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

TL;DR

This paper introduces SF-VD, a video diffusion model that generates labeled fluoroscopy videos to improve guidewire segmentation, reducing the need for extensive annotated datasets and enhancing model accuracy.

Contribution

The paper presents a novel segmentation-guided video diffusion model that synthesizes realistic fluoroscopy videos with annotations, boosting guidewire segmentation performance with limited labeled data.

Findings

Generated videos are of high quality and realistic.

Data augmentation with SF-VD improves segmentation accuracy.

Model outperforms existing methods in guidewire segmentation.

Abstract

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.