The rapid advancement of artificial intelligence (AI) has significantly impacted various aspects of healthcare, particularly in the medical imaging field. This review focuses on recent developments in the application of deep learning (DL) techniques to breast cancer imaging. DL models, a subset of AI algorithms inspired by human brain architecture, have demonstrated remarkable success in analyzing complex medical images, enhancing diagnostic precision, and streamlining workflows. DL models have been applied to breast cancer diagnosis via mammography, ultrasonography, and magnetic resonance imaging. Furthermore, DL-based radiomic approaches may play a role in breast cancer risk assessment, prognosis prediction, and therapeutic response monitoring. Nevertheless, several challenges have limited the widespread adoption of AI techniques in clinical practice, emphasizing the importance of rigorous validation, interpretability, and technical considerations when implementing DL solutions. By examining fundamental concepts in DL techniques applied to medical imaging and synthesizing the latest advancements and trends, this narrative review aims to provide valuable and up-to-date insights for radiologists seeking to harness the power of AI in breast cancer care.

The pulmonary valve (PV) is the least imaged among the heart valves. However, pulmonary regurgitation (PR) and pulmonary stenosis (PS) can occur in a variety of patients ranging from fetuses, newborns (e.g., tetralogy of Fallot) to adults (e.g., endocarditis, carcinoid syndrome, complications of operated tetralogy of Fallot). Due to their complexity, PR and PS are studied using multimodality imaging to assess their mechanism, severity, and hemodynamic consequences. Multimodality imaging is crucial to plan the correct management and to follow up patients with pulmonary valvulopathy. Echocardiography remains the first line methodology to assess patients with PR and PS, but the information obtained with this technique are often integrated with cardiac magnetic resonance (CMR) and computed tomography (CT). This state-of-the-art review aims to provide an updated overview of the usefulness, strengths, and limits of multimodality imaging in patients with PR and PS.

Coronary artery disease is still a major cause of death and morbidity worldwide. In the setting of chronic coronary disease, demonstration of inducible ischemia is mandatory to address treatment. Consequently, scientific and technological efforts were made in response to the request for non-invasive diagnostic tools with better sensitivity and specificity. To date, clinicians have at their disposal a wide range of stress-imaging techniques. Among others, stress cardiac magnetic resonance (S-CMR) and computed tomography perfusion (CTP) techniques both demonstrated their diagnostic efficacy and prognostic value in clinical trials when compared to other non-invasive ischemia-assessing techniques and invasive fractional flow reserve measurement techniques. Standardized protocols for both S-CMR and CTP usually imply the administration of vasodilator agents to induce hyperemia and contrast agents to depict perfusion defects. However, both methods have their own limitations, meaning that optimizing their performance still requires a patient-tailored approach. This review focuses on the characteristics, drawbacks, and future perspectives of these two techniques.

To evaluate the possibility of reducing unnecessary biopsies in patients with BI-RADS 3 lesions by implementing Kaiser score (KS). In this retrospective, single-center study, we included 79 female patients with BI-RADS 3 lesions and risk factors who underwent biopsy following magnetic resonance imaging. Three readers (two experienced breast radiologists and a radiology resident) blinded evaluated the lesions using KS. Lesions with a KS ≤ 4 were considered benign. Results were compared with the histopathological findings (gold standard) assessing sensitivity and specificity along with 95 % confidence intervals (CI) for each reader. Inter-reader agreement was assessed using Fleiss' kappa with 95 % CIs. Moreover, Cohen's kappa was used to assess concordance between two readers at time. 79 female patients (mean age, 50.9 ± 12.2 (standard deviation)) were evaluated. The area under the receiver operating characteristic curve for the three readers was excellent: 0.99, 0.99, and 0.90), respectively. The sensitivity of the two breast radiologists and the resident was 0.92 (95 % CI: 0.62 - 0.99), 1.00 (95 % CI: 0.95 - 1.00) and 0.75 (95 % CI: 0.42 - 0.95), respectively, while the specificity was 1.00 (95 % CI: 0.95---1.00), 0.99 (95 % CI: 0.92 - 1.00), and 1.00 (95 % CI: 0.95 - 1.00) respectively. By using a KS ≤ 4 value to indicate benignity, 66 to 67 biopsies (84 to 85 % of all the biopsies) would have been avoided. Inter-reader concordance via Fleiss' kappa was 0.792 (95 % CI: 0.68 - 0.91). The implementation of KS could have spared 84-85% of biopsies, proving to be a quick, user-friendly tool with strong inter-observer agreement and high specificity.

Background: This retrospective study aimed to evaluate our single-center experience with Magseed as a pre-operative localization system in a cohort of 47 patients with non-palpable breast lesions. Design and methods: Forty-seven patients with non-palpable breast lesions, who underwent Magseed pre-operative localization followed by breast-conserving surgery between November 2022 and June 2024 at our Breast Unit were enrolled in our study. The procedure involved percutaneous placement of the Magseed into the target lesion under ultrasound (66%) or stereotactic (34%) guidance. Data on patient demographics, lesion characteristics, Magseed localization and retrieval, surgical outcomes, and complications were collected and analyzed. Results: Magseed localization was successful in all cases, with no marker migration or dislodgment, and all seeds were retrieved (100%). Breast-conserving surgery was successful in 97.9% of patients, with only one requiring intraoperative widening. No significant complications were reported. Histopathology revealed predominantly invasive breast cancers, with “No Special Type” being the most common subtype (42.5%). Conclusions: The effectiveness of this technique is proven by our results, which reflect the data in the growing scientific literature on Magseed.

Purpose of the Review: In this narrative review, we focus on the latest updates on CA–AS diagnosis, the implementation of CMR, and CT in the diagnostic algorithm and their future prospectives. Recent Findings: Aortic stenosis (AS) is the most common valvular heart disease (VHD) worldwide. In recent years, the association between Cardiac amyloidosis (CA) and AS has emerged as a not uncommon and sneaky association. Trans-thyretin (TTR) and immunoglobulin light chain (AL) are the two most common different types of misfolded amyloid proteins infiltrating the heart. AS–CA shares some anatomical features with CA, but the association leads to worse outcome. Nearly 30% of patients undergoing TAVR suffers from CA. Differentiating CA–AS from lone AS is of great importance to tailorize pharmaceutical therapy and/or surgery. Nowadays, bone scintigraphy and urine/serum analyses are crucial to assess which type of amyloid excess there is, but to represent anatomical changes of the myocardium cardiac magnetic resonance (CMR) and computed tomography cardiac angiography (CTCA), they are the best non-invasive tools. Moreover, extracellular expansion can be quantified via CMR, but new promising studies assessing extracellular volume (ECV) via CT are emerging. Furthermore, AS–CA is a sneaky pathology afflicting elderly patients. Seen the comorbidities of the typical patient, Transcatheter Aortic Valve Replacement (TAVR) should be the indicated procedure. CT is the best imaging modality for TAVR planning with its excellent anatomical resolution. Summary: CMR and CT could be integrated in the CA algorithm. Both can assess myocardium anatomical changes. Moreover, ECV is a precious tool to suggest the presence of amyloid in the myocardium.