A two-stage MAE-plus-contrastive foundation model, Cardiac-CLIP aligns 3D cardiac CT with structured radiology text and reports state-of-the-art zero-shot and fine-tuned performance on classification, retrieval, and clinical risk prediction.
Deep convolutional neural networks to predict cardiovascular risk from computed tomography.Nature communications, 12(1):715, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Cardiac-CLIP: A Vision-Language Foundation Model for 3D Cardiac CT Images
A two-stage MAE-plus-contrastive foundation model, Cardiac-CLIP aligns 3D cardiac CT with structured radiology text and reports state-of-the-art zero-shot and fine-tuned performance on classification, retrieval, and clinical risk prediction.