Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound
This work addresses automated plane localization in 3D ultrasound to improve efficiency and reduce user-dependence, representing an incremental advance with domain-specific applications in medical imaging.
The authors tackled the problem of localizing multiple standard planes in 3D ultrasound volumes using a multi-agent reinforcement learning framework, achieving accuracies of 7.05 degrees/2.21 mm, 8.62 degrees/2.36 mm, and 5.93 degrees/0.89 mm for different planes.
3D ultrasound (US) is widely used due to its rich diagnostic information, portability and low cost. Automated standard plane (SP) localization in US volume not only improves efficiency and reduces user-dependence, but also boosts 3D US interpretation. In this study, we propose a novel Multi-Agent Reinforcement Learning (MARL) framework to localize multiple uterine SPs in 3D US simultaneously. Our contribution is two-fold. First, we equip the MARL with a one-shot neural architecture search (NAS) module to obtain the optimal agent for each plane. Specifically, Gradient-based search using Differentiable Architecture Sampler (GDAS) is employed to accelerate and stabilize the training process. Second, we propose a novel collaborative strategy to strengthen agents' communication. Our strategy uses recurrent neural network (RNN) to learn the spatial relationship among SPs effectively. Extensively validated on a large dataset, our approach achieves the accuracy of 7.05 degree/2.21mm, 8.62 degree/2.36mm and 5.93 degree/0.89mm for the mid-sagittal, transverse and coronal plane localization, respectively. The proposed MARL framework can significantly increase the plane localization accuracy and reduce the computational cost and model size.