大规模预训练框架生成模型实现实时低剂量数字减影血管造影成像：一项人工智能系统开发与多中心验证研究。

Large-scale pretrained frame generative model enables real-time low-dose DSA imaging: An AI system development and multi-center validation study.

作者信息

Zhao Huangxuan, Xu Ziyang, Chen Lei, Wu Linxia, Cui Ziwei, Ma Jinqiang, Sun Tao, Lei Yu, Wang Nan, Hu Hongyao, Tan Yiqing, Lu Wei, Yang Wenzhong, Liao Kaibing, Teng Gaojun, Liang Xiaoyun, Li Yi, Feng Congcong, Nie Tong, Han Xiaoyu, Xiang Dongqiao, Majoie Charles B L M, van Zwam Wim H, van der Lugt Aad, van der Sluijs P Matthijs, van Walsum Theo, Feng Yun, Liu Guoli, Huang Yan, Liu Wenyu, Kan Xuefeng, Su Ruisheng, Zhang Weihua, Wang Xinggang, Zheng Chuansheng

机构信息

Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.

School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China.

出版信息

Med. 2025 Jan 10;6(1):100497. doi: 10.1016/j.medj.2024.07.025. Epub 2024 Aug 19.

DOI:10.1016/j.medj.2024.07.025

PMID:39163857

Abstract

BACKGROUND

Digital subtraction angiography (DSA) devices are commonly used in numerous interventional procedures across various parts of the body, necessitating multiple scans per procedure, which results in significant radiation exposure for both doctors and patients. Inspired by generative artificial intelligence techniques, this study proposes GenDSA, a large-scale pretrained multi-frame generative model-based real-time and low-dose DSA imaging system.

METHODS

GenDSA was developed to generate 1-, 2-, and 3-frame sequences following each real frame. A large-scale dataset comprising ∼3 million DSA images from 27,117 patients across 10 hospitals was constructed to pretrain, fine-tune, and validate GenDSA. Two other datasets from 25 hospitals were used for evaluation. Objective evaluations included SSIM and PSNR. Five interventional radiologists independently assessed the quality of the generated frames using the Likert scale and visual Turing test. Scoring consistency among the radiologists was measured using the Kendall coefficient of concordance (W). The Fleiss' kappa values were used for inter-rater agreement analysis for visual Turing tests.

FINDINGS

Using only one-third of the clinical radiation dose, videos generated by GenDSA were perfectly consistent with real videos. Objective evaluations demonstrated that GenDSA's performance (PSNR = 36.83, SSIM = 0.911, generation time = 0.07 s/frame) surpassed state-of-the-art algorithms. Subjective ratings and statistical results from five doctors indicated no significant difference between real and generated videos. Furthermore, the generated videos were comparable to real videos in overall quality (4.905 vs. 4.935) and lesion assessment (4.825 vs. 4.860).

CONCLUSIONS

With clear clinical and translational values, the developed GenDSA can significantly reduce radiation damage to both doctors and patients during DSA-guided procedures.

FUNDING

This study was supported by the National Key R&D Program and the National Natural Science Foundation of China.

摘要

背景

数字减影血管造影（DSA）设备常用于全身各部位的多种介入手术中，每次手术需要进行多次扫描，这会给医生和患者带来大量辐射暴露。受生成式人工智能技术启发，本研究提出了GenDSA，这是一种基于大规模预训练多帧生成模型的实时低剂量DSA成像系统。

方法

开发GenDSA以在每个真实帧之后生成1帧、2帧和3帧序列。构建了一个包含来自10家医院的27117名患者的约300万张DSA图像的大规模数据集，用于对GenDSA进行预训练、微调及验证。使用来自25家医院的另外两个数据集进行评估。客观评估包括结构相似性（SSIM）和峰值信噪比（PSNR）。五名介入放射科医生使用李克特量表和视觉图灵测试独立评估生成帧的质量。使用肯德尔和谐系数（W）测量放射科医生之间的评分一致性。Fleiss' kappa值用于视觉图灵测试的评分者间一致性分析。

结果

仅使用三分之一的临床辐射剂量，GenDSA生成的视频就与真实视频完美一致。客观评估表明，GenDSA的性能（PSNR = 36.83，SSIM = 0.911，生成时间 = 0.07秒/帧）超过了现有算法。五名医生的主观评分和统计结果表明，真实视频和生成视频之间没有显著差异。此外，生成的视频在整体质量（4.905对4.935）和病变评估（4.825对4.860）方面与真实视频相当。