# AI-CVM > AI in Cardiovascular Medicine (AI-CVM) at Inselspital ## Posts - [CCT-FM](https://ai-cvm.org/cct-fm/): Vision foundation model that segments all 14 cardiac structures from cardiac CT. Open code, weights and data. - [QuadML](https://ai-cvm.org/quadml/): QuadML is a desktop app for building and comparing machine-learning pipelines on tabular datasets without writing code. - [AI-CVM research featured on SRF](https://ai-cvm.org/ai-cvm-research-featured-on-srf/): SRF covers Bern research showing that AI models predict the course of aortic stenosis and cardiac amyloidosis more accurately than existing risk systems. - [AI-CVM research is featured on RSI](https://ai-cvm.org/ai-cvm-research-is-featured-on-rsi/): RSI reports on two AI-CVM studies showing that AI models predict outcomes in aortic stenosis and cardiac amyloidosis more accurately than established risk scores. - [Two AI-CVM studies featured in University of Bern and Inselspital](https://ai-cvm.org/two-ai-cvm-studies-featured-in-university-of-bern-and-inselspital/): Two international studies led by the AI in Cardiovascular Medicine (AI-CVM) research group at the Department of Cardiology, Inselspital, Bern University Hospital, and the University of Bern have been highlighted in the latest UNIBE and Inselspital news. - [Multimodal Artificial Intelligence-based Long-term Mortality Prediction after Transcatheter Aortic Valve Implantation](https://ai-cvm.org/multimodal-artificial-intelligence-based-long-term-mortality-prediction-after-transcatheter-aortic-valve-implantation/): This study develops a multimodal artificial intelligence model that predicts how long patients live after a transcatheter aortic valve implantation, learning from clinical, imaging, laboratory, and procedural data from 3991 patients treated in Switzerland and Japan, and shows that it stratifies long-term risk more accurately than the surgical risk scores currently used to counsel patients before the procedure. - [Machine Learning–Driven Risk Prediction Model in Transthyretin Amyloid Cardiomyopathy](https://ai-cvm.org/machine-learning-driven-risk-prediction-model-in-transthyretin-amyloid-cardiomyopathy/): This study builds a machine learning model that estimates the risk of death or heart failure hospitalization in people with transthyretin amyloid cardiomyopathy, trained on 850 patients from amyloidosis referral centers in Switzerland and Austria, and shows it separates higher from lower risk patients more reliably than the staging systems clinics currently use. - [Delays between CE mark and FDA regulatory approval of AI-enabled software for radiology](https://ai-cvm.org/regulatory-approval-delays-for-ai-enabled-radiology-software/): This study examines how long an artificial intelligence tool for radiology takes to gain approval on both sides of the Atlantic, tracking 239 devices through European CE marking and United States FDA clearance, and finds that products authorized in Europe first typically wait roughly five times longer for their second authorization than those that started in the United States. - [HolOrama](https://ai-cvm.org/holorama/): An open-source software for multimodal cardiac image analysis - [Cardiac-CT Dataset](https://ai-cvm.org/cardiac-ct-dataset/): A cardiac CT dataset covering 14 cardiac structures with expert annotation - [CTAug](https://ai-cvm.org/ctaug/): An open-source Python library of cardiac CT specific data augmentations. - [AiMyoCAST](https://ai-cvm.org/aimyocast-artificial-intelligence-for-myocarditis-outcome-forecast/): Machine learning tool to estimate individual risk of major heart events after myocarditis. - [A Unified Framework for Comprehensive Cardiac CT Segmentation and Phenotyping](https://ai-cvm.org/a-unified-framework-for-comprehensive-cardiac-ct-segmentation-and-phenotyping/): This study introduce a new open-source AI tool that can automatically measure 14 distinct heart structures from CT scans with greater accuracy than existing tools. This development makes it practical to assess heart health on a larger scale using scans that people already receive. - [Artificial Intelligence-Driven Risk Prediction for Major Adverse Cardiovascular Events in Myocarditis](https://ai-cvm.org/artificial-intelligence-driven-risk-prediction-for-major-adverse-cardiovascular-events-in-myocarditis/): AI model predicts major cardiac events after myocarditis from seven routine values, tested on three continents. - [Reconstruction-Informed and Multidomain Deep Learning for Generalizable CT-Free Attenuation Correction in SPECT Myocardial Perfusion Imaging](https://ai-cvm.org/reconstruction-informed-and-multidomain-deep-learning-for-generalizable-ct-free-attenuation-correction-in-spect-myocardial-perfusion-imaging/): This study presents a deep learning approach that feeds several differently reconstructed non-corrected SPECT images into a single model and trains it against both the attenuation map and the corrected image at once, producing attenuation-corrected myocardial perfusion scans that hold up on data from an outside centre and that experienced readers could not reliably tell apart from the CT-corrected versions they were meant to replace. - [TAVI-ALPURA](https://ai-cvm.org/tavi-alpura/): An AI-based tool for predicting long-term mortality after transcatheter aortic valve implantation (TAVI). - [AiTTRIX](https://ai-cvm.org/aittrix-artificial-intelligence-for-transthyretin-cardiac-amyloidosis-risk-prediction-using-an-explainable-model/): An explainable ML platform for transparent risk stratification in cardiac amyloidosis - [Radiuma](https://ai-cvm.org/radiuma-a-no-code-graphical-workflow-generator-for-reproducible-medical-image-analysis-and-machine-learning/): A no-code visual workflow builder for reproducible medical image analysis and machine learning. - [Grounding Clinical AI Competency in the Architecture of Clinical Care](https://ai-cvm.org/grounding-clinical-ai-competency-in-the-architecture-of-clinical-care/): This work introduces the Clinical World Model and Clinical AI Skill-Mix, a shared framework that organises medical AI competency across billions of clinical contexts and reframes the field's central question from whether clinical AI works to the coordinates in which it has demonstrated reliability, and for whom. - [The 2026 Otto Hess Trainee Award​](https://ai-cvm.org/the-2026-otto-hess-trainee-award/): The Swiss Society of Cardiology honored Dr. Stark's doctoral thesis on diagnosing hemodynamic relevance in anomalous aortic origin of a coronary artery (AAOCA), a congenital condition that can cause sudden cardiac death. His work pairs a prospective clinical cohort with computational fluid dynamics and two open-source tools, AIVUS-CAA and multimodars, to make accurate AAOCA assessment more accessible beyond specialized centers. - [Swiss Heart Foundation Research Prize 2026](https://ai-cvm.org/swiss-heart-foundation-research-prize-2026/): Prof. Christoph Gräni was awarded the Cardiology Research Prize 2026 by the Swiss Heart Foundation (Schweizerische Herzstiftung), which was presented on 2 April 2026, in recognition of outstanding contributions to cardiac imaging and prognosis through the integration of artificial intelligence. - [CVRC 2026 Best Poster Prize Awarded to Pooya](https://ai-cvm.org/cvrc-2025-best-poster-prize-awarded-to-pooya/): Pooya received the CVRC 2026 Best Poster Prize (Clinical Category) for his deep learning–based cardiac CT segmentation model. - [PySERA](https://ai-cvm.org/pysera-python-based-standardized-extraction-for-radiomics-analysis/): A python-based standardized feature extraction for radiomics analysis. - [IEEE Bruce Hasegawa Young Investigator Medical Imaging Science Award 2025](https://ai-cvm.org/ieee-bruce-hasegawa-young-investigator-medical-imaging-science-award-2025/): Dr. Isaac Shiri won the IEEE Bruce Hasegawa Young Investigator Award in Medical Imaging Science, which was presented at the IEEE Medical Imaging Conference in Yokohama, Japan, on 4–8 November 2025. - [Automated Intravascular Ultrasound Image Processing and Quantification of Coronary Artery anomalies: The AIVUS-CAA Software](https://ai-cvm.org/automated-intravascular-ultrasound-image-processing-and-quantification-of-coronary-artery-anomalies-the-aivus-caa-software/): This study introduces an executable, low-code software that automatically segments lumen contours and identifies cardiac phases in intravascular ultrasound images from patients with intramural coronary artery anomalies, turning what is normally a slow, rare, and reader-dependent analysis into a fast and reproducible workflow that holds up under both rest and stress conditions. - [AI Heart Anomaly Detection Featured in The Germany Eye](https://ai-cvm.org/ai-heart-anomaly-detection-featured-in-the-germany-eye/): The article highlights how our pioneering tool for detecting and classifying anomalous aortic origin of coronary arteries via CT scans, developed at University of Bern. - [AI-CVM Research Featured in 20 Minuten](https://ai-cvm.org/ai-cvm-research-featured-in-20-minuten/): Our recent work on AI-based detection and classification of anomalous aortic origin of coronary arteries (AAOCA) using coronary CT angiography has been featured in 20 Minuten. - [Young Investigator Award in Valvular Heart Disease at ESC 2024](https://ai-cvm.org/young-investigator-award-in-valvular-heart-disease-at-esc-2024/): Isaac has received the Young Investigator Award in Valvular Heart Disease at the European Society of Cardiology Congress (ESC 2024) for developing TAVI-ALPURA. - [CVRC 2025 Prize for Best Flash Presentation](https://ai-cvm.org/cvrc-2025-prize-for-best-flash-presentation/): Anselm has been awarded the Cardiovascular Research Cluster Bern (CVRC) 2025 Prize for Best Flash Presentation in the Clinical Category for his work on AIVUS-CAA - [Artificial Intelligence in Valvular Heart Disease: Innovations and Future Directions](https://ai-cvm.org/artificial-intelligence-in-valvular-heart-disease-innovations-and-future-directions/): This review examines how artificial intelligence can transform valvular heart disease management by integrating multimodal data for enhanced diagnosis, procedural optimization, and personalized treatment strategies, while addressing critical challenges including validation requirements, algorithmic bias, and transparency concerns that must be resolved for successful clinical implementation. - [Multimodal Machine Learning-Based Technical Failure Prediction in Patients Undergoing Transcatheter Aortic Valve Replacement](https://ai-cvm.org/paper-multimodal-machine-learning-for-tavr-technical-failure-prediction/): This study builds and validates machine learning models that draw on 184 clinical, imaging, and procedural variables from nearly 3,000 consecutive TAVR patients to anticipate VARC-3 technical failure before it happens, showing that cardiac and vascular complications can be predicted with moderate-to-high accuracy. - [Myocardial Perfusion SPECT Radiomic Features Reproducibility](https://ai-cvm.org/paper-myocardial-perfusion-spect-radiomic-features-reproducibility/): This study demonstrated that radiomic features extracted from cardiac SPECT images are highly sensitive to reconstruction parameters, emphasizing the need for standardized imaging protocols to ensure reliable clinical applications in coronary artery disease assessment. - [Generalizability of FDA-Approved AI-Enabled Medical Devices](https://ai-cvm.org/paper-generalizability-of-fda-approved-ai-enabled-medical-devices/): This cross-sectional analysis of 903 FDA-approved AI medical devices revealed significant gaps in clinical validation and generalizability reporting, raising concerns about their performance across diverse patient populations and real-world settings. - [AI-Based Detection and Classification of Anomalous Aortic Origin of Coronary Arteries](https://ai-cvm.org/paper-ai-based-detection-and-classification-of-anomalous-aortic-origin-of-coronary-arteries/): This study developed a fully automated AI system that detects anomalous coronary artery origins in CT scans with over 99% accuracy, classifies their anatomical risk, and can alert clinicians to potentially life-threatening cases that might otherwise be missed. - [DL-AAOCA](https://ai-cvm.org/aaoca/): An automated, deep learning-based tool for the detection, classification, and risk assessment of coronary anomaly - [multimodars](https://ai-cvm.org/multimoda-rs/): Toolkit fo fusing cardiac imaging from CCTA, IVUS, OCT, and MRI. - [nnUZoo](https://ai-cvm.org/nnuzoo/): Open-source benchmarking framework for medical segmentation - [AIVUS-CAA](https://ai-cvm.org/aivus-caa/): AI-powered software for cardiac IVUS analysis with automated segmentation and gating capabilities. - [Christoph Grani](https://ai-cvm.org/christoph-grani/): Explore the advanced realm of cardiovascular imaging with Dr. Christoph Gräni, MD, PhD, an esteemed authority in this specialty. Serving as an Extraordinary Professor at the University of Bern and the Director of Cardiovascular Imaging at the University Hospital Bern, he possesses extensive expertise in non-invasive diagnostics and treatment strategies for heart conditions. His pioneering methodologies integrate cutting-edge imaging technologies with artificial intelligence, aiming to transform cardiovascular healthcare. Discover how he employs imaging-based biomarkers and refined diagnostics to improve patient outcomes and influence the future landscape of cardiac medicine. - [Isaac Shiri](https://ai-cvm.org/isaac-shiri/): Discover the groundbreaking work of Dr. Isaac Shiri, a leader in the intersection of artificial intelligence and cardiovascular medicine. At the helm of the AI-CVM Lab, he pioneers innovative machine and deep learning techniques to tackle pressing health challenges. By integrating diverse data sources—from clinical texts to medical images—Dr. Shiri is transforming how we understand and treat cardiovascular diseases. His commitment to open-source tools and collaborative research is paving the way for a more transparent and innovative future in healthcare. Dive deeper into his vision and contributions that are shaping the future of medicine! ## Pages - [Publication](https://ai-cvm.org/publication/): Welcome to the AI-CVM lab at Inselspital, University of Bern, where we harness the power of artificial intelligence to revolutionize cardiovascular medicine. Our innovative, open-source solutions transform complex medical imaging and clinical data into practical tools that empower cardiologists to make faster, more confident decisions. Committed to transparent and reproducible research, we ensure our multimodal AI systems enhance clinical expertise rather than replace it. Join us in advancing patient care through cutting-edge technology, rigorous evaluation, and collaborative partnerships that bridge the gap between AI research and clinical practice. Discover how we are shaping the future of cardiovascular care! - [Software](https://ai-cvm.org/software/): Welcome to the AI-CVM lab at Inselspital, University of Bern, where we harness the power of artificial intelligence to revolutionize cardiovascular medicine. Our innovative, open-source solutions transform complex medical imaging and clinical data into practical tools that empower cardiologists to make faster, more confident decisions. Committed to transparent and reproducible research, we ensure our multimodal AI systems enhance clinical expertise rather than replace it. Join us in advancing patient care through cutting-edge technology, rigorous evaluation, and collaborative partnerships that bridge the gap between AI research and clinical practice. Discover how we are shaping the future of cardiovascular care! - [AI-CVM Home](https://ai-cvm.org/): The AI in Cardiovascular Medicine Laboratory (AI-CVM) advances artificial intelligence research in cardiovascular health by developing machine and deep learning techniques to address key challenges in cardiovascular disease. The lab analyzes multimodal data, including clinical text, physiological signals, medical images, videos, electronic health records, and omics data, to derive comprehensive insights into patient health. AI-CVM integrates and develops diverse AI paradigms, including vision foundation models, large language models, vision-language models, and agentic AI, to create intelligent and interpretable systems for cardiovascular medicine. Committed to open science, the lab promotes transparency and collaboration by open-sourcing code, models, and datasets. ## Optional - [Agent (MCP protocol)](websites-agents.hostinger.com/ai-cvm.org/mcp) [comment]: # (Generated by Hostinger Tools Plugin)