arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.03035eess.IVcs.CV
收藏

用于单帧空间-语义超声心动图合成的免训练条件视频扩散模型

Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis

Institute for Artificial Intelligence, University of Engineering and Technology, Vietnam National University(越南国家大学工程技术大学人工智能学院);VinUni-Illinois Smart Health Center, VinUniversity(范南大学校伊利诺伊智能健康中心);College of Engineering & Computer Science, VinUniversity(范南大学工程与计算机科学学院)

Van Phi Nguyen, Tri Nhan Luong Ha, Huy Hieu Pham, Quoc Long Tran

AI总结:

提出Free-Echo,基于3D-Unet时间注意力模型和SDEdit免训练条件化,仅凭单张舒张末期分割图生成空间对齐的逼真超声心动图。

摘要:

条件视频扩散模型(CDM)在视频合成方面已展现出良好效果,有望生成逼真的超声心动图,以解决数据稀缺问题。然而,当前的CDM需要配对的分割图和超声心动图数据集。我们提出了一种名为Free-Echo的新方法,可仅凭单张舒张末期分割图生成逼真的超声心动图,且无需额外训练数据。该方法基于带时间注意力层的3D-Unet模型,并采用基于SDEdit的免训练条件化方法,以分割图作为条件。我们在两个公开超声心动图数据集CAMUS和EchoNet-Dynamic上评估了模型。结果表明,该模型能够生成与输入分割图空间对齐的合理超声心动图,性能可与基于训练的CDM相媲美。本研究为从单张分割图生成超声心动图开辟了新可能,可用于医学影像中的数据增强、域适应及其他应用。代码位于https://github.com/gungui98/echo-free。

英文摘要:

Conditional video diffusion models (CDM) have shown promising results for video synthesis, potentially enabling the generation of realistic echocardiograms to address the problem of data scarcity. However, current CDMs require a paired segmentation map and echocardiogram dataset. We present a new method called Free-Echo for generating realistic echocardiograms from a single end-diastolic segmentation map without additional training data. Our method is based on the 3D-Unet with Temporal Attention Layers model and is conditioned on the segmentation map using a training-free conditioning method based on SDEdit. We evaluate our model on two public echocardiogram datasets, CAMUS and EchoNet-Dynamic. We show that our model can generate plausible echocardiograms that are spatially aligned with the input segmentation map, achieving performance comparable to training-based CDMs. Our work opens up new possibilities for generating echocardiograms from a single segmentation map, which can be used for data augmentation, domain adaptation, and other applications in medical imaging. Our code is available at \url{https://github.com/gungui98/echo-free}

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑