Real-time liver tumor localization via a single x-ray projection using deep graph neural network-assisted biomechanical modeling.
Real-time liver tumor localization via a single x-ray projection using deep graph neural network-assisted biomechanical modeling.
复制标题
实时肝脏肿瘤定位通过单x线投影使用深度图神经网络辅助生物力学建模。
DOI：
10.1088/1361-6560/ac6b7b
复制
发表时间：
2022-05-24
影响因子：
3.5
通讯作者：
Zhang, You
中科院分区：
文献类型：
--
作者：
Shao, Hua-Chieh;Wang, Jing;Bai, Ti;Chun, Jaehee;Park, Justin C.;Jiang, Steve;Zhang, You
实时成像在图像引导的放射治疗中是非常理想的，因为它提供了治疗期间患者解剖结构和运动的即时信息，并使在线治疗适应性能够实现最高的肿瘤靶向精度。由于采集时间极其有限，只能采集一个或几个X射线投影用于实时成像，这对从稀少的投影定位肿瘤提出了实质性挑战。对于肝脏放射治疗，肿瘤与周围正常肝脏组织之间的对比度降低进一步加剧了这种挑战。在这里，我们提出了一个结合基于图神经网络的深度学习和生物力学建模的框架，以从单个机载X射线投影实时跟踪肝脏肿瘤。肝脏肿瘤跟踪分两步实现。首先，开发一个深度学习网络，使用从X射线投影中学习的图像特征来预测肝脏表面变形。其次，通过生物力学建模估计肝内变形，使用肝脏表面变形作为边界条件，通过有限元分析求解肿瘤运动。使用10名肝癌患者的数据集评估了所提出的框架的准确性。结果显示，基于图形神经网络的深度学习模型可实现准确的肝脏表面配准，并在生物力学建模后转化为准确、无基准的肝脏肿瘤定位（平均定位误差<1.2（±1.2）mm）。该方法展示了其对治疗内和实时3D肝脏肿瘤监测和定位的潜力。它可用于促进4D剂量累积、多叶准直器跟踪和实时计划自适应。该方法也可以适用于其他解剖部位。
Real-time imaging is highly desirable in image-guided radiotherapy, as it provides instantaneous knowledge of patients’ anatomy and motion during treatments and enables online treatment adaptation to achieve the highest tumor targeting accuracy. Due to extremely limited acquisition time, only one or few x-ray projections can be acquired for real-time imaging, which poses a substantial challenge to localize the tumor from the scarce projections. For liver radiotherapy, such a challenge is further exacerbated by the diminished contrast between the tumor and the surrounding normal liver tissues. Here, we propose a framework combining graph neural network-based deep learning and biomechanical modeling to track liver tumor in real-time from a single onboard x-ray projection. Liver tumor tracking is achieved in two steps. First, a deep learning network is developed to predict the liver surface deformation using image features learned from the x-ray projection. Second, the intra-liver deformation is estimated through biomechanical modeling, using the liver surface deformation as the boundary condition to solve tumor motion by finite element analysis. The accuracy of the proposed framework was evaluated using a dataset of 10 patients with liver cancer. The results show accurate liver surface registration from the graph neural network-based deep learning model, which translates into accurate, fiducial-less liver tumor localization after biomechanical modeling (<1.2 (±1.2) mm average localization error). The method demonstrates its potentiality towards intra-treatment and real-time 3D liver tumor monitoring and localization. It could be applied to facilitate 4D dose accumulation, multi-leaf collimator tracking and real-time plan adaptation. The method can be adapted to other anatomical sites as well.
登录
查看更多内容
影响因子：
3.8
作者：
Chen X;Ouyang L;Yan H;Jia X;Li B;Lyu Q;Zhang Y;Wang J
通讯作者：
Wang J
DOI：
10.1016/j.ejmp.2020.02.001
发表时间：
2020-02-01
影响因子：
3.4
作者：
Hirai, Ryusuke;Sakata, Yukinobu;Mori, Shinichiro
通讯作者：
Mori, Shinichiro
影响因子：
3.8
作者：
Keall, Paul J.;Sawant, Amit;Stathakis, Sotirios
通讯作者：
Stathakis, Sotirios
DOI：
10.1016/s0360-3016(01)01649-2
发表时间：
2001-09-01
影响因子：
7
作者：
Balter, JM;Dawson, LA;Ten Haken, R
通讯作者：
Ten Haken, R
影响因子：
4.1
作者：
Byeon, Seong Pil;Lee, Doo Yong
通讯作者：
Lee, Doo Yong