A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets
基于EDM2的高分辨率合成胎儿超声成像基础生成模型,源自开放数据集
专题命中 扩散模型 :diffusion(abstract);分类 cs.CV
AI总结 该研究针对胎儿超声AI数据稀缺问题,提出基于EDM2的合成框架,生成512×512图像,在分类任务中准确率达93.36%,优于真实数据训练结果,为胎儿超声AI提供开放资源。
Comments Short paper for the 30th Conference on Medical Image Understanding and Analysis