文献速递心血管MR

基于黑血延迟钆增强心脏磁共振深度学习合成白血栓影像

Deep Learning Synthesis of White-Blood From Dark-Blood Late Gadolinium Enhancement Cardiac Magnetic Resonance.
PubMed 文献 · Invest Radiol · 2024-05-01

本研究利用215例患者的黑血延迟钆增强(DB-LGE)和白血延迟钆增强(WB-LGE)数据,训练无配对图像到图像翻译深度学习模型(CycleGAN和对比无配对翻译),以从DB-LGE生成合成WB-LGE图像。CycleGAN生成的合成图像最逼真,视觉读者区分真伪的正确率为55%,合成图像与真实WB-LGE的瘢痕负荷定量高度相关,平均偏差0.44%(一致性界限-10.85%至11.74%),但真实WB图像平均质量评分3.53/5高于合成图像的3.03(P=0.009)。作者结论认为该模型可在不增加扫描时间的情况下评估两种对比度,但临床采用前需进一步评估。

要点

  • CycleGAN模型可从DB-LGE生成合成WB-LGE,视觉上难以区分真伪(正确分类率55%)。
  • 合成WB-LGE与真实WB-LGE的瘢痕负荷定量高度相关,平均偏差0.44%(一致性界限-10.85%至11.74%)。
  • 真实WB图像平均质量评分3.53/5高于合成图像的3.03(P=0.009)。

核心结论

  • 本研究提出CycleGAN模型从DB-LGE图像生成合成WB-LGE,以在不增加扫描时间的情况下评估两种图像对比度;这是对人工智能生成的合成医学图像的临床聚焦评估,但临床采用前需进一步评估。

研究设计与样本

  • 研究使用215例患者的DB-LGE和WB-LGE数据,训练两种无配对图像到图像翻译深度学习模型(CycleGAN和对比无配对翻译),每种模型有5种不同的损失函数超参数设置;基于Fréchet起始距离和专家读者视觉评估确定每种模型的最佳超参数;然后直接比较最优超参数的CycleGAN和对比无配对翻译模型;最后用最佳模型基于合成WB-LGE图像进行瘢痕定量,并与真实采集的WB-LGE比较。

关键影像表现/征象

  • CycleGAN架构生成从DB-LGE图像合成的WB-LGE图像最逼真。
  • 视觉读者区分真实与合成图像的正确分类率为55%。
  • 合成数据与真实采集图像的瘢痕负荷定量高度相关。
  • Bland-Altman分析显示真实WB与合成白血图像之间瘢痕负荷百分比的平均偏差为0.44%,一致性界限为-10.85%至11.74%。
  • 真实WB图像的平均图像质量评分为3.53/5,高于合成白血图像的3.03,P=0.009。

局限性

  • 临床采用前需进一步评估。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: Dark-blood late gadolinium enhancement (DB-LGE) cardiac magnetic resonance has been proposed as an alternative to standard white-blood LGE (WB-LGE) imaging protocols to enhance scar-to-blood contrast without compromising scar-to-myocardium contrast. In practice, both DB and WB contrasts may have clinical utility, but acquiring both has the drawback of additional acquisition time. The aim of this study was to develop and evaluate a deep learning method to generate synthetic WB-LGE images from DB-LGE, allowing the assessment of both contrasts without additional scan time.

MATERIALS AND METHODS: DB-LGE and WB-LGE data from 215 patients were used to train 2 types of unpaired image-to-image translation deep learning models, cycle-consistent generative adversarial network (CycleGAN) and contrastive unpaired translation, with 5 different loss function hyperparameter settings each. Initially, the best hyperparameter setting was determined for each model type based on the Fréchet inception distance and the visual assessment of expert readers. Then, the CycleGAN and contrastive unpaired translation models with the optimal hyperparameters were directly compared. Finally, with the best model chosen, the quantification of scar based on the synthetic WB-LGE images was compared with the truly acquired WB-LGE.

RESULTS: The CycleGAN architecture for unpaired image-to-image translation was found to provide the most realistic synthetic WB-LGE images from DB-LGE images. The results showed that it was difficult for visual readers to distinguish if an image was true or synthetic (55% correctly classified). In addition, scar burden quantification with the synthetic data was highly correlated with the analysis of the truly acquired images. Bland-Altman analysis found a mean bias in percentage scar burden between the quantification of the real WB and synthetic white-blood images of 0.44% with limits of agreement from -10.85% to 11.74%. The mean image quality of the real WB images (3.53/5) was scored higher than the synthetic white-blood images (3.03), P = 0.009.

CONCLUSIONS: This study proposed a CycleGAN model to generate synthetic WB-LGE from DB-LGE images to allow assessment of both image contrasts without additional scan time. This work represents a clinically focused assessment of synthetic medical images generated by artificial intelligence, a topic with significant potential for a multitude of applications. However, further evaluation is warranted before clinical adoption.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Jaspers TJM, Martens B, Crawley R, et al. Deep Learning Synthesis of White-Blood From Dark-Blood Late Gadolinium Enhancement Cardiac Magnetic Resonance. Invest Radiol. 2024. PMID: 38687025. doi:10.1097/RLI.0000000000001086

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。