About this Research Topic
Deep generative artificial intelligence (AI) models are a family of neural networks capable of learning the data distribution from a large set of training samples and then generating realistic new data samples. They are among the most exciting technical breakthroughs in deep learning in recent years. They have demonstrated superior performance, especially in medical data synthesis, and quickly evolved to become the state-of-the-art for data-generation tasks.
In cardiovascular medicine, generative AI models such as Generative Adversarial Nets, Stable Diffusion, and Transformers, have great potential to transform a wide range of research utilizing cardiovascular imaging and non-image information. This topic focuses on novel generative AI approaches and applications to various cardiovascular research, including but not limited to:
• image contrast enhancement and contrast dose reduction;
• data synthesis, augmentation, and domain transfer;
• fast image reconstruction, super-resolution, and noise reduction;
• segmentation and tracking of anatomical features;
• Classification.
It also aims to address the technical challenges of generative AI in model training, validation, transparency, and robustness.
This is an expanded collection following the previous research topic Generative Adversarial Networks in Cardiovascular Research . We welcome researchers with a background in machine learning, basic science, clinical cardiology, or cross-disciplinary fields to contribute high-quality papers in methodology, clinical applications, and reviews.
In cardiovascular medicine, generative AI models such as Generative Adversarial Nets, Stable Diffusion, and Transformers, have great potential to transform a wide range of research utilizing cardiovascular imaging and non-image information. This topic focuses on novel generative AI approaches and applications to various cardiovascular research, including but not limited to:
• image contrast enhancement and contrast dose reduction;
• data synthesis, augmentation, and domain transfer;
• fast image reconstruction, super-resolution, and noise reduction;
• segmentation and tracking of anatomical features;
• Classification.
It also aims to address the technical challenges of generative AI in model training, validation, transparency, and robustness.
This is an expanded collection following the previous research topic Generative Adversarial Networks in Cardiovascular Research . We welcome researchers with a background in machine learning, basic science, clinical cardiology, or cross-disciplinary fields to contribute high-quality papers in methodology, clinical applications, and reviews.
Keywords: Generative AI, contrast enhancement, data synthesis, image reconstruction, segmentation
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
