标题： 多环境终身深度强化学习用于医学影像 显示英文标题

标题： Multi-environment lifelong deep reinforcement learning for medical imaging

摘要： 深度强化学习（DRL）在医学影像领域正受到越来越多的关注。 然而，医学影像任务的环境在成像方位、成像序列和病理方面不断变化。 为此，我们开发了一个终身DRL框架SERIL，以在不发生灾难性遗忘的情况下，持续学习新的任务。 SERIL是利用基于选择性经验回放的终身学习技术，在一系列24种不同的成像环境中，对脑部MRI中的五个解剖标志点进行定位而开发的。 与两种基线设置MERT（多环境最佳情况）和SERT（单环境最差情况）相比，SERIL的性能表现出色，在所有120个任务中，平均距离目标标志点$9.90\pm7.35$像素，而MERT为$10.29\pm9.07$，SERT为$36.37\pm22.41$（$p<0.05$），这表明了在动态变化的成像环境中持续学习多个任务的卓越潜力。 显示英文摘要

摘要： Deep reinforcement learning(DRL) is increasingly being explored in medical imaging. However, the environments for medical imaging tasks are constantly evolving in terms of imaging orientations, imaging sequences, and pathologies. To that end, we developed a Lifelong DRL framework, SERIL to continually learn new tasks in changing imaging environments without catastrophic forgetting. SERIL was developed using selective experience replay based lifelong learning technique for the localization of five anatomical landmarks in brain MRI on a sequence of twenty-four different imaging environments. The performance of SERIL, when compared to two baseline setups: MERT(multi-environment-best-case) and SERT(single-environment-worst-case) demonstrated excellent performance with an average distance of $9.90\pm7.35$ pixels from the desired landmark across all 120 tasks, compared to $10.29\pm9.07$ for MERT and $36.37\pm22.41$ for SERT($p<0.05$), demonstrating the excellent potential for continuously learning multiple tasks across dynamically changing imaging environments.