and accuracy (73.98% versus 62.6%, p=0.0002) of the m-CAC system were improved without significant loss of sensitivity (94.44% versus 98.41%, p=0.1250) compared with the SmartBreast. The m-CAC system showed similar specificity (52.5% versus 45.83%, p=0.2430) and accuracy (73.98% versus 73.58%, p=1.0000) as the radiologist, but a lower sensitivity (94.44% versus 100%, p=0.0156).

CONCLUSION

The CAC system showed an acceptable agreement with the radiologist for characterisation of breast lesions. It has the potential to mimic the decision-making behaviour of radiologists for the classification of breast lesions.

Unassisted Clinicians Versus Deep Learning-Assisted Clinicians in Image-Based Cancer Diagnostics: Systematic Review With Meta-analysis

BACKGROUND

A number of publications have demonstrated that deep learning (DL) algorithms matched or outperformed clinicians in image-based cancer diagnostics, but these algorithms are frequently considered as opponents rather than partners. Despite the clinicians-in-the-loop DL approach having great potential, no study has systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification.

OBJECTIVE

We systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification.

METHODS

PubMed, Embase, IEEEXplore, and the Cochrane Library were searched for studies published between January 1, 2012, and December 7, 2021. Any type of study design was permitted that focused on comparing unassisted clinicians and DL-assisted clinicians in cancer identification using medical imaging. Studies using medical waveform-data graphics material and those investigating image segmentation rather than classification were excluded. Studies providing binary diagnostic accuracy data and contingency tables were included for further meta-analysis. Two subgroups were defined and analyzed, including cancer type and imaging modality.

RESULTS

In total, 9796 studies were identified, of which 48 were deemed eligible for systematic review. Twenty-five of these studies made comparisons between unassisted clinicians and DL-assisted clinicians and provided sufficient data for statistical synthesis. We found a pooled sensitivity of 83% (95% CI 80%-86%) for unassisted clinicians and 88% (95% CI 86%-90%) for DL-assisted clinicians. Pooled specificity was 86% (95% CI 83%-88%) for unassisted clinicians and 88% (95% CI 85%-90%) for DL-assisted clinicians. The pooled sensitivity and specificity values for DL-assisted clinicians were higher than for unassisted clinicians, at ratios of 1.07 (95% CI 1.05-1.09) and 1.03 (95% CI 1.02-1.05), respectively. Similar diagnostic performance by DL-assisted clinicians was also observed across the predefined subgroups.

CONCLUSIONS

The diagnostic performance of DL-assisted clinicians appears better than unassisted clinicians in image-based cancer identification. However, caution should be exercised, because the evidence provided in the reviewed studies does not cover all the minutiae involved in real-world clinical practice. Combining qualitative insights from clinical practice with data-science approaches may improve DL-assisted practice, although further research is required.

TRIAL REGISTRATION

PROSPERO CRD42021281372; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=281372.

AI: Can It Make a Difference to the Predictive Value of Ultrasound Breast Biopsy?

(1) Background: This study aims to compare the ground truth (pathology results) against the BI-RADS classification of images acquired while performing breast ultrasound diagnostic examinations that led to a biopsy and against the result of processing the same images through the AI algorithm KOIOS DS ^TM (KOIOS). (2) Methods: All results of biopsies performed with ultrasound guidance during 2019 were recovered from the pathology department. Readers selected the image which better represented the BI-RADS classification, confirmed correlation to the biopsied image, and submitted it to the KOIOS AI software. The results of the BI-RADS classification of the diagnostic study performed at our institution were set against the KOIOS classification and both were compared to the pathology reports. (3) Results: 403 cases were included in this study. Pathology rendered 197 malignant and 206 benign reports. Four biopsies on BI-RADS 0 and two images are included. Of fifty BI-RADS 3 cases biopsied, only seven rendered cancers. All but one had a positive or suspicious cytology; all were classified as suspicious by KOIOS. Using KOIOS, 17 B3 biopsies could have been avoided. Of 347 BI-RADS 4, 5, and 6 cases, 190 were malignant (54.7%). Because only KOIOS suspicious and probably malignant categories should be biopsied, 312 biopsies would have resulted in 187 malignant lesions (60%), but 10 cancers would have been missed. (4) Conclusions: KOIOS had a higher ratio of positive biopsies in this selected case study vis-à-vis the BI-RADS 4, 5 and 6 categories. A large number of biopsies in the BI-RADS 3 category could have been avoided.

Artificial Intelligence for Breast US

US is a widely available, commonly used, and indispensable imaging modality for breast evaluation. It is often the primary imaging modality for the detection and diagnosis of breast cancer in low-resource settings. In addition, it is frequently employed as a supplemental screening tool via either whole breast handheld US or automated breast US among women with dense breasts. In recent years, a variety of artificial intelligence systems have been developed to assist radiologists with the detection and diagnosis of breast lesions on US. This article reviews the background and evidence supporting the use of artificial intelligence tools for breast US, describes implementation strategies and impact on clinical workflow, and discusses potential emerging roles and future directions.

Prediction of the Malignancy of a Breast Lesion Detected on Breast Ultrasound: Radiomics Applied to Clinical Practice

The study aimed to evaluate the performance of radiomics features and one ultrasound CAD (computer-aided diagnosis) in the prediction of the malignancy of a breast lesion detected with ultrasound and to develop a nomogram incorporating radiomic score and available information on CAD performance, conventional Breast Imaging Reporting and Data System evaluation (BI-RADS), and clinical information. Data on 365 breast lesions referred for breast US with subsequent histologic analysis between January 2020 and March 2022 were retrospectively collected. Patients were randomly divided into a training group (n = 255) and a validation test group (n = 110). A radiomics score was generated from the US image. The CAD was performed in a subgroup of 209 cases. The radiomics score included seven radiomics features selected with the LASSO logistic regression model. The multivariable logistic model incorporating CAD performance, BI-RADS evaluation, clinical information, and radiomic score as covariates showed promising results in the prediction of the malignancy of breast lesions: Area under the receiver operating characteristic curve, [AUC]: 0.914; 95% Confidence Interval, [CI]: 0.876-0.951. A nomogram was developed based on these results for possible future applications in clinical practice.

The utilization of artificial intelligence applications to improve breast cancer detection and prognosis

Breast imaging faces challenges with the current increase in medical imaging requests and lesions that breast screening programs can miss. Solutions to improve these challenges are being sought with the recent advancement and adoption of artificial intelligent (AI)-based applications to enhance workflow efficiency as well as patient-healthcare outcomes. rtificial intelligent tools have been proposed and used to analyze different modes of breast imaging, in most of the published studies, mainly for the detection and classification of breast lesions, breast lesion segmentation, breast density evaluation, and breast cancer risk assessment. This article reviews the background of the Conventional Computer-aided Detection system and AI, AI-based applications in breast medical imaging for the identification, segmentation, and categorization of lesions, breast density and cancer risk evaluation. In addition, the challenges, and limitations of AI-based applications in breast imaging are also discussed.

Machine learning analysis of breast ultrasound to classify triple negative and HER2+ breast cancer subtypes

OBJECTIVES

Early diagnosis of triple-negative (TN) and human epidermal growth factor receptor 2 positive (HER2+) breast cancer is important due to its increased risk of micrometastatic spread necessitating early treatment and for guiding targeted therapies. This study aimed to evaluate the diagnostic performance of machine learning (ML) classification of newly diagnosed breast masses into TN versus non-TN (NTN) and HER2+ versus HER2 negative (HER2-) breast cancer, using radiomic features extracted from grayscale ultrasound (US) b-mode images.

MATERIALS AND METHODS

A retrospective chart review identified 88 female patients who underwent diagnostic breast US imaging, had confirmation of invasive malignancy on pathology and receptor status determined on immunohistochemistry available. The patients were classified as TN, NTN, HER2+ or HER2- for ground-truth labelling. For image analysis, breast masses were manually segmented by a breast radiologist. Radiomic features were extracted per image and used for predictive modelling. Supervised ML classifiers included: logistic regression, k-nearest neighbour, and Naïve Bayes. Classification performance measures were calculated on an independent (unseen) test set. The area under the receiver operating characteristic curve (AUC), sensitivity (%), and specificity (%) were reported for each classifier.

RESULTS

The logistic regression classifier demonstrated the highest AUC: 0.824 (sensitivity: 81.8%, specificity: 74.2%) for the TN sub-group and 0.778 (sensitivity: 71.4%, specificity: 71.6%) for the HER2 sub-group.

CONCLUSION

ML classifiers demonstrate high diagnostic accuracy in classifying TN versus NTN and HER2+ versus HER2- breast cancers using US images. Identification of more aggressive breast cancer subtypes early in the diagnostic process could help achieve better prognoses by prioritizing clinical referral and prompting adequate early treatment.

Evaluation of physician performance using a concurrent-read artificial intelligence system to support breast ultrasound interpretation

Purpose

The purpose of this study was to compare the diagnostic performance and the interpretation time of breast ultrasound examination between reading without and with the artificial intelligence (AI) system as a concurrent reading aid.

Material and methods

A fully crossed multi-reader and multi-case (MRMC) reader study was conducted. Sixteen participating physicians were recruited and retrospectively interpreted 172 breast ultrasound cases in two reading scenarios, once without and once with the AI system (BU-CAD™, TaiHao Medical Inc.) assistance for concurrent reading. Interpretations of any given case set with and without the AI system were separated by at least 5 weeks. These reading results were compared to the reference standard and the area under the LROC curve (AUCLROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for performance evaluations. The interpretation time was also compared between the unaided and aided scenarios.

Results

With the help of the AI system, the readers had higher diagnostic performance with an increase in the average AUCLROC from 0.7582 to 0.8294 with statistically significant. The sensitivity, specificity, PPV, and NPV were also improved from 95.77%, 24.07%, 44.18%, and 93.50%–98.17%, 30.67%, 46.91%, and 96.10%, respectively. Of these, the improvement in specificity reached statistical significance. The average interpretation time was significantly reduced by approximately 40% when the readers were assisted by the AI system.

Conclusion

The concurrent-read AI system improves the diagnostic performance in detecting and diagnosing breast lesions on breast ultrasound images. In addition, the interpretation time is effectively reduced for the interpreting physicians.

•

A reader study was conducted to compare the breast ultrasound interpreting performance without and with the aid of AI system.

•

The performance of breast ultrasound interpretation was improved by the AI system as a concurrent reading aid.

•

The breast ultrasound interpretation time is significantly reduced by the AI system as a concurrent reading aid.

•

The reproducibility experiments of the same lesion cropped by different rectangular proved the robustness of the AI system.

Ultrasound radiomics in personalized breast management: Current status and future prospects

Breast cancer is the most common cancer in women worldwide. Providing accurate and efficient diagnosis, risk stratification and timely adjustment of treatment strategies are essential steps in achieving precision medicine before, during and after treatment. Radiomics provides image information that cannot be recognized by the naked eye through deep mining of medical images. Several studies have shown that radiomics, as a second reader of medical images, can assist physicians not only in the detection and diagnosis of breast lesions but also in the assessment of risk stratification and prediction of treatment response. Recently, more and more studies have focused on the application of ultrasound radiomics in breast management. We summarized recent research advances in ultrasound radiomics for the diagnosis of benign and malignant breast lesions, prediction of molecular subtype, assessment of lymph node status, prediction of neoadjuvant chemotherapy response, and prediction of survival. In addition, we discuss the current challenges and future prospects of ultrasound radiomics.

The Impact of Dense Breasts on the Stage of Breast Cancer at Diagnosis: A Review and Options for Supplemental Screening

The purpose of breast cancer screening is to find cancers early to reduce mortality and to allow successful treatment with less aggressive therapy. Mammography is the gold standard for breast cancer screening. Its efficacy in reducing mortality from breast cancer was proven in randomized controlled trials (RCTs) conducted from the early 1960s to the mid 1990s. Panels that recommend breast cancer screening guidelines have traditionally relied on the old RCTs, which did not include considerations of breast density, race/ethnicity, current hormone therapy, and other risk factors. Women do not all benefit equally from mammography. Mortality reduction is significantly lower in women with dense breasts because normal dense tissue can mask cancers on mammograms. Moreover, women with dense breasts are known to be at increased risk. To provide equity, breast cancer screening guidelines should be created with the goal of maximizing mortality reduction and allowing less aggressive therapy, which may include decreasing the interval between screening mammograms and recommending consideration of supplemental screening for women with dense breasts. This review will address the issue of dense breasts and the impact on the stage of breast cancer at the time of diagnosis, and discuss options for supplemental screening.

Deep learning in breast imaging

Millions of breast imaging exams are performed each year in an effort to reduce the morbidity and mortality of breast cancer. Breast imaging exams are performed for cancer screening, diagnostic work-up of suspicious findings, evaluating extent of disease in recently diagnosed breast cancer patients, and determining treatment response. Yet, the interpretation of breast imaging can be subjective, tedious, time-consuming, and prone to human error. Retrospective and small reader studies suggest that deep learning (DL) has great potential to perform medical imaging tasks at or above human-level performance, and may be used to automate aspects of the breast cancer screening process, improve cancer detection rates, decrease unnecessary callbacks and biopsies, optimize patient risk assessment, and open up new possibilities for disease prognostication. Prospective trials are urgently needed to validate these proposed tools, paving the way for real-world clinical use. New regulatory frameworks must also be developed to address the unique ethical, medicolegal, and quality control issues that DL algorithms present. In this article, we review the basics of DL, describe recent DL breast imaging applications including cancer detection and risk prediction, and discuss the challenges and future directions of artificial intelligence-based systems in the field of breast cancer.

Updates in Artificial Intelligence for Breast Imaging

Artificial intelligence (AI) for breast imaging has rapidly moved from the experimental to implementation phase. As of this writing, Food and Drug Administration (FDA)-approved mammographic applications are available for triage, lesion detection and classification, and breast density assessment. For sonography and MRI, FDA-approved applications are available for lesion classification. Numerous other interpretive and noninterpretive AI applications are in the development phase. This article reviews AI applications for mammography, sonography, and MRI that are currently available for clinical use. In addition, clinical implementation and the future of AI for breast imaging are discussed.

Deep learning prediction of axillary lymph node status using ultrasound images

OBJECTIVE

To investigate the ability of our convolutional neural network (CNN) to predict axillary lymph node metastasis using primary breast cancer ultrasound (US) images.

METHODS

In this IRB-approved study, 338 US images (two orthogonal images) from 169 patients from 1/2014-12/2016 were used. Suspicious lymph nodes were seen on US and patients subsequently underwent core-biopsy. 64 patients had metastatic lymph nodes. A custom CNN was utilized on 248 US images from 124 patients in the training dataset and tested on 90 US images from 45 patients. The CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The 9 convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Feature maps were down-sampled using strided convolutions. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer and a final SoftMax score threshold of 0.5 from the average of raw logits from each pixel was used for two class classification (metastasis or not).

RESULTS

Our CNN achieved an AUC of 0.72 (SD ± 0.08) in predicting axillary lymph node metastasis from US images in the testing dataset. The model had an accuracy of 72.6% (SD ± 8.4) with a sensitivity and specificity of 65.5% (SD ± 28.6) and 78.9% (SD ± 15.1) respectively. Our algorithm is available to be shared for research use. (https://github.com/stmutasa/MetUS).

CONCLUSION

It's feasible to predict axillary lymph node metastasis from US images using a deep learning technique. This can potentially aid nodal staging in patients with breast cancer.

A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultrasound-Detected Suspicious Breast Masses

We developed a machine learning model based on radiomics to predict the BI-RADS category of ultrasound-detected suspicious breast lesions and support medical decision-making towards short-interval follow-up versus tissue sampling. From a retrospective 2015–2019 series of ultrasound-guided core needle biopsies performed by four board-certified breast radiologists using six ultrasound systems from three vendors, we collected 821 images of 834 suspicious breast masses from 819 patients, 404 malignant and 430 benign according to histopathology. A balanced image set of biopsy-proven benign (n = 299) and malignant (n = 299) lesions was used for training and cross-validation of ensembles of machine learning algorithms supervised during learning by histopathological diagnosis as a reference standard. Based on a majority vote (over 80% of the votes to have a valid prediction of benign lesion), an ensemble of support vector machines showed an ability to reduce the biopsy rate of benign lesions by 15% to 18%, always keeping a sensitivity over 94%, when externally tested on 236 images from two image sets: (1) 123 lesions (51 malignant and 72 benign) obtained from two ultrasound systems used for training and from a different one, resulting in a positive predictive value (PPV) of 45.9% (95% confidence interval 36.3–55.7%) versus a radiologists’ PPV of 41.5% (p < 0.005), combined with a 98.0% sensitivity (89.6–99.9%); (2) 113 lesions (54 malignant and 59 benign) obtained from two ultrasound systems from vendors different from those used for training, resulting into a 50.5% PPV (40.4–60.6%) versus a radiologists’ PPV of 47.8% (p < 0.005), combined with a 94.4% sensitivity (84.6–98.8%). Errors in BI-RADS 3 category (i.e., assigned by the model as BI-RADS 4) were 0.8% and 2.7% in the Testing set I and II, respectively. The board-certified breast radiologist accepted the BI-RADS classes assigned by the model in 114 masses (92.7%) and modified the BI-RADS classes of 9 breast masses (7.3%). In six of nine cases, the model performed better than the radiologist did, since it assigned a BI-RADS 3 classification to histopathology-confirmed benign masses that were classified as BI-RADS 4 by the radiologist.

Accuracy of ultrasonic artificial intelligence in diagnosing benign and malignant breast diseases: A protocol for systematic review and meta-analysis

BACKGROUND

Artificial intelligence system is a deep learning system based on computer-assisted ultrasonic image diagnosis, which can extract morphological features of breast mass and conduct objective and efficient image analysis, thus automatically intelligent classification of breast mass, avoiding subjective error and improving the accuracy of diagnosis.[1-2] A large number of studies have confirmed that artificial intelligence (AI) has high effectiveness and reliability in the differential diagnosis of benign and malignant breast diseases.[3-4] However, the results of these studies have been contradictory. Therefore, this meta-analysis tested the hypothesis that artificial intelligence system is accurate in distinguishing benign and malignant breast diseases.

METHODS

We will search PubMed, Web of Science, Cochrane Library, and Chinese biomedical databases from their inceptions to the November 20, 2021, without language restrictions. Two authors will independently carry out searching literature records, scanning titles and abstracts, full texts, collecting data, and assessing risk of bias. Review Manager 5.2 and Stata14.0 software will be used for data analysis.

RESULTS

This systematic review will determine the accuracy of AI in the differential diagnosis of benign and malignant breast diseases.

CONCLUSION

Its findings will provide helpful evidence for the accuracy of AI in the differential diagnosis of benign and malignant breast diseases.

SYSTEMATIC REVIEW REGISTRATION

INPLASY2021110087.

Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams

Though consistently shown to detect mammographically occult cancers, breast ultrasound has been noted to have high false-positive rates. In this work, we present an AI system that achieves radiologist-level accuracy in identifying breast cancer in ultrasound images. Developed on 288,767 exams, consisting of 5,442,907 B-mode and Color Doppler images, the AI achieves an area under the receiver operating characteristic curve (AUROC) of 0.976 on a test set consisting of 44,755 exams. In a retrospective reader study, the AI achieves a higher AUROC than the average of ten board-certified breast radiologists (AUROC: 0.962 AI, 0.924 ± 0.02 radiologists). With the help of the AI, radiologists decrease their false positive rates by 37.3% and reduce requested biopsies by 27.8%, while maintaining the same level of sensitivity. This highlights the potential of AI in improving the accuracy, consistency, and efficiency of breast ultrasound diagnosis.

AI-enhanced breast imaging: Where are we and where are we heading?

Significant advances in imaging analysis and the development of high-throughput methods that can extract and correlate multiple imaging parameters with different clinical outcomes have led to a new direction in medical research. Radiomics and artificial intelligence (AI) studies are rapidly evolving and have many potential applications in breast imaging, such as breast cancer risk prediction, lesion detection and classification, radiogenomics, and prediction of treatment response and clinical outcomes. AI has been applied to different breast imaging modalities, including mammography, ultrasound, and magnetic resonance imaging, in different clinical scenarios. The application of AI tools in breast imaging has an unprecedented opportunity to better derive clinical value from imaging data and reshape the way we care for our patients. The aim of this study is to review the current knowledge and future applications of AI-enhanced breast imaging in clinical practice.

BI-RADS 3 on Screening Breast Ultrasound: What Is It and What Is the Appropriate Management?

US is widely used in breast imaging for diagnostic purposes and is also used increasingly for supplemental screening in women with dense breasts. US frequently depicts masses that are occult on mammography, even after tomosynthesis, and the vast majority of such masses are benign. Many masses seen only on screening US are easily recognized as benign simple cysts. Probably benign, BI-RADS 3, or low suspicion, BI-RADS 4A masses are also common and often prompt short-interval follow-up or biopsy, respectively, yet the vast majority of these are benign. This review details appropriate characterization, classification, and new approaches to the management of probably benign masses seen on screening US that can reduce false positives and, thereby, reduce costs and patient anxiety.

Incorporating Peer Learning Into Your Breast Imaging Practice

Traditional score-based peer review has come under scrutiny in recent years, as studies have demonstrated it to be generally ineffective at improving quality. Many practices and programs are transitioning to a peer learning model to replace or supplement traditional peer review. Peer learning differs from traditional score-based peer review in that the emphasis is on sharing learning opportunities and creating an environment that fosters discussion of errors in a nonpunitive forum with the goal of improved patient care. Creating a just culture is central to fostering successful peer learning. In a just culture, mistakes can be discussed without shame or fear of retribution and the focus is on systems improvement rather than individual blame. Peer learning, as it pertains to breast imaging, can occur in many forms and venues. Examples of the various formats in which peer learning can occur include through individual colleague interaction, as well as divisional, multidisciplinary, department-wide, and virtual conferences, and with the assistance of artificial intelligence. Incorporating peer learning into the practice of breast imaging aims to reduce delayed diagnoses of breast cancer and optimize patient care.