Multi-environment lifelong deep reinforcement learning for medical imaging
This addresses the challenge of evolving imaging environments in medical imaging for practitioners, though it is incremental as it builds on existing lifelong learning techniques.
The paper tackled the problem of catastrophic forgetting in deep reinforcement learning for medical imaging by developing SERIL, a lifelong learning framework that achieved an average distance of 9.90±7.35 pixels across 120 tasks, outperforming baselines.
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.