BI-RADS Research Articles

Inter-reader agreement of the BI-RADS CEM lexicon.

The purpose of this study was to assess the inter-reader agreement of the breast imaging reporting and data system (BI-RADS) contrast-enhanced mammography (CEM) lexicon. In this IRB-approved, single-center, retrospective study, three breast radiologists, each with different levels of experience, reviewed 462 lesions in 421 routine clinical CEM according to the fifth edition of the BI-RADS lexicon for mammography and to the first version of the BI-RADS lexicon for CEM. Readers were blinded to patient outcomes and evaluated breast and lesion features on low-energy (LE) images (breast density, type of lesion, associated architectural distortion), lesion features on recombined (RC) images (type of enhancement, characteristic of mass enhancement, non-mass enhancement or enhancing asymmetry), and provided a final BI-RADS assessment. The inter-reader agreement was calculated for each evaluated feature using Fleiss' kappa coefficient. Sensitivity and specificity were calculated. The inter-reader agreement was moderate to substantial for breast density (ĸ = 0.569), type of lesion on LE images (ĸ = 0.654), and type of enhancement (ĸ = 0.664). There was a moderate to substantial agreement on CEM mass enhancement descriptors. The agreement was fair to moderate for non-mass enhancement and enhancing asymmetry descriptors. Inter-reader agreement for LE and LE with RC BI-RADS assessment was moderate (ĸ = 0.421) and fair (ĸ = 0.364). Diagnostic performance was good and comparable for all readers. Inter-reader agreement of the CEM lexicon was moderate to substantial for most features. There was a low agreement for some RC descriptors, such as non-mass enhancement and enhancing asymmetry, and BI-RADS assessment, but this did not impact the diagnostic performance. Question Data on the reproducibility and inter-reader agreement for the first version of the BI-RADS lexicon dedicated to CEM are missing. Finding The inter-reader agreement for the lexicon was overall substantial to moderate, but it was lower for the descriptors for non-mass enhancement and enhancing asymmetry. Clinical relevance A common lexicon simplifies communication between specialists in clinical practice. The good inter-reader agreement confirms the effectiveness of the CEM-BIRADS in ensuring consistent communication. Detailed definitions of some descriptors (non-mass, enhancing asymmetry) are needed to ensure higher agreements.

Image Features and Diagnostic Value of Contrast-Enhanced Ultrasound for Ductal Carcinoma In Situ of the Breast: Preliminary Findings.

To explore the image features and the diagnostic value of contrast-enhanced ultrasound (CEUS) for ductal carcinoma in situ (DCIS) of the breast. A total of 96 female patients with a solitary and histologically proven DCIS were analyzed retrospectively, and 100 female cases of invasive ductal carcinoma (IDC) lesions were used as the control group. The Breast Imaging Reporting and Data System (BI-RADS) category of breast lesions was assessed according to conventional ultrasound features. The DCIS lesions were classified into mass type and non-mass type. The CEUS characteristics of these breast lesions were retrospectively analyzed qualitatively and quantitatively. The final gold standard was biopsy or surgery with histo-pathological examination. Comparing the ultrasound images of DCIS with that of IDC, there were significant differences in echo pattern, calcification morphology, and calcification distribution (p < .05 for all). There was a significant difference between DCIS and IDC in enhancement intensity, perfusion defects, peripheral high enhancement, intratumoral vessels, and arrival time (AT) (p < .05 for all). In the logistic multivariate regression analysis, two indicators linked with DCIS were recognized: perfusion defects (p = .002) and peripheral high enhancement (p < .001). In forecasting DCIS, the logistic regression equation resulted in an AUC of 0.689, a specificity of 0.720, and a sensitivity of 0.563. CEUS showed differences in enhancement characteristics between DCIS and IDC, with perfusion defects and peripheral high enhancement being associated with DCIS.

Machine Learning Assessment of Background Parenchymal Enhancement in Breast Cancer and Clinical Applications: A Literature Review

Background Parenchymal Enhancement (BPE) on breast MRI holds promise as an imaging biomarker for breast cancer risk and prognosis. The ability to identify those at greatest risk can inform clinical decisions, promoting early diagnosis and potentially guiding strategies for prevention such as risk-reduction interventions with the use of selective estrogen receptor modulators and aromatase inhibitors. Currently, the standard method of assessing BPE is based on the Breast Imaging-Reporting and Data System (BI-RADS), which involves a radiologist’s qualitative categorization of BPE as minimal, mild, moderate, or marked on contrast-enhanced MRI. This approach can be subjective and prone to inter/intra-observer variability, and compromises accuracy and reproducibility. In addition, this approach limits qualitative assessment to 4 categories. More recently developed methods using machine learning/artificial intelligence (ML/AI) techniques have the potential to quantify BPE more accurately and objectively. This paper will review the current machine learning/AI methods to determine BPE, and the clinical applications of BPE as an imaging biomarker for breast cancer risk prediction and prognosis.

Performance of breast MRI for high-risk screening during lactation.

To assess the diagnostic performance of breast MRI during lactation in the setting of high-risk breast cancer screening. Screening breast MRIs performed between April 2008 and March 2024 were retrospectively reviewed. Background parenchymal enhancement (BPE) grade was compared between lactating patients and patients who recently stopped lactating using the Mann-Whitney test. Breast Imaging Reporting and Data System (BI-RADS) scores prevalence rates were compared between lactating patients and controls encompassing young non-lactating patients using the Chi-square test. Diagnostic performance was calculated for patients with a biopsy reference or a 1-year radiologic follow-up. One-hundred forty-two screening breast MRIs were performed in lactating patients (n = 104, median age, 36.0 ± 6.0 years). Marked BPE appeared in 82% of cases (116/142), with a higher BPE grade in exams performed during lactation as compared with those performed in patients who had recently ceased lactating (p < 0.001). Screening MRIs performed during lactation had a higher rate of BI-RADS 3 scores (40/142, 28% vs. 683/8922, 7%, p < 0.001) and a lower rate of BI-RADS 1/2 scores (88/142, 62% vs. 7549/8922, 84.6%, p = 0.002) compared with those performed in controls (n = 8922). One pregnancy-associated breast cancer was detected, and one interval-cancer occurred. All MRI-guided biopsies were negative (n = 13). Screening breast MRI during lactation had 50% sensitivity (1/2), 60% specificity (72/120), 2.0% positive predictive value (1/49), and 98.6% negative predictive value (71/82). The efficacy of breast MRI for high-risk screening during lactation is limited by prominent BPE, leading to an increased rate of BI-RADS 3 categorization and diminished overall specificity. Question Studies on breast MRI during lactation were solely focused on studies conducted in patients with known cancer but not in the screening setting. Findings Screening breast MRI during lactation usually results in marked background parenchymal enhancement, negatively impacting its diagnostic performance. Clinical relevance Despite the lower performance, and amidst the significant risk of pregnancy-associated breast cancer, this screening approach remains relevant for lactating patients with high-risk profiles, such as BReast Cancer (BRCA) carriers. Radiologists should be familiar with the normal appearance of breast MRI duringlactation.

Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o

BackgroundTo assess the reliability and comprehensibility of breast radiology reports simplified by artificial intelligence using the large language model (LLM) ChatGPT-4o.MethodsA radiologist with 20 years’ experience selected 21 anonymized breast radiology reports, 7 mammography, 7 breast ultrasound, and 7 breast magnetic resonance imaging (MRI), categorized according to breast imaging reporting and data system (BI-RADS). These reports underwent simplification by prompting ChatGPT-4o with “Explain this medical report to a patient using simple language”. Five breast radiologists assessed the quality of these simplified reports for factual accuracy, completeness, and potential harm with a 5-point Likert scale from 1 (strongly agree) to 5 (strongly disagree). Another breast radiologist evaluated the text comprehension of five non-healthcare personnel readers using a 5-point Likert scale from 1 (excellent) to 5 (poor). Descriptive statistics, Cronbach’s α, and the Kruskal–Wallis test were used.ResultsMammography, ultrasound, and MRI showed high factual accuracy (median 2) and completeness (median 2) across radiologists, with low potential harm scores (median 5); no significant group differences (p ≥ 0.780), and high internal consistency (α > 0.80) were observed. Non-healthcare readers showed high comprehension (median 2 for mammography and MRI and 1 for ultrasound); no significant group differences across modalities (p = 0.368), and high internal consistency (α > 0.85) were observed. BI-RADS 0, 1, and 2 reports were accurately explained, while BI-RADS 3–6 reports were challenging.ConclusionThe model demonstrated reliability and clarity, offering promise for patients with diverse backgrounds. LLMs like ChatGPT-4o could simplify breast radiology reports, aid in communication, and enhance patient care.Relevance statementSimplified breast radiology reports generated by ChatGPT-4o show potential in enhancing communication with patients, improving comprehension across varying educational backgrounds, and contributing to patient-centered care in radiology practice.Key PointsAI simplifies complex breast imaging reports, enhancing patient understanding.Simplified reports from AI maintain accuracy, improving patient comprehension significantly.Implementing AI reports enhances patient engagement and communication in breast imaging.Graphical

Role of Image-Guided Biopsy in Nonpalpable Breast Lesions: A Study in the Sub-Himalayan Region of North India

Background Nonpalpable breast lesions pose a challenge in their early diagnosis. Image-guided biopsy is preferred in these cases so that a pathological diagnosis of breast carcinoma is reached timely for a better prognosis as the disease has an increased chance of successful outcome with early identification and treatment. Objective The study aims at evaluating the role of stereotactic core needle biopsy (CNB) and percutaneous ultrasound-guided core needle biopsy (US-CNB) in diagnosing suspicious nonpalpable breast lesions. Methods Our study included 35 patients with nonpalpable breast lesions and having a Breast Imaging Reporting and Data System (BI-RADS) risk assessment category IV or V on mammography or sonography. These 35 lesions were subjected to percutaneous image-guided (stereotactic or US) biopsy for histopathological analysis. Results Out of a total of 35 cases, 17 were pathologically malignant (48.6%), with the most common subtype being invasive ductal carcinoma (82.3%). Twenty-nine cases underwent US-CNB, 16 (55.1%) of which were malignant and 13 (44.8%) were benign on histopathological evaluation (HPE). The remaining six cases, which on mammography showed no mass but suspicious malignant calcification only, were subjected to stereotactic CNB, out of which one (16.6%) was malignant and five (83.3%) were benign on HPE. Hence, the lesions visible on sonography were more likely to be malignant. Conclusion Sonography and mammography play a complimentary role in detecting breast carcinoma. Percutaneous biopsy under image guidance can be used as an accurate diagnostic alternative to open surgical excisional biopsy to avoid diagnostic delay.

The association between mammographic breast density, epicardial adipose tissue volume and coronary artery disease

Abstract Background Dysfunctional adipose tissue is strongly linked to cardiometabolic disease. Epicardial adipose tissue (EAT) which is measurable on cardiac computed tomography (CT) is well correlated with cardiovascular disease (CVD), however it is not reported clinically. Breast mammography mandates reporting of breast density (BD), which is also a marker of breast adipose tissue quantity with less dense breasts indicating greater adipose tissue volume. Given the widespread use of screening mammography, this presents an opportunity to employ BD as a possible surrogate for CVD risk. Purpose To evaluate the correlation between BD, EAT and coronary artery disease (CAD). Methods Single-centre, retrospective, cross-sectional study, including women who had both clinically indicated coronary computed tomography angiogram (CCTA) and mammography. Epicardial adipose tissue volume (EATv) was quantified using semi-automated software (QFAT 2.0). BD was visually assessed by standard 4-level Breast Imaging-Reporting and Data System (BI-RADS) grade with grade A-B representing low density, and C-D representing high density. CAD was categorised as presence/absence of any coronary artery plaque, and CAD severity was quantified using the Coronary Artery Disease Reporting and Data Systems (CAD-RADS) score, with CAD-RADS 1-2 representing mild disease, CAD-RADS 3 moderate disease and CAD-RADS 4 severe disease. CAD analyses were adjusted for modifiable (hypertension, dyslipidaemia, diabetes, body mass index) and non-modifiable (age, past smoking, family history, breast cancer) risk factors. Logistic regression was performed with results presented as Odds Ratio (OR) and [95% Confidence Intervals]. Results Among 153 patients (mean age 62±10), 103 (67.3%) had low BD (high breast adiposity). Compared with high BD, low BD patients were older, had greater rates of hypertension, had significantly higher mean EAT (106.6 ± 43.0 vs 81.0 ± 31.6ml, p&amp;lt;0.001) (Figure 1), and body mass index (30.5 ± 6.3 vs 26.4 ± 5.4kg/m², p&amp;lt;0.001). Adjusted for age and hypertension, EATv remained independently predictive of low BD (OR:1.02 [1.01-1.03], p=0.006). Low BD made up a higher proportion of mild (76.5%), moderate (73.9%) and severe (80.0%) disease. Low BD was strongly associated with presence of CAD (prevalence 75% vs 48%, OR 3.21 [1.58-6.53], p=0.001) independent of EATv (p=0.25), and independent of modifiable (OR: 2.69 [1.24-5.92], p=0.012) and non-modifiable (OR: 2.42 [1.04-5.85], p=0.047) risk factors (Figure 2). Conclusions Low breast density is associated with higher EATv and independently associated with CAD presence beyond EATv and other risk factors. Consequently, mammographic breast density may act as an early risk identification tool for CAD in women.

Automated breast density assessment for full-field digital mammography and digital breast tomosynthesis.

Mammographic density is a strong risk factor for breast cancer (BC) and is reported clinically as part of Breast Imaging Reporting and Data System (BI-RADS) results issued by radiologists. Automated assessment of density is needed that can be used for both full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) as both types of exams are acquired in standard clinical practice. We trained a deep learning model to automate the estimation of BI-RADS density from a prospective Washington University (WashU) clinic-based cohort of 9,714 women, entering into the cohort in 2013 with follow-up through, October 31, 2020. The cohort included 27% non-Hispanic Black women. The trained algorithm was assessed in an external validation cohort that included 18,360 women screened at Emory from January 1, 2013 and followed through December 31, 2020 that included 42% non-Hispanic Black women. Our model-estimated BI-RADS density demonstrated substantial agreement with the density as assessed by radiologist. In the external validation, the agreement with radiologists for category B 81% and C 77% for FFDM and B 83% and C 74% for DBT show important distinction for separation of women with dense breast. We obtained a Cohen's κ of 0.72 (95% CI, 0.71, 0.73) in FFDM and 0.71 (95% CI 0.69, 0.73) in DBT. We provided a consistent and fully automated BI-RADS estimation for both FFDM and DBT using a deep learning model. The software can be easily implemented anywhere for clinical use and risk prediction.

TECRR: a benchmark dataset of radiological reports for BI-RADS classification with machine learning, deep learning, and large language model baselines

BackgroundRecently, machine learning (ML), deep learning (DL), and natural language processing (NLP) have provided promising results in the free-form radiological reports’ classification in the respective medical domain. In order to classify radiological reports properly, a high-quality annotated and curated dataset is required. Currently, no publicly available breast imaging-based radiological dataset exists for the classification of Breast Imaging Reporting and Data System (BI-RADS) categories and breast density scores, as characterized by the American College of Radiology (ACR). To tackle this problem, we construct and annotate a breast imaging-based radiological reports dataset and its benchmark results. The dataset was originally in Spanish. Board-certified radiologists collected and annotated it according to the BI-RADS lexicon and categories at the Breast Radiology department, TecSalud Hospitals Monterrey, Mexico. Initially, it was translated into English language using Google Translate. Afterwards, it was preprocessed by removing duplicates and missing values. After preprocessing, the final dataset consists of 5046 unique reports from 5046 patients with an average age of 53 years and 100% women. Furthermore, we used word-level NLP-based embedding techniques, term frequency-inverse document frequency (TF-IDF) and word2vec to extract semantic and syntactic information. We also compared the performance of ML, DL and large language models (LLMs) classifiers for BI-RADS category classification.ResultsThe final breast imaging-based radiological reports dataset contains 5046 unique reports. We compared K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient-Boosting (GB), Extreme Gradient Boosting (XGB), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT) and Biomedical Generative Pre-trained Transformer (BioGPT) classifiers. It is observed that the BioGPT classifier with preprocessed data performed 6% better with a mean sensitivity of 0.60 (95% confidence interval (CI), 0.391-0.812) compared to the second best performing classifier BERT, which achieved mean sensitivity of 0.54 (95% CI, 0.477-0.607).ConclusionIn this work, we propose a curated and annotated benchmark dataset that can be used for BI-RADS and breast density category classification. We also provide baseline results of most ML, DL and LLMs models for BI-RADS classification that can be used as a starting point for future investigation. The main objective of this investigation is to provide a repository for the investigators who wish to enter the field to push the boundaries further.

Interpretable diagnosis of breast lesions in ultrasound imaging using deep multi-stage reasoning

Objective.Ultrasound is the primary screening test for breast cancer. However, providing an interpretable auxiliary diagnosis of breast lesions is a challenging task. This study aims to develop an interpretable auxiliary diagnostic method to enhance usability in human-machine collaborative diagnosis.Approach.To address this issue, this study proposes the deep multi-stage reasoning method (DMSRM), which provides individual and overall breast imaging-reporting and data system (BI-RADS) assessment categories for breast lesions. In the first stage of the DMSRM, the individual BI-RADS assessment network (IBRANet) is designed to capture lesion features from breast ultrasound images. IBRANet performs individual BI-RADS assessments of breast lesions using ultrasound images, focusing on specific features such as margin, contour, echogenicity, calcification, and vascularity. In the second stage, evidence reasoning (ER) is employed to achieve uncertain information fusion and reach an overall BI-RADS assessment of the breast lesions.Main results.To evaluate the performance of DMSRM at each stage, two test sets are utilized: the first for individual BI-RADS assessment, containing 4322 ultrasound images; the second for overall BI-RADS assessment, containing 175 sets of ultrasound image pairs. In the individual BI-RADS assessment of margin, contour, echogenicity, calcification, and vascularity, IBRANet achieves accuracies of 0.9491, 0.9466, 0.9293, 0.9234, and 0.9625, respectively. In the overall BI-RADS assessment of lesions, the ER achieves an accuracy of 0.8502. Compared to independent diagnosis, the human-machine collaborative diagnosis results of three radiologists show increases in positive predictive value by 0.0158, 0.0427, and 0.0401, in sensitivity by 0.0400, 0.0600 and 0.0434, and in area under the curve by 0.0344, 0.0468, and 0.0255.Significance.This study proposes a DMSRM that enhances the transparency of the diagnostic reasoning process. Results indicate that DMSRM exhibits robust BI-RADS assessment capabilities and provides an interpretable reasoning process that better suits clinical needs.

Effect of patient age and breast parenchymal density on Breast Imaging-Reporting and Data System (BIRADS-4) Subcategorization

Background &amp; Objectives: BI-RADS (Breast Imaging-Reporting and Data System) is a standard radiological risk assessment for breast lesions, including six categories, of which category four is the widest range of likelihood cancer risk (2% to 95%). This study aimed to evaluate the effect of patient age and ACR breast density on the positive predictive value (PPV) of BI-RADS 4 subcategorization (4A, 4B, and 4C). Methods: A retrospective study was conducted at King Fahed Hospital (KFH) between September 1, 2021, and June 30, 2022. PPV was calculated based on a histopathological report for all lesions. The correlation was made with patients’ age groups ranging from &lt; 45 years, 45-55 years, and &gt; 55 years and four types of breast density on mammography. We used IBM-SPSS for data synthesis. The Chi-square test was used to assess any correlation between variables. A p-value &lt; 0.05 was considered statistically significant. Results: The mean age was 44.62 ±14.32. Of the 248 cases, 81% were benign, 17% were malignant, and 2% were high-risk lesions. The age-related PPV of each BI-RADS category showed no significant differences among all age groups. However, the breast composition-related PPV cases with BI-RADS categories differed significantly within subcategory 4C (p-value&lt;0.001). Conclusions: There were no positive relationships between increasing age and PPV in BI-RADS 4 subcategories 4A, B, and C. Breast composition-related PPV showed significant differences with BI-RADS 4C subcategories. doi: https://doi.org/10.12669/pjms.40.10.9552 How to cite this: Ghunaim HA. Effect of patient age and breast parenchymal density on Breast Imaging-Reporting and Data System (BIRADS-4) Subcategorization. Pak J Med Sci. 2024;40(10):2356-2362. doi: https://doi.org/10.12669/pjms.40.10.9552 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Ultrasound strain elastography to improve diagnostic performance of breast lesions by reclassifying BI-RADS 3 and 4a lesions: a multicenter diagnostic study.

To investigate the added value of strain elastography (SE) by recategorizing ultrasound (US) Breast Imaging Reporting and Data System (BI-RADS) 3 and 4a lesions. A total of 4371 patients underwent US and SE with BI-RADS 2-5 categories solid breast lesions were included from thirty-two hospitals. We evaluated the elastographic images according to elasticity scores (ES) and strain ratios (SR). Three combined methods (BI-RADS+ES, BI-RADS+SR, BI-RADS+ES+SR) and two reclassified methods were used (method one: upgrading BI-RADS 3 and downgrading BI-RADS 4a, method two: downgrading BI-RADS 4a alone). The diagnostic performance and the potential reduction of unnecessary biopsies were evaluated. Combining BI-RADS with SE had a higher area under the curve (AUC) than BI-RADS alone (0.822-0.898 vs. 0.794, P<0.01). For reclassified method one, the sensitivity, specificity, and accuracy were 99.36%, 66.70%, 78.36% for BI-RADS+ES and 98.01%, 66.45%, 77.72% for BI-RADS+SR, and 99.42%, 66.70%, 78.38% for BI-RADS+ES+SR, respectively. For reclassified method two, the sensitivity, specificity, and accuracy were 99.17%, 70.72%, 80.87% for BI-RADS+ES and 97.76%, 81.75%, 87.46% for BI-RADS+SR, and 99.23%, 69.83%, 80.32% for BI-RADS+ES+SR, respectively. Downgrading BI-RADS 4a alone had higher AUC, specificity, and accuracy (P<0.01) and similar sensitivity (P>0.05) to upgrading BI-RADS 3 and downgrading BI-RADS 4a. Combining SE with BI-RADS could help reduce unnecessary biopsies by 17.64%-55.20%. Combining BI-RADS with SE improved the diagnostic performance in distinguishing benign from malignant lesions and could decrease false-positive breast biopsy rates. Downgrading BI-RADS 4a lesions alone might be sufficient for achieving good diagnostic performance. Downgrading BI-RADS category 4a lesions alone had higher AUC, specificity, and accuracy, and similar sensitivity to upgrading or downgrading BI-RADS category 3 and 4a lesions.

Complementing Mammography Screening with Automated 3D Ultrasound in Women with High-Density Breasts

Background. In early breast screening structure, an important factor is breast density. Women with types C and D breast density according to American College of Radiology (ACR) classification have 4–6-fold increased risk of cancer compared to women with type A breast density. With this type of density, the effectiveness of diagnostic mammography (MG) is significantly decreased. Today, automated breast 3D ultrasound can be considered as an additional screening method in women with breast structure types C and D according to ACR.Objective: to perform a comparative analysis of the diagnostic efficacy of 2D and 3D ultrasound in women aged 40 years and older with high breast tissue density.Material and methods. Retro-prospective, observational, single-center study was conducted. From February 2019 to May 2023, 1283 patients aged 40 years and older were examined. The patients were divided into two groups. In group A, women underwent 2D ultrasound and MG. In group B, additionally to these methods, 3D ultrasound was performed. In both groups, the results were evaluated according to Breast Imaging-Reporting and Data System (BI-RADS). Based on the obtained data, the following indicators were determined: positive (PPV) and negative (NPV) predictive values, sensitivity, specificity and accuracy of all methods. For 2D and 3D ultrasound, the predictive model areas under curve (AUC) of receiver operating characteristic (ROC) were calculated.Results. MG method showed PPV 0.89, NPV 0.93, sensitivity 0.53, specificity 0.99, and balanced accuracy 0.76. Indicators for 2D ultrasound demonstrated PPV 0.8, NPV 0.98, sensitivity 0.9, specificity 0.97, balanced accuracy 0.93, AUC ROC 0.968. The results for 3D ultrasound were as follows: PPV 0.97, NPV 0.97, sensitivity 0.9, specificity 0.99, balanced accuracy 0.94, AUC ROC 0.98.Conclusion. The diagnostic efficiency of breast automated 3D ultrasound in patients aged 40 years and older is comparable to 2D ultrasound in terms of sensitivity, and it’s better in terms of accuracy, specificity. The prognostic model of 3D ultrasound is also better compared to 2D ultrasound.

Diagnosis and management of Rosai–Dorfman disease of the breast: Case report and literature review

AbstractRosai–Dorfman disease (RDD) is a rare subtype of non–Langerhans cell histiocytosis. It is a benign disease with variable presentations, with breast involvement being an uncommon manifestation. In this paper, we present a case of breast RDD in a 59‐year‐old Chinese woman who presented with a painless, enlarging mass in her right breast, accompanied by skin changes and no palpable axillary lymph node. A mammogram and breast ultrasonography revealed a progressively enlarging lesion with a suspicious axillary lymph node, leading to an upgrade from Breast Imaging Reporting and Data System (BIRADS) score of 3 to 4A on interval imaging. Core biopsy of the breast mass and cytology of the right axillary lymph node confirmed extranodal RDD. After a 5‐year period of observation, excision was performed due to persistent symptoms. Local recurrence of RDD, with skin discolouration and thickening, was confirmed by skin biopsy 1 year and 9 months after the operation. To the best of our knowledge, this is the first reported case of breast RDD in Hong Kong.

Exploring the accuracy of embedded ChatGPT-4 and ChatGPT-4o in generating BI-RADS scores: a pilot study in radiologic clinical support

This study evaluates the accuracy of ChatGPT-4 and ChatGPT-4o in generating Breast Imaging Reporting and Data System (BI-RADS) scores from radiographic images. We tested both models using 77 breast cancer images from radiopaedia.org, including mammograms and ultrasounds. Images were analyzed in separate sessions to avoid bias. ChatGPT-4 and ChatGPT-4o achieved a 66.2 % accuracy across all BI-RADS cases. Performance was highest in BI-RADS 5 cases, with ChatGPT-4 and ChatGPT4o scoring 84.4 % and 88.9 %, respectively. However, both models struggled with BIRADS 1–3 cases, often assigning higher severity ratings. This study highlights the limitations of current LLMs in accurately grading these images and emphasizes the need for further research in these technologies before clinical integration.

Correlation between radiological imaging and histopathological findings in patients with breast lump

Background: Breast cancer is the most common cancer among women globally and the second leading cause of cancer-related deaths, after lung cancer. Early detection via routine screening is crucial, as not all breast lumps are cancerous and benign lumps do not always progress to cancer. To improve diagnostic accuracy, a triple assessment approach is used, combining radiological imaging, pathological diagnosis, and clinical examination. Techniques such as mammography, ultrasonography, and fine needle aspiration cytology (FNAC) are key to this evaluation. This study assesses the breast imaging reporting and data system (BIRADS) scoring system’s diagnostic accuracy by comparing radiological techniques with histopathological findings. Methods: The study involved 100 patients with breast lumps, categorised into three groups based on BIRADS scores: group A (BIRADS I-III), group B (BIRADS IV), and group C (BIRADS V). Data analysis using chi-square and student’s t tests were done. Results: In our study we found that accuracy of BIRADS score: sensitivity: 88.9%, specificity: 89.5%, positive predictive value: 97.3%, negative predictive value: 65.4% and diagnostic accuracy: 81%. Conclusions: The study demonstrated a high incidence of fibroadenoma (66%), others (3%) as benign cases and invasive ductal carcinoma (31%) malignant cases. The study highlights the importance of accurate diagnosis and targeted screening, especially in high-risk groups such as postmenopausal women and those with a family history of breast cancer. The findings affirm the high sensitivity and specificity of the BIRADS system as a valuable diagnostic tool.

Abstract C003: Multimodal and multiplexed spatial regulation of the breast collagen proteome: Comparative analysis in Black and White women from normal breast tissue and triple-negative breast cancer

Abstract Non-Hispanic Black women (BW) are diagnosed with more aggressive breast cancer subtypes at younger ages and have higher mortality rates compared to non-Hispanic White women (WW). Within the breast microenvironment emergent data shows that stromal collagen plays a significant role in aggressiveness of breast cancer linked to ancestral traits. However, the molecular composition of collagen stroma has yet to be linked to ancestry and aggressiveness of breast cancer. The purpose of this study was to evaluate the microenvironment within ancestry-defined normal breast and triple-negative breast cancer (TNBC) to understand spatial regulation of collagen stroma that may link to ancestral differences in cancer. Multimodal, multiplexed spatial analyses were performed. Techniques included Second Harmonic Generation (SHG) to measure collagen fibers, mass spectrometry imaging to measure the collagen proteome, and mass-tagged antibody panels to investigate immune signatures in TNBC. Normal breast tissues were obtained from the Susan G. Komen Tissue Bank, African American (AA; n=20) and European American (EA; n=20) samples were annotated with risk scores, age, Body Mass Index (BMI), Breast Imaging-Reporting and Data System (BI-RADS), continental ancestry, and family history. Triple-negative breast cancer (TNBC, n=80) tissues from BW with extensive clinical annotations including age, BMI, stage, metastasis, and survival were evaluated in comparison to 20+ TNBC tissues from WW. In the normal breast cohort, evaluation of BMI (overweight and obese) within ancestry groups showed significant but opposing differences in fiber width measurements. As BMI increases, AA showed statistically thicker fibers while EA showed statistically thinner fibers. At the protein level, two types of collagens were significantly higher in EA and one type is higher in AA. Within the TNBC cohort, collagen fiber length and width measurements by SHG were significantly shorter and thinner in stage II compared to stage I but no other stage comparisons were significant. This may indicate that ECM remodeling occurs at earlier stages in TNBC. Initial analyses showed that collagen peptide intensities significantly vary by TNBC stage (75 peptides, ANOVA test FDR p-value &amp;lt; 0.05). In the cohort of women who survived, 90 ECM peptides significantly correlated with collagen fiber widths, indicating a relationship between collagen physical and molecular properties within a defined region. Seven immune markers defined differences in survival when grouped by high vs low expression within tumor regions. These markers include CD20 (Hazard Ratio HR = 7.99, p-value = 0.002) and PD-1 (HR = 3.68, p-value = 0.048), which have both been studied in breast cancer. Current work focuses on collagen peptide post-translational modifications that may differ in TNBC patients by vital status and are detected in normal breast at risk of cancer. These findings support that molecular composition in breast stroma contributes to aggressive ancestral traits of breast cancer risk and triple-negative breast cancer. Citation Format: Jaclyn B. Dunne, Heather Jensen-Smith, Laura Spruill, Taylor S. Hulahan, Jade K. Macdonald, George E. Sandusky, M. A. Hollingsworth, Anand S. Mehta, Richard R. Drake, Jeffrey R. Marks, Harikrishna Nakshatri, Marvella E. Ford, Peggi M. Angel. Multimodal and multiplexed spatial regulation of the breast collagen proteome: Comparative analysis in Black and White women from normal breast tissue and triple-negative breast cancer [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr C003.

Evaluating text and visual diagnostic capabilities of large language models on questions related to the Breast Imaging Reporting and Data System Atlas 5th edition.

This study aimed to evaluate the performance of large language models (LLMs) and multimodal LLMs in interpreting the Breast Imaging Reporting and Data System (BI-RADS) categories and providing clinical management recommendations for breast radiology in text-based and visual questions. This cross-sectional observational study involved two steps. In the first step, we compared ten LLMs (namely ChatGPT 4o, ChatGPT 4, ChatGPT 3.5, Google Gemini 1.5 Pro, Google Gemini 1.0, Microsoft Copilot, Perplexity, Claude 3.5 Sonnet, Claude 3 Opus, and Claude 3 Opus 200K), general radiologists, and a breast radiologist using 100 text-based multiple-choice questions (MCQs) related to the BI-RADS Atlas 5th edition. In the second step, we assessed the performance of five multimodal LLMs (ChatGPT 4o, ChatGPT 4V, Claude 3.5 Sonnet, Claude 3 Opus, and Google Gemini 1.5 Pro) in assigning BI-RADS categories and providing clinical management recommendations on 100 breast ultrasound images. The comparison of correct answers and accuracy by question types was analyzed using McNemar's and chi-squared tests. Management scores were analyzed using the Kruskal- Wallis and Wilcoxon tests. Claude 3.5 Sonnet achieved the highest accuracy in text-based MCQs (90%), followed by ChatGPT 4o (89%), outperforming all other LLMs and general radiologists (78% and 76%) (P < 0.05), except for the Claude 3 Opus models and the breast radiologist (82%) (P > 0.05). Lower-performing LLMs included Google Gemini 1.0 (61%) and ChatGPT 3.5 (60%). Performance across different categories of showed no significant variation among LLMs or radiologists (P > 0.05). For breast ultrasound images, Claude 3.5 Sonnet achieved 59% accuracy, significantly higher than other multimodal LLMs (P < 0.05). Management recommendations were evaluated using a 3-point Likert scale, with Claude 3.5 Sonnet scoring the highest (mean: 2.12 ± 0.97) (P < 0.05). Accuracy varied significantly across BI-RADS categories, except Claude 3 Opus (P < 0.05). Gemini 1.5 Pro failed to answer any BI-RADS 5 questions correctly. Similarly, ChatGPT 4V failed to answer any BI-RADS 1 questions correctly, making them the least accurate in these categories (P < 0.05). Although LLMs such as Claude 3.5 Sonnet and ChatGPT 4o show promise in text-based BI-RADS assessments, their limitations in visual diagnostics suggest they should be used cautiously and under radiologists' supervision to avoid misdiagnoses. This study demonstrates that while LLMs exhibit strong capabilities in text-based BI-RADS assessments, their visual diagnostic abilities are currently limited, necessitating further development and cautious application in clinical practice.

Diagnostic Accuracy and Incremental Value of Contrast-Enhanced Mammography Compared With Full Field Digital Mammography in a Tertiary Cancer Care Center.

To assess the diagnostic accuracy and incremental value of contrast-enhanced mammography (CEM) compared with full-field digital mammography (FFDM). A retrospective analysis was performed with 150 consecutive patients who underwent CEM at our institute between November 2020 and February 2021, fulfilling the inclusion criteria. The first round of analysis included a review of FFDM with an interpretation of findings as per the Breast Imaging Reporting and Data System (BIRADS) lexicon and the assignment of the BIRADS category to the detected abnormalities. After this documentation, a second round of analysis included a review of recombined subtracted images of CEM. The diagnostic accuracy of FFDM and CEM was calculated with histopathology as the gold standard. Among the 150 cases assessed, 202 lesions were detected with histopathological correlation, of which 42 were benign and 160 were malignant. The sensitivity of FFDM was 90.6% compared to 98.12% for CEM. The specificity of FFDM was 66.7% compared to 76.19% for CEM. The negative predictive value (NPV) of FFDM was low, at 65.12%; CEM showed a better NPV, at 91.43%. The positive predictive value (PPV) was almost the same, at 94.01% for CEM and 91.19% for FFDM. The area under the curve (AUC) was superior for CEM compared to that of FFDM, with a value of 0.87. FFDM had a low sensitivity, especially in dense breast parenchyma, at 88.79% and a specificity of 70%, whereas CEM showed a higher sensitivity, specificity, and NPV, measuring 99.14%, 76.67%, and 95.83%, respectively. Superior sensitivity and high NPV for CEM make it a preferable modality compared with FFDM, especially in dense breast parenchyma, where CEM overcomes the limitations of FFDM. We conclude that CEM is superior to FFDM in evaluating the extent of disease, additional satellite lesion detection, and ruling out ambiguous findings.

Effects of Left Internal Mammary Artery (LIMA) Harvesting During Coronary Artery By-Pass Grafting Surgery on Benign Breast Diseases

Introduction: Coronary artery bypass surgery of the primary conduits employed in coronary artery bypass grafting surgery (CABG) is the left internal mammary artery (LIMA), which has garnered considerable attention due to its favorable characteristics and outcomes. There are not enough studies examining the relationship between benign breast diseases (BBD) and LIMA removal. This study is one of the pioneering studies investigating the effects of LIMA removal after bypass surgery in patients with benign breast diseases. This study aims to evaluate the effect of LIMA removal on benign breast diseases in female patients undergoing bypass surgery by analyzing pre- and post-operative breast imaging. Material and Methods: A total of 47 of 452 female patients who underwent bypass surgery between February 18, 2019, and December 31, 2021, were included in the study. All patients’ LIMA were harvested and evaluated, regarding any progression of benign breast diseases. Results: There was a significant difference between the Breast Imaging Reporting and Data System (BI-RADS) classes of the patients before and after CABG (p