Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Xinyuan, Wang, Lili, Chen, Ruoyu, Liu, Bowen, Zhang, Weiyi, Yang, Xi, Feng, Yifan, He, Mingguang, Shi, Danli
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.17346
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916538994393088
author Wu, Xinyuan
Wang, Lili
Chen, Ruoyu
Liu, Bowen
Zhang, Weiyi
Yang, Xi
Feng, Yifan
He, Mingguang
Shi, Danli
author_facet Wu, Xinyuan
Wang, Lili
Chen, Ruoyu
Liu, Bowen
Zhang, Weiyi
Yang, Xi
Feng, Yifan
He, Mingguang
Shi, Danli
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17346
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FFA Sora, video generation as fundus fluorescein angiography simulator
Wu, Xinyuan
Wang, Lili
Chen, Ruoyu
Liu, Bowen
Zhang, Weiyi
Yang, Xi
Feng, Yifan
He, Mingguang
Shi, Danli
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title FFA Sora, video generation as fundus fluorescein angiography simulator
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.17346