Zhang Molin, Xu Junshen, Turk Esra Abaci, Grant P Ellen, Golland Polina, Adalsteinsson Elfar
Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, USA.
Fetal-Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital, Boston, MA, USA.
Med Image Comput Comput Assist Interv. 2020 Oct;12266:396-405. doi: 10.1007/978-3-030-59725-2_38. Epub 2020 Sep 29.
Fetal MRI is heavily constrained by unpredictable and substantial fetal motion that causes image artifacts and limits the set of viable diagnostic image contrasts. Current mitigation of motion artifacts is predominantly performed by fast, single-shot MRI and retrospective motion correction. Estimation of fetal pose in real time during MRI stands to benefit prospective methods to detect and mitigate fetal motion artifacts where inferred fetal motion is combined with online slice prescription with low-latency decision making. Current developments of deep reinforcement learning (DRL), offer a novel approach for fetal landmarks detection. In this task 15 agents are deployed to detect 15 landmarks simultaneously by DRL. The optimization is challenging, and here we propose an improved DRL that incorporates priors on physical structure of the fetal body. First, we use graph communication layers to improve the communication among agents based on a graph where each node represents a fetal-body landmark. Further, additional reward based on the distance between agents and physical structures such as the fetal limbs is used to fully exploit physical structure. Evaluation of this method on a repository of 3-mm resolution in vivo data demonstrates a mean accuracy of landmark estimation within 10 mm of ground truth as 87.3%, and a mean error of 6.9 mm. The proposed DRL for fetal pose landmark search demonstrates a potential clinical utility for online detection of fetal motion that guides real-time mitigation of motion artifacts as well as health diagnosis during MRI of the pregnant mother.
胎儿磁共振成像（MRI）受到不可预测且显著的胎儿运动严重限制，这种运动导致图像伪影，并限制了可行的诊断图像对比度集。当前对运动伪影的缓解主要通过快速单次MRI和回顾性运动校正来实现。在MRI过程中实时估计胎儿姿势有助于采用前瞻性方法来检测和减轻胎儿运动伪影，其中推断的胎儿运动与在线切片处方相结合，并进行低延迟决策。深度强化学习（DRL）的当前发展为胎儿地标检测提供了一种新方法。在这项任务中，部署了15个智能体通过DRL同时检测15个地标。优化具有挑战性，在此我们提出一种改进的DRL，其纳入了胎儿身体物理结构的先验信息。首先，我们使用图通信层来改善基于图的智能体之间的通信，其中每个节点代表一个胎儿身体地标。此外，基于智能体与诸如胎儿肢体等物理结构之间的距离的额外奖励被用于充分利用物理结构。在一个3毫米分辨率的体内数据存储库上对该方法进行评估，结果表明地标估计的平均准确率在距离真实值10毫米范围内为87.3%，平均误差为6.9毫米。所提出的用于胎儿姿势地标搜索的DRL展示了在在线检测胎儿运动方面的潜在临床效用，该运动可指导在孕妇MRI期间实时减轻运动伪影以及进行健康诊断。
