Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance
 
conference paper

Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance

Zhang, William
•
Huang, Si Yu
•
Yang, Jiancheng  
Show more
Linguraru, MG
•
Dou, Q
Show more
January 1, 2024
Medical Image Computing And Computer Assisted Intervention - Miccai 2024, Pt I
27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

Fundus Fluorescein Angiography (FFA) is a critical tool for assessing retinal vascular dynamics and aiding in the diagnosis of eye diseases. However, its invasive nature and less accessibility compared to Color Fundus (CF) images pose significant challenges. Current CF to FFA translation methods are limited to static generation. In this work, we pioneer dynamic FFA video generation from static CF images. We introduce an autoregressive GAN for smooth, memory-saving frame-by-frame FFA synthesis. To enhance the focus on dynamic lesion changes in FFA regions, we design a knowledge mask based on clinical experience. Leveraging this mask, our approach integrates innovative knowledge mask-guided techniques, including knowledge-boosted attention, knowledge-aware discriminators, and mask-enhanced patchNCE loss, aimed at refining generation in critical areas and addressing the pixel misalignment challenge. Our method achieves the best FVD of 1503.21 and PSNR of 11.81 compared to other common video generation approaches. Human assessment by an ophthalmologist confirms its high generation quality. Notably, our knowledge mask surpasses supervised lesion segmentation masks, offering a promising non-invasive alternative to traditional FFA for research and clinical applications. The code is available at https://github.com/Michi-3000/Fundus2Video.

  • Details
  • Metrics
Type
conference paper
DOI
10.1007/978-3-031-72378-0_64
Web of Science ID

WOS:001342205800064

Author(s)
Zhang, William

Hong Kong Polytechnic University

Huang, Si Yu

Clemson University

Yang, Jiancheng  

École Polytechnique Fédérale de Lausanne

Chen, Ruoyu

Hong Kong Polytechnic University

Ge, Zongyuan

Monash University

Zheng, Yingfeng

Sun Yat Sen University

Shi, Danli

Hong Kong Polytechnic University

He, Mingguang

Hong Kong Polytechnic University

Editors
Linguraru, MG
•
Dou, Q
•
Feragen, A
•
Giannarou, S
•
Glocker, B
•
Lekadir, K
•
Schnabel, JA
Date Issued

2024-01-01

Publisher

Springer Nature

Publisher place

CHAM

Published in
Medical Image Computing And Computer Assisted Intervention - Miccai 2024, Pt I
ISBN of the book

978-3-031-72377-3

978-3-031-72378-0

Series title/Series vol.

Lecture Notes in Computer Science; 15001

ISSN (of the series)

0302-9743

1611-3349

Start page

689

End page

699

Subjects

Video Generation

•

Generative Adversarial Network

•

Autoregressive Generation

•

Retinal Fundus Photography

•

Fluorescence Angiography

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
CVLAB  
Event nameEvent acronymEvent placeEvent date
27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

Marrakesh, MOROCCO

2024-10-06 - 2024-10-10

FunderFunding(s)Grant NumberGrant URL

Global STEM Professorship Scheme

P0046113;P0048623

HKSAR

P0048623

Available on Infoscience
January 31, 2025
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/246119
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés