EchoChat is a generative multimodal vision‑language model that performs comprehensive echocardiographic analysis, emulating a cardiologist’s cognitive workflow. Trained on 46,358 examinations, it achieves state‑of‑the‑art performance across 33 cardiac conditions, including 15 new ones, and outperforms existing foundation models in both recognition and quantification tasks. In a blinded reader study, reports co‑generated with EchoChat were rated higher in diagnostic accuracy and completeness, improving F1 score from 72.78% to 82.75%.
arXiv:2603.22179v2 Announce Type: replace Abstract: Cardiovascular disease remains the leading cause of global mortality, with progress hindered by human interpretation of complex cardiac tests. Curr...
arXiv:2606. 28164v1 Announce Type: cross Abstract: Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis.
arXiv:2608.22323v1 Announce Type: new Abstract: The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest. However, existing benchmarks largely focus...
arXiv:2512.09944v4 Announce Type: replace Abstract: Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning,...
arXiv:2607. 20814v1 Announce Type: new Abstract: The electrocardiogram (ECG) is a cornerstone of cardiac as- sessment, yet clinical deployment of deep learning models remains con- strained by limited interpretability and the hallucination risk of large language models (LLMs).
EchoTab is a representation learning framework for multi‑view echocardiography that uses measurement‑specific tokens as an intermediate representation between echo views and diagnosis. Each token attends to the views relevant to its measurement and is trained via tabular reconstruction to predict the measurement value, producing a factorized representation that encodes clinically meaningful structural and functional properties. Experiments on two datasets show that EchoTab improves diagnosis classification and that its learned attention aligns with cardiologists’ established measurement‑view relationships.
arXiv:2606. 00123v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxies for clinical use, relying on isolated inputs and simplified recognition-style tasks.
The paper presents a supervised large language model (LLM) that performs late fusion of heterogeneous echocardiography AI outputs directly in language space. By aggregating view‑specific predicted findings and measurements, the LLM learns a case‑level fusion function without requiring conversion to binary decisions or feature engineering. In a patient‑level three‑fold cross‑validation on 859 examinations, the method matched the best reference strategy and surpassed a general‑purpose LLM that lacked task‑specific training.
arXiv:2611.02581v1 Announce Type: cross Abstract: Automated liver ultrasound report generation improves the diagnosis of liver diseases by producing clinically structured descriptions of anatomical a...
arXiv:2606. 14766v1 Announce Type: cross Abstract: Autonomous medical and robotic systems increasingly rely on intelligent perception and reasoning capabilities to interpret visual data and support clinical decision making.
NV-Reason-CT is a generative vision‑language model designed for chest and abdominal CT analysis that preserves native 3D visual encoding and incorporates radiologist‑guided reasoning. The system couples a 3D vision transformer with a language model, feeding all visual tokens and their 3D coordinates directly into language decoding to maintain volumetric spatial information. Trained on a curated corpus of about 550,000 multimodal instruction examples, the model supports abnormality classification, report generation, and interactive reasoning, achieving strong performance on CT benchmarks and reducing expert interpretation time by 50%.
The paper introduces MedDream, a radiographic world model that learns a shared continuous latent state from paired chest radiograph-text observations. MedDream outperforms existing diagnostic and generative AI models across eight clinical datasets, improving diagnostic reasoning, resident concordance, and evidence generation. Targeted synthetic augmentation guided by subgroup performance gaps further enhances model performance, particularly for Asian patients.