Temporally Consistent and Controllable Video Generation of 2D Cine CMR via Latent Space Motion Modeling
arXiv:2606.14759v1 Announce Type: cross Abstract: Cine cardiac magnetic resonance is the gold standard for assessing cardiac function, but the scarcity of public datasets limits the development of advanced data-driven models. To address this limitation, we propose a generative method for synthesizing temporally coherent and anatomically consistent cardiac sequences. Our text-to-video framework decouples cardiac spatial structure from temporal motion. First, a fine-tuned diffusion model synthesizes an initial frame from a clinical text prompt, controlling anatomical features. Then, a latent flo
The rapid advancements in generative AI, particularly diffusion models and text-to-video capabilities, are enabling new applications in specialized domains like medical imaging.
This development addresses a critical data scarcity issue in medical AI, particularly for cardiac imaging, which can accelerate diagnostic tool development and personalization of care.
The ability to synthesize temporally consistent and anatomically accurate medical video data overcomes a major bottleneck for training and validating advanced medical AI models.
- · Medical AI developers
- · Healthcare providers
- · Patients with cardiac conditions
- · Generative AI research institutions
- · Traditional medical data acquisition methodsreliant on large clinical datasets w
Improved diagnosis and treatment strategies for cardiac diseases due to more robust AI models.
Reduced costs and increased accessibility of medical AI development, democratizing advanced diagnostic tools.
Potential for broader application of synthetic data generation across other medical imaging modalities and specialized fields of medicine.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI