NeuralBoneReg Solved the Hardest Alignment Problem in Robotic Surgery Without a Single Labeled Training Example.

NeuralBoneReg: How a Self-Supervised Neural Framework Solved the Hardest Problem in Robotic Orthopedic Surgery

A team from Balgrist University Hospital and ETH Zurich built an instance-specific self-supervised framework that registers bone surfaces across imaging modalities by learning a continuous neural distance field from the preoperative scan and using thousands of neural hypothesis generation heads…

NeuralBoneReg: How a Self-Supervised Neural Framework Solved the Hardest Problem in Robotic Orthopedic Surgery Read More »