Coronary microvascular disease (CMVD) is an underdiagnosed but significant contributor to the burden of ischemic heart disease, characterized by angina and myocardial infarction. The development of risk prediction models such as polygenic risk scores (PRS) for CMVD has been limited by a lack of large-scale genome-wide association studies (GWAS). However, there is significant overlap between CMVD and enrollment criteria for coronary artery disease (CAD) GWAS. In this study, we developed CMVD PRS models by selecting variants identified in a CMVD GWAS and applying weights from an external CAD GWAS, using CMVD-associated loci as proxies for the genetic risk. We integrated plasma proteomics, clinical measures from perfusion PET imaging, and PRS to evaluate their contributions to CMVD risk prediction in comprehensive machine and deep learning models. We then developed a novel unsupervised endotyping framework for CMVD from perfusion PET-derived myocardial blood flow data, revealing distinct patient subgroups beyond traditional case-control definitions. This imaging-based stratification substantially improved classification performance alongside plasma proteomics and PRS, achieving AUROCs between 0.65 and 0.73 per class, significantly outperforming binary classifiers and existing clinical models, highlighting the potential of this stratification approach to enable more precise and personalized diagnosis by capturing the underlying heterogeneity of CMVD. This work represents the first application of imaging-based endotyping and the integration of genetic and proteomic data for CMVD risk prediction, establishing a framework for multimodal modeling in complex diseases.

Ascending aortic (AscAo) dimensions partially depend on body size. Ratiometric (linear) indexing of AscAo dimensions to height and body surface area (BSA) are currently recommended, but it is unclear whether these allometric relationships are indeed linear. This study aimed to evaluate allometric relations, normative values, and the prognostic performance of AscAo dimension indices. We studied UK Biobank (UKB) (n = 49,271) and Penn Medicine BioBank (PMBB) (n = 8,426) participants. A convolutional neural network was used to segment the thoracic aorta from available magnetic resonance and computed tomography thoracic images. Normal allometric exponents of AscAo dimensions were derived from log-log models among healthy reference subgroups. Prognostic associations of AscAo dimensions were assessed with the use of Cox models. Among reference subgroups of both UKB (n = 11,310; age 52 ± 8 years; 37% male) and PMBB (n = 799; age 50 ± 16 years; 41% male), diameter/height, diameter/BSA, and area/BSA exhibited highly nonlinear relationships. In contrast, the allometric exponent of the area/height index was close to unity (UKB: 1.04; PMBB: 1.13). Accordingly, the linear ratio of area/height index did not exhibit residual associations with height (UKB: R² = 0.04 [P = 0.411]; PMBB: R² = 0.08 [P = 0.759]). Across quintiles of height and BSA, area/height was the only ratiometric index that consistently classified aortic dilation, whereas all other indices systematically underestimated or overestimated AscAo dilation at the extremes of body size. Area/height was robustly associated with thoracic aorta events in the UKB (HR: 3.73; P < 0.001) and the PMBB (HR: 1.83; P < 0.001). Among AscAo indices, area/height was allometrically correct, did not exhibit residual associations with body size, and was consistently associated with adverse events.

Accurate segmentation of the mitral valve in transthoracic echocardiography (TTE) enables the extraction of various anatomical parameters that are important for guiding clinical management. However, manual mitral valve segmentation is time-consuming and prone to interobserver variability. To support robust automatic analysis of mitral valve anatomy, we propose a novel AI-based method for mitral valve segmentation and anatomical measurement extraction. We retrospectively collected a set of echocardiographic exams from 1756 consecutive patients with suspected coronary artery disease. For these patients, we retrieved expert-defined scores for mitral regurgitation (MR) severity and follow-up characteristics. PLAX-view videos were automatically identified, and the inside border of the mitral valve leaflets were manually segmented in 182 patients. To automatically segment mitral valve leaflets, we designed a deep neural network that takes a video frame and outputs a distance- and classification-map for each leaflet, supervised by manual segmentations. From the resulting automatic segmentations, we extracted leaflet length, annulus diameter, tenting area, and coaptation length. To demonstrate the clinical relevance of these automatically extracted measurements, we performed univariable and multivariable Cox Regression survival analysis, with the clinical endpoint defined as heart-failure hospitalization or all-cause mortality. We trained the segmentation model on annotated frames of 111 patients, and tested segmentation performance on a set of 71 patients. For the survival analysis, we included 1,117 patients (mean age 64.1 ± 12.4 years, 58% male, median follow-up 3.3 years). The trained model achieved an average surface distance of 0.89 mm, a Hausdorff distance of 3.34 mm, and a temporal consistency score of 97%. Additionally, leaflet coaptation was accurately detected in 93% of annotated frames. In univariable Cox regression, automated annulus diameter (>35 mm, hazard ratio (HR) = 2.38, p<0.001), tenting area (>2.4 cm², HR = 2.48, p<0.001), tenting height (>10 mm, HR = 1.91, p<0.001), and coaptation length (>3 mm, HR = 1.53, p = 0.007) were significantly associated with the defined clinical endpoint. For reference, significant MR by expert assessment resulted in an HR of 2.31 (p<0.001). In multivariable Cox Regression analysis, automated annulus diameter and coaptation length predicted the defined endpoint as independent parameters (p = 0.03 and p = 0.05, respectively). Our method allows accurate segmentation of the mitral valve in TTE, and enables fully automated quantification of key measurements describing mitral valve anatomy. This has the potential to improve risk stratification for cardiac patients.

Late Gadolinium Enhancement (LGE) imaging remains the gold standard for assessing myocardial fibrosis and scarring, with left ventricular (LV) LGE presence and extent serving as a predictor of major adverse cardiac events (MACE). Despite its clinical significance, LGE-based LV scar quantification is not used routinely due to the labor-intensive manual segmentation and substantial inter-observer variability. We developed ScarNet that synergistically combines a transformer-based encoder in Medical Segment Anything Model (MedSAM), which we fine-tuned with our dataset, and a convolution-based decoder in U-Net with tailored attention blocks to automatically segment myocardial scar boundaries while maintaining anatomical context. This network was trained and fine-tuned on an existing database of 401 ischemic cardiomyopathy patients (4,137 2D LGE images) with expert segmentation of myocardial and scar boundaries in LGE images, validated on 100 patients (1,034 2D LGE images) during training, and tested on unseen set of 184 patients (1,895 2D LGE images). Ablation studies were conducted to validate each architectural component's contribution. In 184 independent testing patients, ScarNet achieved accurate scar boundary segmentation (median DICE=0.912 [interquartile range (IQR): 0.863-0.944], concordance correlation coefficient [CCC]=0.963), significantly outperforming both MedSAM (median DICE=0.046 [IQR: 0.043-0.047], CCC=0.018) and nnU-Net (median DICE=0.638 [IQR: 0.604-0.661], CCC=0.734). For scar volume quantification, ScarNet demonstrated excellent agreement with manual analysis (CCC=0.995, percent bias=-0.63%, CoV=4.3%) compared to MedSAM (CCC=0.002, percent bias=-13.31%, CoV=130.3%) and nnU-Net (CCC=0.910, percent bias=-2.46%, CoV=20.3%). Similar trends were observed in the Monte Carlo simulations with noise perturbations. The overall accuracy was highest for SCARNet (sensitivity=95.3%; specificity=92.3%), followed by nnU-Net (sensitivity=74.9%; specificity=69.2%) and MedSAM (sensitivity=15.2%; specificity=92.3%). ScarNet outperformed MedSAM and nnU-Net for predicting myocardial and scar boundaries in LGE images of patients with ischemic cardiomyopathy. The Monte Carlo simulations demonstrated that ScarNet is less sensitive to noise perturbations than other tested networks.

The accurate and timely diagnosis of acute aortic syndrome (AAS) in patients presenting with acute chest pain remains a clinical challenge. Aortic computed tomography (CT) angiography is the imaging protocol of choice in patients with suspected AAS. However, due to economic and workflow constraints in China, the majority of suspected patients initially undergo noncontrast CT as the initial imaging testing, and CT angiography is reserved for those at higher risk. Although noncontrast CT can reveal specific signs indicative of AAS, its diagnostic efficacy when used alone has not been well characterized. Here we present an artificial intelligence-based warning system, iAorta, using noncontrast CT for AAS identification in China, which demonstrates remarkably high accuracy and provides clinicians with interpretable warnings. iAorta was evaluated through a comprehensive step-wise study. In the multicenter retrospective study (n = 20,750), iAorta achieved a mean area under the receiver operating curve of 0.958 (95% confidence interval 0.950-0.967). In the large-scale real-world study (n = 137,525), iAorta demonstrated consistently high performance across various noncontrast CT protocols, achieving a sensitivity of 0.913-0.942 and a specificity of 0.991-0.993. In the prospective comparative study (n = 13,846), iAorta demonstrated the capability to significantly shorten the time to correct diagnostic pathway for patients with initial false suspicion from an average of 219.7 (115-325) min to 61.6 (43-89) min. Furthermore, for the prospective pilot deployment that we conducted, iAorta correctly identified 21 out of 22 patients with AAS among 15,584 consecutive patients presenting with acute chest pain and under noncontrast CT protocol in the emergency department. For these 21 AAS-positive patients, the average time to diagnosis was 102.1 (75-133) min. Finally, iAorta may help prevent delayed or missed diagnoses of AAS in settings where noncontrast CT remains the only feasible initial imaging modality-such as in resource-limited regions or in patients who cannot receive, or did not receive, intravenous contrast.

Dextrocardia is a congenital anomaly arising during fetal development, characterised by the abnormal positioning of the heart on the right side of the chest, instead of its usual anatomical location on the left. This paper describes a machine learning-based method to automatically assess ultrasound (US) transverse videos to detect dextrocardia by analysing the Situs and four-chamber (4CH) views. The method processes ultrasound video sweeps that users capture, which include the Situs and 4CH views. The automated analysis method consists of three stages. First, four fetal anatomical structures (chest, spine, stomach and heart) are automatically segmented using SegFormer. Second, a quality assessment (QA) module verifies that the video includes informative frames. Thirdly, the orientation of the stomach and heart relative to the fetal chest (either right or left side) is determined to assess dextrocardia. The method utilises a Transformer-based segmentation model to perform segmentation of the fetal anatomy. Segmentation performance was evaluated using the Dice coefficient, and fetal anatomy centroid estimation accuracy using root mean squared error (RMSE). Dextrocardia was classified based on a frame-based classification score (FBCS). The datasets consist of 142 pairs of Situs and 4CH US (284 frames in total) for training; and 14 US videos (7 normal, 7 dextrocardia, 2,916 frames total) for testing. The method achieved a Dice score of 0.968, 0.958, 0.953, 0.949 for chest, spine, stomach and heart segmentation, respectively, and anatomy centroid RMSE of 0.23mm, 0.34mm, 0.25mm, 0.39mm for the same structures. The QA rejected 172 frames. The assessment for dextrocardia achieved a FBCS of 0.99 with a standard deviation of 0.01 for normal and 0.02 for dextrocardia videos. Our automated method demonstrates accurate segmentation and reliable detection of dextrocardia from US videos. Due to the simple acquisition protocol and its robust analytical pipeline, our method is suitable for healthcare providers who are non-cardiac experts. It has the potential to facilitate earlier and more consistent prenatal identification of dextrocardia during screening, particularly in settings with limited access to experts in fetal echocardiography.

Background and AimsEchocardiography serves as a cornerstone of cardiovascular diagnostics through multiple standardized imaging views. While recent AI foundation models demonstrate superior capabilities across cardiac imaging tasks, their massive computational requirements and reliance on large-scale datasets create accessibility barriers, limiting AI development to well-resourced institutions. Vector embedding approaches offer promising solutions by leveraging compact representations from original medical images for downstream applications. Furthermore, demographic fairness remains critical, as AI models may incorporate biases that confound clinically relevant features. We developed a multi-view encoder framework to address computational accessibility while investigating demographic fairness challenges. MethodsWe utilized the MIMIC-IV-ECHO dataset (7,169 echocardiographic studies) to develop a transformer-based multi-view encoder that aggregates view-level representations into study-level embeddings. The framework incorporated adversarial learning to suppress demographic information while maintaining clinical performance. We evaluated performance across 21 binary classification tasks encompassing echocardiographic measurements and clinical diagnoses, comparing against foundation model baselines with varying adversarial weights. ResultsThe multi-view encoder achieved a mean improvement of 9.0 AUC points (12.0% relative improvement) across clinical tasks compared to foundation model embeddings. Performance remained robust with limited echocardiographic views compared to the conventional approach. However, adversarial learning showed limited effectiveness in reducing demographic shortcuts, with stronger weighting substantially compromising diagnostic performance. ConclusionsOur framework democratizes advanced cardiac AI capabilities, enabling substantial diagnostic improvements without massive computational infrastructure. While algorithmic approaches to demographic fairness showed limitations, the multi-view encoder provides a practical pathway for broader AI adoption in cardiovascular medicine with enhanced efficiency in real-world clinical settings. Structured graphical abstract or graphical abstractO_ST_ABSKey QuestionC_ST_ABSCan multi-view encoder frameworks achieve superior diagnostic performance compared to foundation model embeddings while reducing computational requirements and maintaining robust performance with fewer echocardiographic views for cardiac AI applications? Key FindingMulti-view encoder achieved 12.0% relative improvement (9.0 AUC points) across 21 cardiac tasks compared to foundation model baselines, with efficient 512-dimensional vector embeddings and robust performance using fewer echocardiographic views. Take-home MessageVector embedding approaches with attention-based multi-view integration significantly improve cardiac diagnostic performance while reducing computational requirements, offering a pathway toward more efficient AI implementation in clinical settings. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=83 SRC="FIGDIR/small/25333725v1_ufig1.gif" ALT="Figure 1"> View larger version (22K): [email protected]@a75818org.highwire.dtl.DTLVardef@88a588org.highwire.dtl.DTLVardef@12bad06_HPS_FORMAT_FIGEXP M_FIG C_FIG Translational PerspectiveOur proposed multi-view encoder framework overcomes critical barriers to the widespread adoption of artificial intelligence in echocardiography. By dramatically reducing computational requirements, the multi-view encoder approach allows smaller healthcare institutions to develop sophisticated AI models locally. The framework maintains robust performance with fewer echocardiographic examinations, which addresses real-world clinical constraints where comprehensive imaging is not feasible due to patient factors or time limitations. This technology provides a practical way to democratize advanced cardiac AI capabilities, which could improve access to cardiovascular care across diverse healthcare settings while reducing dependence on proprietary datasets and massive computational resources.

Heart failure is a major cause of morbitidy and mortality, with the severest forms requiring heart transplantation. Heart size matching between the donor and recipient is a critical step in ensuring a successful transplantation. Currently, a set of equations based on population measures of height, weight, sex and age, viz. predicted heart mass (PHM), are used but can be improved upon by personalized information from recipient and donor chest CT images. Here, we developed GigaHeart, the first heart-specific foundation model pretrained on 180,897 chest CT volumes from 56,607 patients. The key idea of GigaHeart is to direct the foundation models attention towards the heart by contrasting the heart region and the entire chest, thereby encouraging the model to capture fine-grained cardiac features. GigaHeart achieves the best performance on 8 cardiac-specific classification tasks and further, exhibits superior performance on cross-modal tasks by jointly modeling CT images and reports. We similarly developed a thorax-specific foundation model and observed promising performance on 9 thorax-specific tasks, indicating the potential to extend GigaHeart to other organ-specific foundation models. More importantly, GigaHeart addresses the heart sizing problem. It avoids oversizing by correctly segmenting the sizes of hearts of donors and recipients. In regressions against actual heart masses, our AI-segmented total cardiac volumes (TCVs) has a 33.3% R2 improvement when compared to PHM. Meanwhile, GigaHeart also solves the undersizing problem by adding a regression layer to the model. Specifically, GigaHeart reduces the mean squared error by 57% against PHM. In total, we show that GigaHeart increases the acceptable range of donor heart sizes and matches more accurately than the widely used PHM equations. In all, GigaHeart is a state-of-the-art, cardiac-specific foundation model with the key innovation of directing the models attention to the heart. GigaHeart can be finetuned for accomplishing a number of tasks accurately, of which AI-assisted heart sizing is a novel example.

Brain-inspired neuromorphic computing offers significant potential for efficient and adaptive computational platforms. Emerging ferroelectric and antiferroelectric HfZrO_<i>x</i> devices provide key roles in convolutional neural network (CNN) and spiking neural network (SNN) computing with unique polarization switching characteristics. Here, we present ferroelectric/antiferroelectric HfZrO_<i>x</i> devices to realize functions of artificial synapse/neurons by element doping engineering. The HfZrO_<i>x</i>-based ferroelectric and antiferroelectric devices exhibit excellent endurance characteristics of 1 × 10⁹ cycles. Based on the non-volatile polarization switching and spontaneous depolarization nature of ferroelectric and antiferroelectric devices, integrate-and-fire behaviors were constructed for neuromorphic computing. For the first time, a complementary ferroelectric/antiferroelectric HfZrO_<i>x</i> artificial synapse/neuron-based hybrid CNN-SNN framework was constructed for energy-efficient cardiac magnetic resonance imaging (MRI) classification. The hybrid neural network breaks the limitation of pure SNN in 3D image recognition and improves the accuracy from 82.3 to 92.7% compared to pure CNN, highlighting the potential of composition-engineered ferroelectric materials to implement high-efficiency neuromorphic computing.

Venous thromboembolism (VTE) remains a leading cause of cardiovascular morbidity and mortality, despite advances in imaging and anticoagulation. VTE arises from diverse and overlapping risk factors, such as inherited thrombophilia, immobility, malignancy, surgery or trauma, pregnancy, hormonal therapy, obesity, chronic medical conditions (e.g., heart failure, inflammatory disease), and advancing age. Clinicians, therefore, face challenges in balancing the benefits of thromboprophylaxis against the bleeding risk. Existing clinical risk scores often exhibit only modest discrimination and calibration across heterogeneous patient populations. Machine learning (ML) has emerged as a promising tool to address these limitations. In imaging, convolutional neural networks and hybrid algorithms can detect VTE on CT pulmonary angiography with areas under the curves (AUCs) of 0.85 to 0.96. In surgical cohorts, gradient-boosting models outperform traditional risk scores, achieving AUCs between 0.70 and 0.80 in predicting postoperative VTE. In cancer-associated venous thrombosis, advanced ML models demonstrate AUCs between 0.68 and 0.82. However, concerns about bias and external validation persist. Bleeding risk prediction models remain challenging in extended anticoagulation settings, often matching conventional models. Predicting recurrent VTE using neural networks showed AUCs of 0.93 to 0.99 in initial studies. However, these lack transparency and prospective validation. Most ML models suffer from limited external validation, "black box" algorithms, and integration hurdles within clinical workflows. Future efforts should focus on standardized reporting (e.g., Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis [TRIPOD]-ML), transparent model interpretation, prospective impact assessments, and seamless incorporation into electronic health records to realize the full potential of ML in VTE.