CVAI Catalog

·

View Catalog

tune

3 models found

·

3 public code

·

3 public weights

ViTa

Technical University of Munich (Zhang, Hager, Pan et al.) · 2025

graph_1

Code & model weights public

Multimodal cardiac MRI foundation model that fuses 3D+T cine CMR (short-axis and long-axis views) with tabular patient health records (demographics, metabolic, and lifestyle factors) from 42,000 UK Biobank participants. Two-stage self-supervised pretraining -- masked-image reconstruction, then imaging-tabular contrastive alignment -- produces representations that transfer to whole-heart segmentation, cardiac phenotype/physiological-feature regression, and cardiac/metabolic disease classification within one unified framework.

Cardiac MRI

Filter by Modality:
Cardiac MRI

Structured EHR

Filter by Modality:
Text & EHR

Multimodal

Filter by Modality:
Multimodal

Cardiac chamber segmentation

Filter by Disease / Trait:
Structural Heart & Cardiomyopathy

General Purpose / Multi-task

Filter by Disease / Trait:
General / Foundation

Coronary artery disease / stenosis

Filter by Disease / Trait:
Coronary & Ischemic Disease

Segmentation

Filter by Task Type:
Segmentation & Detection

Regression

Filter by Task Type:
Regression

Binary classification

Filter by Task Type:
Classification

Hybrid

Filter by Architecture:
Hybrid / Multi-branch

PyTorch

Filter by Framework:
PyTorch

MIT

Filter by License:
Permissive


Model ID: 0062

·

Subject Count: 74,916

CMR-CLIP

Cleveland Clinic / Case Western (Nakashima et al.) · 2026

graph_1

Code & model weights public

Vision-language model that jointly embeds a cardiac MRI study, treated as video, with the impression section of its clinical report. Combines a video encoder over cine/LGE frame sequences with a Bio+ClinicalBERT text encoder using CLIP-style contrastive training. Supports zero-shot and few-shot classification of cardiomyopathies, amyloidosis, and LV dysfunction, plus image/report retrieval and structured report drafting. Trained on a private, single-institution corpus of roughly 11,000-14,000 CMR study-report pairs from Cleveland Clinic and Case Western.

Cardiac MRI

Filter by Modality:
Cardiac MRI

Clinical text

Filter by Modality:
Text & EHR

Multimodal

Filter by Modality:
Multimodal

General Purpose / Multi-task

Filter by Disease / Trait:
General / Foundation

Non-ischemic cardiomyopathy

Filter by Disease / Trait:
Structural Heart & Cardiomyopathy

Ischemic cardiomyopathy

Filter by Disease / Trait:
Coronary & Ischemic Disease

Cardiac amyloidosis

Filter by Disease / Trait:
Structural Heart & Cardiomyopathy

LV systolic dysfunction (LVSD)

Filter by Disease / Trait:
Cardiac Function & Hemodynamics

LV dilation

Filter by Disease / Trait:
Structural Heart & Cardiomyopathy

Left ventricular hypertrophy (LVH)

Filter by Disease / Trait:
Structural Heart & Cardiomyopathy

Multi-label classification

Filter by Task Type:
Classification

Binary classification

Filter by Task Type:
Classification

Embedding

Filter by Task Type:
Representation Learning

Hybrid

Filter by Architecture:
Hybrid / Multi-branch

PyTorch

Filter by Framework:
PyTorch

MIT

Filter by License:
Permissive


Model ID: 0007

·

Subject Count: 12,500

CineMA

UCL / Mycardium (Fu et al.) · 2025

graph_1

Code & model weights public

Foundation model for cine cardiac MRI, self-supervised via masked autoencoding on nearly 75,000 UK Biobank scans. Uses a Vision Transformer with a convolutional stem, unified across long-axis and short-axis views. Fine-tuned checkpoints are released for ventricle and myocardium segmentation, ejection-fraction regression, cardiovascular disease classification, and landmark localization across several public benchmark datasets (ACDC, M&Ms, M&Ms2, EMIDEC, and others).

Cardiac MRI

Filter by Modality:
Cardiac MRI

General Purpose / Multi-task

Filter by Disease / Trait:
General / Foundation

Cardiac chamber segmentation

Filter by Disease / Trait:
Structural Heart & Cardiomyopathy

LVEF estimation

Filter by Disease / Trait:
Cardiac Function & Hemodynamics

Binary classification

Filter by Task Type:
Classification

Segmentation

Filter by Task Type:
Segmentation & Detection

Regression

Filter by Task Type:
Regression

Detection / localization

Filter by Task Type:
Segmentation & Detection

Vision Transformer

Filter by Architecture:
Transformer

PyTorch

Filter by Framework:
PyTorch

MIT

Filter by License:
Permissive


Model ID: 0003

·

Subject Count: 74,916