用文字生成眼底荧光血管造影动态视频，辅助医生学习诊断。
FFA Sora, video generation as fundus fluorescein angiography simulator
- 通过小波流变分自编码器与扩散Transformer，将报告转为动态视频。
- 生成视频与文本匹配度高，客观指标显示FVD=329.78，VQAScore=0.61。
- 保护患者隐私且视觉质量好，适合医学教育与临床培训使用。
眼底荧光血管造影（FFA）对视网膜血管病诊断至关重要，但初学者常难以解读图像。本研究开发了FFA Sora，一种文生视频模型，利用小波流变分自编码器（WF-VAE）和扩散Transformer（DiT），将FFA报告转化为动态视频。模型在匿名数据集上训练，客观评估显示：弗雷切特视频距离（FVD）为329.78，感知图像块相似度（LPIPS）为0.48，视觉问答得分（VQAScore）为0.61。特定评估表明生成视频与文本提示具有可接受的对齐性，BERTScore为0.35。检索评估中，模型表现出良好的隐私保护能力，平均召回率@K为0.073。人工评估显示视频视觉质量良好，平均得分1.570（1为最佳，5为最差）。该模型解决了大规模FFA数据共享带来的隐私问题，并有助于医学教育。
原文摘要 · Abstract (English)
Fundus fluorescein angiography (FFA) is critical for diagnosing retinal vascular diseases, but beginners often struggle with image interpretation. This study develops FFA Sora, a text-to-video model that converts FFA reports into dynamic videos via a Wavelet-Flow Variational Autoencoder (WF-VAE) and a diffusion transformer (DiT). Trained on an anonymized dataset, FFA Sora accurately simulates disease features from the input text, as confirmed by objective metrics: Frechet Video Distance (FVD) = 329.78, Learned Perceptual Image Patch Similarity (LPIPS) = 0.48, and Visual-question-answering Score (VQAScore) = 0.61. Specific evaluations showed acceptable alignment between the generated videos and textual prompts, with BERTScore of 0.35. Additionally, the model demonstrated strong privacy-preserving performance in retrieval evaluations, achieving an average Recall@K of 0.073. Human assessments indicated satisfactory visual quality, with an average score of 1.570(scale: 1 = best, 5 = worst). This model addresses privacy concerns associated with sharing large-scale FFA data and enhances medical education.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。