Zhang Yucheng, Lobo-Mueller Edrise M, Karanicolas Paul, Gallinger Steven, Haider Masoom A, Khalvati Farzad
Department of Medical Imaging, University of Toronto, Toronto, ON, Canada.
Department of Diagnostic Imaging and Department of Oncology, Faculty of Medicine and Dentistry, Cross Cancer Institute, University of Alberta, Edmonton, AB, Canada.
Front Artif Intell. 2020 Oct 5;3:550890. doi: 10.3389/frai.2020.550890. eCollection 2020.
Pancreatic Ductal Adenocarcinoma (PDAC) is one of the most aggressive cancers with an extremely poor prognosis. Radiomics has shown prognostic ability in multiple types of cancer including PDAC. However, the prognostic value of traditional radiomics pipelines, which are based on hand-crafted radiomic features alone is limited. Convolutional neural networks (CNNs) have been shown to outperform radiomics models in computer vision tasks. However, training a CNN from scratch requires a large sample size which is not feasible in most medical imaging studies. As an alternative solution, CNN-based transfer learning models have shown the potential for achieving reasonable performance using small datasets. In this work, we developed and validated a CNN-based transfer learning model for prognostication of overall survival in PDAC patients using two independent resectable PDAC cohorts. The proposed transfer learning-based prognostication model for overall survival achieved the area under the receiver operating characteristic curve of 0.81 on the test cohort, which was significantly higher than that of the traditional radiomics model (0.54). To further assess the prognostic value of the models, the predicted probabilities of death generated from the two models were used as risk scores in a univariate Cox Proportional Hazard model and while the risk score from the traditional radiomics model was not associated with overall survival, the proposed transfer learning-based risk score had significant prognostic value with hazard ratio of 1.86 (95% Confidence Interval: 1.15-3.53, -value: 0.04). This result suggests that transfer learning-based models may significantly improve prognostic performance in typical small sample size medical imaging studies.
胰腺导管腺癌（PDAC）是侵袭性最强的癌症之一，预后极差。放射组学已在包括PDAC在内的多种癌症中显示出预后评估能力。然而，仅基于手工提取的放射组学特征的传统放射组学流程的预后价值有限。在计算机视觉任务中，卷积神经网络（CNN）已被证明优于放射组学模型。然而，从头开始训练CNN需要大量样本，这在大多数医学影像研究中是不可行的。作为一种替代解决方案，基于CNN的迁移学习模型已显示出使用小数据集实现合理性能的潜力。在这项工作中，我们开发并验证了一种基于CNN的迁移学习模型，用于使用两个独立的可切除PDAC队列对PDAC患者的总生存期进行预后评估。所提出的基于迁移学习的总生存期预后模型在测试队列中的受试者工作特征曲线下面积为0.81，显著高于传统放射组学模型（0.54）。为了进一步评估模型的预后价值，将两个模型生成的死亡预测概率用作单变量Cox比例风险模型中的风险评分，虽然传统放射组学模型的风险评分与总生存期无关，但所提出的基于迁移学习的风险评分具有显著的预后价值，风险比为1.86（95%置信区间：1.15 - 3.53，P值：0.04）。这一结果表明，基于迁移学习的模型可能会显著提高典型小样本量医学影像研究中的预后性能。
