Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging
Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging
复制标题
DOI：
10.1158/1078-0432.ccr-18-2495
复制
发表时间：
2019-06-01
影响因子：
11.5
通讯作者：
Aerts, Hugo J. W. L.
中科院分区：
文献类型：
--
作者：
Xu, Yiwen;Hosny, Ahmed;Aerts, Hugo J. W. L.
目的：肿瘤是一个不断进化的生物系统，而医学成像在监测整个治疗过程中的变化方面具有独特的优势。虽然在空间和时间上定性地跟踪病变可能是微不足道的，但结合连续成像数据的临床相关的自动放射组学方法的开发更具挑战性。在这项研究中，我们通过分析局部晚期非小细胞肺癌（NSCLC）患者的时间序列CT图像来评估深度学习网络预测临床结局的能力。实验设计：数据集A由179例接受明确放化疗的III期NSCLC患者组成，包括治疗前和治疗后1个月、3个月和6个月随访的CT图像（581次扫描）。使用卷积神经网络（CNN）与递归神经网络（RNN）的转移学习，使用单种子点肿瘤定位来开发模型。对数据集B进行病理学反应验证，数据集包括89例接受放化疗和手术治疗的NSCLC患者（178次扫描）。结果：使用时间序列扫描的深度学习模型可显著预测生存率和癌症特异性结局（进展、远处转移和局部区域复发）。模型性能随着对CNN模型的每次额外的后续扫描而增强（例如，2-年总生存率：AUC = 0.74，P < 0.05）。模型将患者分为低死亡风险组和高死亡风险组，这与总生存率显著相关[HR = 6.16; 95%置信区间（CI），2.17-17.44; P < 0.001]。该模型还显著预测了数据集B中的病理反应（P = 0.016）。结论：我们证明了深度学习可以在多个时间点整合成像扫描，以改善临床结果预测。基于人工智能的非侵入性放射组学生物标志物可以在临床上产生重大影响，因为它们成本低，对人类输入的要求最低。
Purpose: Tumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non-small cell lung cancer (NSCLC).Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans).Results: Deep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17-17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016).Conclusions: We demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.