Background: To assess the reliability and comprehensibility of breast radiology reports simplified by artificial intelligence using the large language model (LLM) ChatGPT-4o. Methods: A 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. Results: Mammography, 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. Conclusion: The 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 statement: Simplified 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 Points: AI 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

Objectives: The Node-RADS score was recently introduced to offer a standardized assessment of lymph node invasion (LNI). We tested its diagnostic performance in accurately predicting LNI in breast cancer (BC) patients with magnetic resonance imaging. The study also explores the consistency of the score across three readers. Materials and methods: A retrospective study was conducted on BC patients who underwent preoperative breast contrast-enhanced magnetic resonance imaging and lymph node dissection between January 2020 and January 2023. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value were calculated for different Node-RADS cut-off values. Pathologic results were considered the gold standard. The overall diagnostic performance was evaluated using receiver operating characteristic curves and the area under the curve (AUC). A logistic regression analysis was performed. Cohen’s Kappa analysis was used for inter-reader agreement. Results: The final population includes 192 patients and a total of 1134 lymph nodes analyzed (372 metastatic and 762 benign). Increasing the Node-RADS cut-off values, specificity and PPV rose from 71.4% to 100% and 76.7% to 100%, respectively, for Reader 1, 69.4% to 100% and 74.6% to 100% for Reader 2, and from 64.3% to 100% and 72% to 100% for Reader 3. Node-RADS > 2 could be considered the best cut-off value due to its balanced performance. Node-RADS exhibited a similar AUC for the three readers (0.97, 0.93, and 0.93). An excellent inter-reader agreement was found (Kappa values between 0.71 and 0.83). Conclusions: The Node-RADS score demonstrated moderate-to-high overall accuracy in identifying LNI in patients with BC, suggesting that the scoring system can aid in the identification of suspicious lymph nodes and facilitate appropriate treatment decisions. Clinical relevance statement: Node-RADS > 2 can be considered the best cut-off for discriminating malignant nodes, suggesting that the scoring system can effectively help identify suspicious lymph nodes by staging the disease and providing a global standardized language for clear communication. Key Points: Axillary lymphadenopathies in breast cancer are crucial for determining the disease stage. Node-RADS was introduced to provide a standardized evaluation of breast cancer lymph nodes. RADS > 2 can be considered the best cut-off for discriminating malignant nodes.

The aim of this prospective study was to compare the diagnostic performance of contrast-enhanced mammography (CEM) versus digital mammography (DM) combined with breast ultrasound (BUS) in women with dense breasts. Between March 2021 and February 2022, patients eligible for CEM with the breast composition category ACR BI-RADS c–d at DM and an abnormal finding (BI-RADS 3-4-5) at DM and/or BUS were considered. During CEM, a nonionic iodinated contrast agent (Iohexol 350 mg I/mL, 1.5 mL/kg) was power-injected intravenously. Images were evaluated independently by two breast radiologists. Findings classified as BI-RADS 1–3 were considered benign, while BI-RADS 4–5 were considered malignant. In case of discrepancies, the higher category was considered for DM+BUS. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were calculated, using histology/≥12-month follow-up as gold standards. In total, 51 patients with 65 breast lesions were included. 59 (90.7%) abnormal findings were detected at DM+BUS, and 65 (100%) at CEM. The inter-reader agreement was excellent (Cohen’s k = 0.87 for DM+BUS and 0.97 for CEM). CEM showed a 93.5% sensitivity (vs. 90.3% for DM+BUS), a 79.4–82.4% specificity (vs. 32.4–35.5% for DM+BUS) (McNemar p = 0.006), a 80.6–82.9% PPV (vs. 54.9–56.0% for DM+BUS), a 93.1–93.3% NPV (vs. 78.6–80.0% for DM+BUS), and a 86.1–87.7% accuracy (vs. 60.0–61.5% for DM+BUS). The AUC was higher for CEM than for DM+BUS (0.865 vs. 0.613 for Reader 1, and 0.880 vs. 0.628, for Reader 2) (p < 0.001). In conclusion, CEM had a better diagnostic performance than DM and BUS alone and combined together in patients with dense breasts.

Cryoablation is a minimally invasive technique currently employed in breast cancer care, that uses freeze and thaw cycles to treat benign breast lesions, small breast cancers or focal sites of metastatic disease in patients not eligible for surgery. The final goal of this procedure is to destroy breast cancer cells using extreme cold. In addition, several studies have shown that this technique seems to have an enhancing effect on the immune response, especially by increasing the expression of tumor neoantigens specific to tumor cells, which are then attacked and destroyed. Exploiting this effect, cryoablation in combination with immunotherapy could be the key to treating early-stage breast cancers or patients who are unsuitable for surgery. According to some recent studies, there are other potential tools that could be used to enhance the therapeutic effect of cryoablation, such as FE3O4 nanoparticles or the manipulation of aquaporin expression. The aim of this narrative review is to summarize the current evidence regarding the use, indications, advantages and disadvantages of cryoablation in the treatment of breast cancer.

Objectives: We assessed the diagnostic performance of contrast-enhanced mammography (CEM) using a high-concentration iodinated contrast medium (HCCM, 400 mgI/mL) to determine whether the reduced iodine dose and increased iodine delivery rate (IDR) achieved might offer a more sustainable alternative to CEM performed with lower iodine concentrations. Methods: This two-center retrospective study included 205 patients who underwent CEM between March 2021 and February 2022. Patients were injected with HCCM at 1.0 mL/kg bodyweight at an IDR of 1.2 gL/s. Standard cranio-caudal and mediolateral-oblique views were acquired. Images were reviewed independently by two experienced radiologists who were blinded to patient clinical and imaging information. Diagnostic performance, including sensitivity, specificity, and accuracy, was assessed based on histological or long-term imaging follow-up as the reference standard. Results: Among the 205 patients, 149 (72.7%) had malignant lesions, and 56 (27.3%) had benign findings. The sensitivity and specificity of CEM were 96–97% and 84–87.5%, respectively, with an overall accuracy of 93–95%. The IDR achieved with HCCM resulted in excellent contrast enhancement, particularly in patients with aggressive malignancies. ROC analysis confirmed the good diagnostic performance, with AUC values of 0.90–0.92. Compared to conventional mammography and ultrasound, CEM demonstrated significantly higher diagnostic accuracy, especially in patients with dense breast tissue. Conclusions: CEM with HCCM provides excellent diagnostic performance, achieving high sensitivity and specificity while allowing for a reduced iodine dose and increased IDR. This approach may offer a more sustainable alternative to conventional contrast media without compromising diagnostic accuracy, particularly for the detection and characterization of aggressive breast lesions. Critical relevance statement: This study demonstrates that reducing the volume of injected contrast media while increasing iodine concentration maintains the diagnostic benefits of CEM, further supporting its potential to improve early cancer detection, thereby advancing clinical radiology practices and optimizing screening strategies for women with dense breasts. Key Points: Currently, CEM protocols utilize a variety of iodine concentrations and flow rates. CEM with high-concentration contrast (400 mgI/mL) achieved 96% sensitivity and 87.5% specificity. High-concentration contrast in CEM improves early detection of aggressive breast cancers. Graphical

Background: Digital breast tomosynthesis (DBT) is a valuable imaging modality for breast cancer detection; however, its interpretation remains time-consuming and subject to inter-reader variability. This study aimed to develop and evaluate two deep learning (DL) models based on transfer learning for the binary classification of breast lesions (benign vs. malignant) using DBT images to support clinical decision-making and risk stratification. Methods: In this retrospective monocentric study, 184 patients with histologically or clinically confirmed benign (107 cases, 41.8%) or malignant (77 cases, 58.2%) breast lesions were included. Each case underwent DBT with a single lesion manually segmented for radiomic analysis. Two convolutional neural network (CNN) architectures—ResNet50 and DenseNet201—were trained using transfer learning from ImageNet weights. A 10-fold cross-validation strategy with ensemble voting was applied. Model performance was evaluated through ROC–AUC, accuracy, sensitivity, specificity, PPV, and NPV. Results: The ResNet50 model outperformed DenseNet201 across most metrics. On the internal testing set, ResNet50 achieved a ROC–AUC of 63%, accuracy of 60%, sensitivity of 39%, and specificity of 75%. The DenseNet201 model yielded a lower ROC–AUC of 55%, accuracy of 55%, and sensitivity of 24%. Both models demonstrated relatively high specificity, indicating potential utility in ruling out malignancy, though sensitivity remained suboptimal. Conclusions: This study demonstrates the feasibility of using transfer learning-based DL models for lesion classification on DBT. While the overall performance was moderate, the results highlight both the potential and current limitations of AI in breast imaging. Further studies and approaches are warranted to enhance model robustness and clinical applicability.