RATIONALE AND OBJECTIVES: This article proposes the use of a disembodied autonomous actor for navigation support within complex virtual medical objects reconstructed from Computed Tomography or Magnetic Resonance Imaging. Such objects are often maze-like, and users risk getting lost within them during Virtual Reality sessions. Therefore, users need paths for guided fly-throughs when performing non-invasive diagnostic tasks. MATERIALS AND METHODS: We present a synthetic vision-based actor capable of finding collision-free paths from a given position to a goal point in environments containing loops and impasses. When navigating, the actor voxelizes the virtual environment and searches for collision-free paths in voxel space by using a back tracking search algorithm. Automata and rules control its search behaviour. The resulting paths can be used in dedicated virtual endoscopy applications. RESULTS: Our path search method has been tested within a variety of tubular virtual anatomical structures in 3D such as aortas, colons, or blood vessels of the brain. The actor finds paths within reasonable time limits, even when considering complex anatomical surface models. CONCLUSION: The method may be used as a valuable tool for assisting virtual endoscopic diagnostic and screening activities in the near future.
RATIONALE AND OBJECTIVES: This article proposes the use of a disembodied autonomous actor for navigation support within complex virtual medical objects reconstructed from Computed Tomography or Magnetic Resonance Imaging. Such objects are often maze-like, and users risk getting lost within them during Virtual Reality sessions. Therefore, users need paths for guided fly-throughs when performing non-invasive diagnostic tasks. MATERIALS AND METHODS: We present a synthetic vision-based actor capable of finding collision-free paths from a given position to a goal point in environments containing loops and impasses. When navigating, the actor voxelizes the virtual environment and searches for collision-free paths in voxel space by using a back tracking search algorithm. Automata and rules control its search behaviour. The resulting paths can be used in dedicated virtual endoscopy applications. RESULTS: Our path search method has been tested within a variety of tubular virtual anatomical structures in 3D such as aortas, colons, or blood vessels of the brain. The actor finds paths within reasonable time limits, even when considering complex anatomical surface models. CONCLUSION: The method may be used as a valuable tool for assisting virtual endoscopic diagnostic and screening activities in the near future.
Authors: Andrew A Gumbs; Vincent Grasso; Nicolas Bourdel; Roland Croner; Gaya Spolverato; Isabella Frigerio; Alfredo Illanes; Mohammad Abu Hilal; Adrian Park; Eyad Elyan Journal: Sensors (Basel) Date: 2022-06-29 Impact factor: 3.847