School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China; Department of Radiology, Columbia University Medical Center, 630 West 168th Street, New York, NY 10032.
Department of Radiology, Columbia University Medical Center, 630 West 168th Street, New York, NY 10032; Gustave Roussy, Université Paris-Saclay, Université Paris-Saclay, Département D'imagerie Médicale, Villejuif, France.
Acad Radiol. 2020 Feb;27(2):e10-e18. doi: 10.1016/j.acra.2019.02.024. Epub 2019 May 28.
To develop a deep learning-based algorithm to automatically identify optimal portal venous phase timing (PVP-timing) so that image analysis techniques can be accurately performed on post contrast studies.
681 CT-scans (training: 479 CT-scans; validation: 202 CT-scans) from a multicenter clinical trial in patients with liver metastases from colorectal cancer were retrospectively analyzed for algorithm development and validation. An additional external validation was performed on a cohort of 228 CT-scans from gastroenteropancreatic neuroendocrine cancer patients. Image acquisition was performed according to each centers' standard CT protocol for single portal venous phase, portal venous acquisition. The reference gold standard for the classification of PVP-timing as either optimal or nonoptimal was based on experienced radiologists' consensus opinion. The algorithm performed automated localization (on axial slices) of the portal vein and aorta upon which a novel dual input Convolutional Neural Network calculated a probability of the optimal PVP-timing.
The algorithm automatically computed a PVP-timing score in 3 seconds and reached area under the curve of 0.837 (95% CI: 0.765, 0.890) in validation set and 0.844 (95% CI: 0.786, 0.889) in external validation set.
A fully automated, deep-learning derived PVP-timing algorithm was developed to classify scans' contrast-enhancement timing and identify scans with optimal PVP-timing. The rapid identification of such scans will aid in the analysis of quantitative (radiomics) features used to characterize tumors and changes in enhancement with treatment in a multitude of settings including quantitative response criteria such as Choi and MASS which rely on reproducible measurement of enhancement.
开发一种基于深度学习的算法，以自动识别最佳门静脉期（PVP-timing），从而使图像分析技术能够准确地应用于对比后研究。
对来自结直肠癌肝转移多中心临床试验的 681 例 CT 扫描（训练：479 例 CT 扫描；验证：202 例 CT 扫描）进行回顾性分析，以开发和验证算法。还对来自胃肠胰神经内分泌癌患者的 228 例 CT 扫描进行了额外的外部验证。图像采集是根据每个中心的单门静脉期、门静脉采集的标准 CT 协议进行的。将 PVP-timing 分类为最佳或非最佳的参考金标准是基于经验丰富的放射科医生的共识意见。该算法在轴向切片上自动定位门静脉和主动脉，然后一个新的双输入卷积神经网络计算出最佳 PVP-timing 的概率。
该算法在 3 秒内自动计算出 PVP-timing 评分，在验证集和外部验证集的 AUC 分别为 0.837（95%CI：0.765，0.890）和 0.844（95%CI：0.786，0.889）。
开发了一种完全自动化的、基于深度学习的 PVP-timing 算法，用于分类扫描的对比增强时间，并识别具有最佳 PVP-timing 的扫描。快速识别此类扫描将有助于分析定量（放射组学）特征，这些特征用于在多种环境中对肿瘤进行特征描述以及随治疗的增强变化，包括定量反应标准，如 Choi 和 MASS，这些标准依赖于增强的可重复测量。
