Breast ultrasound (BUS) malignancy assessment is challenged by acquisition variability and cross-dataset shift. We developed AgentDS-BUS, an agentic clinical decision-support framework that uses pretrained foundation models without additional BUS-specific model fine-tuning and decomposes malignancy assessment into lesion localization and segmentation, region-of-interest (ROI)-conditioned extraction of Breast Imaging Reporting and Data System (BI-RADS)-aligned evidence, and structured decision aggregation. In this implementation, lesion masks are obtained using consensus-gated Segment Anything Model 3 (SAM3), with clinician-provided bounding boxes used for fallback segmentation in low-consensus cases. Across 4,331 images from seven public BUS benchmarks and three vision-language model (VLM) backbones, AgentDS-BUS improved pooled AUROC/AUPRC over image-only prompting. Under Qwen3-VL, performance increased from 0.636/0.524 with image-only prompting to 0.717/0.606 for AgentDS-BUS with consensus-gated ROIs and 0.791/0.654 for AgentDS-BUS with ground-truth (GT) oracle ROIs. With Lingshu, AgentDS-BUS achieved 0.760/0.678 in the consensus-gated ROI setting and 0.807/0.715 in the GT-ROI setting. These findings support structured agentic decomposition and ROI-conditioned evidence extraction as a transparent approach to BUS decision support.

BACKGROUND:To utilize high spatial resolution reconstructions for cardiac imaging at energy-integrating detector CT (EID)-CT with comparable noise to similar reconstructions at photon-counting detector (PCD)-CT, methods to control EID-CT image noise are needed. Supervised convolutional neural networks (CNN) have shown promise for denoising, but a challenge remains to efficiently create high-quality and unbiased estimates of noise without access to dedicated software or proprietary information, such that natural noise texture is retained in CNN-denoised CT images. PURPOSE:This study aims to develop and test image-based noise estimation methods that can be used to train a CNN model, and to evaluate denoising performance and noise texture preservation for EID-CT coronary CT angiography (cCTA) images reconstructed with high-resolution kernels. METHODS:U-net CNN models were trained for denoising. To supervise training, noise-only images were estimated directly from high-resolution kernel (Bv59) reconstructed EID-CT (HR EID-CT) patient images using two different methods: subtraction of low- and high-strength iterative reconstruction (IR); subtraction of adjacent image slices with the same IR strength. The noise estimates from these methods contain differing noise texture and anatomical information. Networks were trained and validated separately for three data sets: the training data from each of the two noise-estimation methods, and a 50%-50% partition of training data between the two methods. The trained models were applied to two sets of testing data: CT images of a uniform water phantom to measure noise power spectra (NPS), and an independent cohort of seven patient cCTA HR EID-CT exams. The denoised patient images were compared to standard resolution EID-CT reconstructions (Bv40). As a low-noise reference, patient images acquired on the same day with a PCD-CT and reconstructed using a similar kernel as HR EID-CT were used for comparison. RESULTS:Models trained with each noise-image estimation method denoised the HR EID-CT images by 74%-79% to achieve a comparable noise magnitude to the HR PCD-CT images. The peak, average, and 10% peak frequencies of the NPS of the input images (6.08, 6.24, and 12.0 cm-1) were better approximated by the model trained on adjacent slice subtraction (6.56, 5.87, and 11.5 cm-1) than by the model trained on subtraction of low- and high-IR images (4.64, 5.44, and 11.3 cm-1). In cCTA images, the IR subtraction model images retained anatomic structures from input images but resulted in undesirable salt-and-pepper noise texture and CT number bias. The model trained on adjacent slice subtraction images had more natural texture and no significant bias, but the model sometimes removed small anatomic structures. The model trained on the mixed training dataset preserved both noise texture and anatomy from the model inputs and enabled visualization of small structures seen in PCD-CT images that were previously unresolved by EID-CT. CONCLUSIONS:The noise texture and anatomical accuracy in CT images denoised with an image-based supervised CNN are greatly influenced by the characteristics and partitioning of training data. With higher-resolution reconstructions and noise texture-preserving deep learning denoising, the quality of cCTA images from EID-CT can be enhanced to enable resolvability of subtle anatomy similar to PCD-CT.

Hepatic artery pseudoaneurysm is a rare complication that may occur in the setting of liver transplantation and other traumatic instrumentation of the hepatobiliary system. This condition poses a significant morbidity and mortality risk and must be diagnosed and intervened upon emergently. Herein we present a case of hepatic artery pseudoaneurysm complicated by hemorrhagic shock in the setting of a post-liver transplant biliary leak. In this case, the patient was ultimately diagnosed via hepatic angiogram, treated with hepatic artery embolization, and required subsequent retransplantation. The objective of this case was to demonstrate the importance of maintaining a high clinical suspicion for hepatic artery pseudoaneurysm in the post-transplant setting, emphasize the use of computed tomography angiography as a primary diagnostic tool, and involving interventional radiology early in the treatment course.

Multiple applications for machine learning and artificial intelligence (AI) in cardiovascular imaging are being proposed and developed. However, the processes involved in implementing AI in cardiovascular imaging are highly diverse, varying by imaging modality, patient subtype, features to be extracted and analyzed, and clinical application. This article establishes a framework that defines value from an organizational perspective, followed by value chain analysis to identify the activities in which AI might produce the greatest incremental value creation. The various perspectives that should be considered are highlighted, including clinicians, imagers, hospitals, patients, and payers. Integrating the perspectives of all health care stakeholders is critical for creating value and ensuring the successful deployment of AI tools in a real-world setting. Different AI tools are summarized, along with the unique aspects of AI applications to various cardiac imaging modalities, including cardiac computed tomography, magnetic resonance imaging, and positron emission tomography. AI is applicable and has the potential to add value to cardiovascular imaging at every step along the patient journey, from selecting the more appropriate test to optimizing image acquisition and analysis, interpreting the results for classification and diagnosis, and predicting the risk for major adverse cardiac events.

Health care organizations are building, deploying, and self-governing digital health technologies (DHTs), including artificial intelligence, at an increasing rate. This scope necessitates expertise and quality infrastructure to ensure that the technology impacting patient care is safe, effective, and ethical throughout its lifecycle. The objective of this article is to describe Mayo Clinic's approach for embedding internal accountability as a case study for other health care institutions seeking modalities for responsible implementation of artificial intelligence-enabled DHTs. Mayo Clinic aims to enable and empower innovators by (1) building internal skills and expertise, (2) establishing a centralized review board, and (3) aligning development and deployment processes with regulations, standards, and best practices. In 2022, Mayo Clinic established the Software as a Medical Device Review Board (The Board), an independent body of physicians and domain experts to represent the organization in providing innovators regulatory and risk mitigation recommendations for DHTs. Hundreds of digital health product teams have since benefited from this function, intended to enable responsible innovation in alignment with regulation and state-of-the-art quality management practices. Other health care institutions can adopt similar internal accountability bodies using this framework. Opportunity remains to iterate on Mayo Clinic's approach in alignment with advancing best practices and enhance representation on The Board as part of standard continuous improvement practices.

Abstract Background/Introduction Little is known about the prevalence of high-risk plaque features or cardiometabolic predictors in diverse patient populations with underrepresented minorities, in the setting of stable chest pain. Purpose The goals of our study are to 1) describe plaque characteristics in a diverse patient population with underrepresented minorities and 2) characterize cardiometabolic risk factors associated with high prevalence of high-risk quantitative low attenuation noncalcified plaque (LDNCP) burden. Methods Our study included patients with chest pain undergoing CCTA between June 2016 and October 2021 for stable chest pain, who had a complete cardiometabolic panel including lipoprotein(a) and lipid panel, and at least one blood pressure recording before CCTA. Patients with prior PCI or CABG where excluded. CACS was performed before CCTA as per Agatston method and quantified in Agatston Units (AU). Stenosis was graded as per SCCT guidelines by cardiologists and radiologists with level 3 cardiac CT expertise. Plaque measurements were performed using previously validated semiautomated software (AutoPlaque version 2.5) in all patients with CAD-RADS >0 by expert readers blinded from patients' characteristics. Coronary atherosclerotic plaque volumes were measured. Independent predictors for plaque on CCTA among patients were examined using Wilcox multivariate logistic regression. Results A total of 227 consecutive patients were included in our study (see table; age 55.00 [47.50–62.00] years, 63% female, 16% diabetes, 44% hypertension, 40% hyperlipidemia and 32% with current or previous smoking history). Majority of patients were Hispanic (64%) and the rest were Black (27%), White (6%) and Asian (3%). Patients with LDNCP burden >4% were older (60.00 [52.00–66.50] vs 53.00 [43.75–61.00]; p<0.001), more likely to be diabetic (27.7 vs 11.5%; p=0.005), hypertensive (67.7 vs 33.8%; p<0.001), hyperlipidemic (64.6 vs 29.9%; p<0.001) and present smokers (31.3 vs 13.9%; p=0.003). Almost all patients (63/67) with LDNCP burden >4% had non-obstructive disease (CAD-RADS<4). Patient with LDNCP burden >4% were more likely to be on statin therapy (46.0 vs 30.4%; p=0.041). There was no differences in ethnicity, hemoglobin A1C, TC, LDL-C, HLD-C, TGs, lipoprotein(a), SBP or DBP. By logistic regression analysis, age (OR [CI]: 1.06 [1.01–1.08]), hypertension (2.20, [1.06–4.63]) and hyperlipidemia (2.73 [1.37–5.47]) increased the likelihood of LDNCP burden >4%, but not Lipoprotein (a)>175 nmol/L (OR [CI]: 1.07 [0.48–2.31]. Conclusions In our cohort of patients with high number of unrepresented minorities presenting with stable chest pain, almost all patients (94%) with LDNCP burden >4% had non-obstructive CAD (CAD-RADS<4). There were no differences in prevalence of LDNCP or CAD-RADS among different ethnic groups. Age, hypertension and hyperlipidemia, were the cardiometabolic factors related to LDNCP burden >4%. Funding Acknowledgement Type of funding sources: None.

Coronary Artery Disease Reporting and Data System (CAD-RADS) was created to standardize reporting system for patients undergoing coronary CT angiography (CCTA) and to guide possible next steps in patient management. The goal of this updated 2022 CAD-RADS 2.0 is to improve the initial reporting system for CCTA by considering new technical developments in Cardiac CT, including data from recent clinical trials and new clinical guidelines. The updated CAD-RADS classification will follow an established framework of stenosis, plaque burden, and modifiers, which will include assessment of lesion-specific ischemia using CT fractional-flow-reserve (CT-FFR) or myocardial CT perfusion (CTP), when performed. Similar to the method used in the original CAD-RADS version, the determinant for stenosis severity classification will be the most severe coronary artery luminal stenosis on a per-patient basis, ranging from CAD-RADS 0 (zero) for absence of any plaque or stenosis to CAD-RADS 5 indicating the presence of at least one totally occluded coronary artery. Given the increasing data supporting the prognostic relevance of coronary plaque burden, this document will provide various methods to estimate and report total plaque burden. The addition of P1 to P4 descriptors are used to denote increasing categories of plaque burden. The main goal of CAD-RADS, which should always be interpreted together with the impression found in the report, remains to facilitate communication of test results with referring physicians along with suggestions for subsequent patient management. In addition, CAD-RADS will continue to provide a framework of standardization that may benefit education, research, peer-review, artificial intelligence development, clinical trial design, population health and quality assurance with the ultimate goal of improving patient care.