Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pan, Shaoyan, Liu, Yikang, Zhao, Lin, Chen, Eric Z., Chen, Xiao, Chen, Terrence, Sun, Shanhui
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916586277830656
author Pan, Shaoyan
Liu, Yikang
Zhao, Lin
Chen, Eric Z.
Chen, Xiao
Chen, Terrence
Sun, Shanhui
author_facet Pan, Shaoyan
Liu, Yikang
Zhao, Lin
Chen, Eric Z.
Chen, Xiao
Chen, Terrence
Sun, Shanhui
contents The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16050
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy
Pan, Shaoyan
Liu, Yikang
Zhao, Lin
Chen, Eric Z.
Chen, Xiao
Chen, Terrence
Sun, Shanhui
Computer Vision and Pattern Recognition
Artificial Intelligence
The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.
title Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.16050