Laparoscopic Liver
Laparoscopic liver surgery benefits greatly from accurate intraoperative registration of pre-operative imaging data with the live surgical view, improving surgical precision and reducing complications. Current research focuses on developing robust and efficient registration methods using various approaches, including deep learning architectures (e.g., neural radiance fields, graph convolutional networks) and geometric algorithms (e.g., SLAM, ICP), often combined with biomechanical models to account for organ deformation. These advancements aim to improve the accuracy and speed of registration, ultimately enhancing the safety and effectiveness of minimally invasive liver surgery. The development of large, annotated datasets is also crucial for training and evaluating these advanced algorithms.
Papers
Intraoperative Registration by Cross-Modal Inverse Neural Rendering
Maximilian Fehrentz, Mohammad Farid Azampour, Reuben Dorent, Hassan Rasheed, Colin Galvin, Alexandra Golby, William M. Wells, Sarah Frisken, Nassir Navab, Nazim Haouchine
SLAM assisted 3D tracking system for laparoscopic surgery
Jingwei Song, Ray Zhang, Wenwei Zhang, Hao Zhou, Maani Ghaffari