Centre for Medical Image Computing, University College London, London, United Kingdom.
Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom.
Phys Med Biol. 2024 May 20;69(11):115010. doi: 10.1088/1361-6560/ad46dd.
Minimally invasive ablation techniques for renal cancer are becoming more popular due to their low complication rate and rapid recovery period. Despite excellent visualisation, one drawback of the use of computed tomography (CT) in these procedures is the requirement for iodine-based contrast agents, which are associated with adverse reactions and require a higher x-ray dose. The purpose of this work is to examine the use of time information to generate synthetic contrast enhanced images at arbitrary points after contrast agent injection from non-contrast CT images acquired during renal cryoablation cases. To achieve this, we propose a new method of conditioning generative adversarial networks with normalised time stamps and demonstrate that the use of a HyperNetwork is feasible for this task, generating images of competitive quality compared to standard generative modelling techniques. We also show that reducing the receptive field can help tackle challenges in interventional CT data, offering significantly better image quality as well as better performance when generating images for a downstream segmentation task. Lastly, we show that all proposed models are robust enough to perform inference on unseen intra-procedural data, while also improving needle artefacts and generalising contrast enhancement to other clinically relevant regions and features.
由于微创消融技术具有并发症发生率低、恢复期快等优点，其在肾癌治疗中的应用越来越广泛。尽管计算机断层扫描（CT）在这些手术中有很好的可视化效果，但在这些手术中使用 CT 存在一个缺点，即需要使用碘基造影剂，这会引起不良反应，而且需要更高的 X 射线剂量。本研究旨在探讨利用时间信息，从肾冷冻消融病例中获取的非对比增强 CT 图像，在注射造影剂后的任意时间点生成合成的对比增强图像。为此，我们提出了一种新的方法，用归一化时间戳来条件生成对抗网络，并证明了使用超网络对于这项任务是可行的，生成的图像质量与标准生成模型技术相当。我们还表明，减少感受野有助于解决介入 CT 数据中的挑战，为下游分割任务生成图像时，可显著提高图像质量和性能。最后，我们表明，所有提出的模型都足够稳健，可以对未在术中使用的数据进行推断，同时还可以改善针迹伪影，并将对比增强推广到其他临床相关区域和特征。
