Toward predicting the evolution of lung tumors during radiotherapy observed on a longitudinal MR imaging study via a deep learning algorithm
Toward predicting the evolution of lung tumors during radiotherapy observed on a longitudinal MR imaging study via a deep learning algorithm
复制标题
DOI：
10.1002/mp.13765
复制
发表时间：
2019-09-06
期刊：
影响因子：
3.8
通讯作者：
Zhang, Pengpeng
中科院分区：
文献类型：
--
作者：
Wang, Chuang;Rimner, Andreas;Zhang, Pengpeng
目的通过深度学习算法预测纵向磁共振成像（MRI）研究下放射治疗期间肺部肿瘤的空间和时间轨迹，以促进自适应放射治疗（ART）。方法对10例肺癌患者在放疗过程中每周进行一次MRI T2 w扫描。在ART工作流程下，我们开发了一个预测神经网络（P-net），利用课程早期获得的图像预测未来几周内肿瘤的空间分布。三步P-net由卷积神经网络组成，用于提取肿瘤及其环境的相关特征，然后是用门控递归单元构建的递归神经网络，用于分析肿瘤对放射治疗的反应轨迹，最后是注意力模型，用于加权每周观察的重要性并产生预测。在留一法下，用Dice和算法预测的肿瘤与专家轮廓之间的均方根表面距离（RMSSD）来衡量P-net的性能。结果9例患者放疗结束时肿瘤缩小60% +/- 27%（平均值+/-标准差）。使用前三周的图像，P-net预测未来几周（4，5，6）的肿瘤，Dice和RMSSD分别为（0.78 +/- 0.22，0.69 +/- 0.24，0.69 +/- 0.26）和（2.1 +/- 1.1 mm，2.3 +/- 0.8 mm，2.6 +/- 1.4 mm）。结论提出的深度学习算法可以在纵向成像研究中捕获和预测肿瘤消退的空间和时间模式。它密切遵循临床工作流程，可以促进ART的决策。一个前瞻性的研究，包括更多的病人是必要的。
Purpose To predict the spatial and temporal trajectories of lung tumor during radiotherapy monitored under a longitudinal magnetic resonance imaging (MRI) study via a deep learning algorithm for facilitating adaptive radiotherapy (ART). Methods We monitored 10 lung cancer patients by acquiring weekly MRI-T2w scans over a course of radiotherapy. Under an ART workflow, we developed a predictive neural network (P-net) to predict the spatial distributions of tumors in the coming weeks utilizing images acquired earlier in the course. The three-step P-net consisted of a convolutional neural network to extract relevant features of the tumor and its environment, followed by a recurrence neural network constructed with gated recurrent units to analyze trajectories of tumor evolution in response to radiotherapy, and finally an attention model to weight the importance of weekly observations and produce the predictions. The performance of P-net was measured with Dice and root mean square surface distance (RMSSD) between the algorithm-predicted and experts-contoured tumors under a leave-one-out scheme. Results Tumor shrinkage was 60% +/- 27% (mean +/- standard deviation) by the end of radiotherapy across nine patients. Using images from the first three weeks, P-net predicted tumors on future weeks (4, 5, 6) with a Dice and RMSSD of (0.78 +/- 0.22, 0.69 +/- 0.24, 0.69 +/- 0.26), and (2.1 +/- 1.1 mm, 2.3 +/- 0.8 mm, 2.6 +/- 1.4 mm), respectively. Conclusion The proposed deep learning algorithm can capture and predict spatial and temporal patterns of tumor regression in a longitudinal imaging study. It closely follows the clinical workflow, and could facilitate the decision-making of ART. A prospective study including more patients is warranted.