Skip to main content
QUICK REVIEW

[论文解读] A Deep learning Approach to Generate Contrast-Enhanced Computerised Tomography Angiography without the Use of Intravenous Contrast Agents

Anirudh Chandrashekar, Ashok Handa|arXiv (Cornell University)|Mar 2, 2020
Advanced X-ray and CT Imaging被引用 4
一句话总结

本研究提出一种基于深度学习的方法,采用循环生成对抗网络(CycleGAN)从非增强CT扫描生成对比增强CT血管造影(CTA)图像,从而无需使用静脉对比剂。该方法通过利用非增强数据中固有的亨氏单位(Hounsfield Unit)差异,成功区分血液、血栓和血管壁组织,生成的CTA图像在视觉保真度上与真实对比增强扫描高度相似。

ABSTRACT

Contrast-enhanced computed tomography angiograms (CTAs) are widely used in cardiovascular imaging to obtain a non-invasive view of arterial structures. However, contrast agents are associated with complications at the injection site as well as renal toxicity leading to contrast-induced nephropathy (CIN) and renal failure. We hypothesised that the raw data acquired from a non-contrast CT contains sufficient information to differentiate blood and other soft tissue components. We utilised deep learning methods to define the subtleties between soft tissue components in order to simulate contrast enhanced CTAs without contrast agents. Twenty-six patients with paired non-contrast and CTA images were randomly selected from an approved clinical study. Non-contrast axial slices within the AAA from 10 patients (n = 100) were sampled for the underlying Hounsfield unit (HU) distribution at the lumen, intra-luminal thrombus and interface locations. Sampling of HUs in these regions revealed significant differences between all regions (p<0.001 for all comparisons), confirming the intrinsic differences in the radiomic signatures between these regions. To generate a large training dataset, paired axial slices from the training set (n=13) were augmented to produce a total of 23,551 2-D images. We trained a 2-D Cycle Generative Adversarial Network (cycleGAN) for this non-contrast to contrast (NC2C) transformation task. The accuracy of the cycleGAN output was assessed by comparison to the contrast image. This pipeline is able to differentiate between visually incoherent soft tissue regions in non-contrast CT images. The CTAs generated from the non-contrast images bear strong resemblance to the ground truth. Here we describe a novel application of Generative Adversarial Network for CT image processing. This is poised to disrupt clinical pathways requiring contrast enhanced CT imaging.

研究动机与目标

  • 开发一种无需使用静脉对比剂即可生成诊断级对比增强CT血管造影(CTA)图像的方法。
  • 克服碘化对比剂引起的对比剂肾病和患者不适等局限性。
  • 利用非增强CT数据中固有的放射组学差异,模拟对比增强效果。
  • 实现对历史非增强CT扫描的回顾性分析,用于血管形态学及动脉瘤进展建模。
  • 探索该方法在其他血管和软组织结构中的可行性。

提出的方法

  • 训练了一个二维循环生成对抗网络(CycleGAN),以实现从非增强到对比增强(NC2C)的图像转换。
  • 使用13名患者的非增强与对比增强CT轴向切片作为训练数据,经数据增强后达到23,551幅图像。
  • 分析了管腔、管腔内血栓(ILT)及界面区域的亨氏单位(HU)分布,发现差异具有统计学显著性(p < 0.001)。
  • 生成器网络通过将非增强图像中的HU模式映射到相应的对比增强特征,学习生成对比增强的外观。
  • 判别器网络被训练以区分真实对比增强图像与生成图像,从而确保输出结果的真实性。
  • 通过将生成的CTA图像与真实对比增强扫描进行视觉和结构相似性比较,对模型进行评估。

实验结果

研究问题

  • RQ1深度学习方法能否仅基于非增强CT数据准确模拟CT血管造影中的对比增强效果?
  • RQ2非增强CT扫描中固有的亨氏单位差异是否足以区分血液、血栓和血管壁组织?
  • RQ3基于CycleGAN的方法能否在无配对训练数据的情况下生成具有诊断价值的CTA类图像?
  • RQ4该方法在多大程度上能保留解剖细节,如小血管(如肾动脉)和复杂界面(如血栓-血液边界)?
  • RQ5该方法能否扩展至主动脉以外的其他血管和软组织结构?

主要发现

  • 在管腔、管腔内血栓(ILT)及界面区域之间发现了显著的亨氏单位(HU)差异(所有比较p < 0.001),证实了固有放射组学差异的存在。
  • CycleGAN模型成功从非增强CT扫描中生成了与真实对比增强图像高度相似的CTA类图像。
  • 该模型展示了在非增强扫描中对视觉上不连贯的软组织区域(如血液、血栓和血管壁)进行视觉区分的能力。
  • 生成的图像保留了精细的解剖细节,包括肾动脉和椎动脉等小动脉分支。
  • 该方法使历史非增强CT扫描的潜在再利用成为可能,可用于高级血管形态学分析,包括腹主动脉瘤的三维几何与体积建模。
  • 该方法可能减少对静脉对比剂的依赖,从而降低对比剂肾病及注射相关并发症的风险。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。