Communicative Reinforcement Learning Agents for Landmark Detection in Brain Images
This addresses the need for accurate landmark detection in medical imaging, but it is incremental as it builds on existing multi-agent methods with communication enhancements.
The paper tackled the problem of anatomical landmark detection in 3D brain images by proposing a communicative multi-agent reinforcement learning system, which outperformed previous single-agent approaches on adult MRI and fetal ultrasound datasets.
Accurate detection of anatomical landmarks is an essential step in several medical imaging tasks. We propose a novel communicative multi-agent reinforcement learning (C-MARL) system to automatically detect landmarks in 3D brain images. C-MARL enables the agents to learn explicit communication channels, as well as implicit communication signals by sharing certain weights of the architecture among all the agents. The proposed approach is evaluated on two brain imaging datasets from adult magnetic resonance imaging (MRI) and fetal ultrasound scans. Our experiments show that involving multiple cooperating agents by learning their communication with each other outperforms previous approaches using single agents.