Dr. Kang Li is an Associate Professor in the Department of Orthopaedics at Rutgers New Jersey Medical School. He is also a graduate faculty member in the Departments of Biomedical Engineering and Computer Science at Rutgers University. He was an Assistant Professor in the Department of Industrial and Systems Engineering at Rutgers University before joining the medical school. He serves as Associate Editor of IEEE Transactions on Human-Machine Systems, IEEE ACCESS, and BMC Musculoskeletal Disorders.
The 3D morphology and quantitative assessment of knee articular cartilages (i.e., femoral, tibial, and patellar cartilage) in magnetic resonance (MR) imaging is of great importance for knee osteoarthritis (OA) diagnostic decision making. However, effective and efficient delineation of all the knee articular cartilages in large-sized and high-resolution 3D MR knee data is still an open challenge. We propose a novel framework to solve the MR knee cartilage segmentation task. The key contribution is the adversarial learning based collaborative multi-agent segmentation network. We use three parallel segmentation agents to label cartilages in their respective region of interest (ROI), and then fuse the three cartilages by a novel ROI-fusion layer. The collaborative learning is driven by an adversarial sub-network. The ROI-fusion layer not only fuses the individual cartilages from multiple agents, but also backpropagates the training loss from the adversarial sub-network to each agent to enable joint learning of shape and spatial constraints. Extensive evaluations are conducted on a dataset including hundreds of MR knee volumes with diverse populations, and the proposed method shows superior performance.
Institute of Medical Robotics