18288355. VOLUMETRIC FILTER OF FLUOROSCOPIC SWEEP VIDEO simplified abstract (Covidien LP)
Contents
VOLUMETRIC FILTER OF FLUOROSCOPIC SWEEP VIDEO
Organization Name
Inventor(s)
Ariel Birenbaum of Raanana (IL)
Shaked Pessah of Maccabim-Reut (IL)
Guy Alexandroni of Yehud-Monosson (IL)
VOLUMETRIC FILTER OF FLUOROSCOPIC SWEEP VIDEO - A simplified explanation of the abstract
This abstract first appeared for US patent application 18288355 titled 'VOLUMETRIC FILTER OF FLUOROSCOPIC SWEEP VIDEO
The patent application involves a method for object detection using fluoroscopic images and 3D volumetric reconstruction.
- Receiving a fluoroscopic video with multiple images captured by a rotating fluoroscope.
- Generating a 3D volumetric reconstruction from the fluoroscopic images.
- Deleting values outside a region of interest around an object in the 3D reconstruction.
- Creating 2D images from the remaining 3D reconstruction.
- Detecting the object in the 2D images to find its initial position.
- Refining the detected initial position of the object.
Potential Applications: - Medical imaging for surgical procedures. - Industrial inspection and quality control. - Robotics for object recognition and manipulation.
Problems Solved: - Accurate object detection in complex environments. - Improved visualization of objects in 3D space.
Benefits: - Enhanced precision in object detection. - Reduced errors in identifying object positions. - Increased efficiency in image analysis.
Commercial Applications: Title: Advanced Object Detection System for Medical and Industrial Use This technology can be used in medical facilities for surgical planning and guidance, as well as in industrial settings for quality control and automation processes.
Questions about Object Detection Technology: 1. How does this technology improve object detection accuracy compared to traditional methods? 2. What are the potential limitations of using fluoroscopic images for object detection in real-time applications?
Original Abstract Submitted
Object detection including receiving a fluoroscopic video including a plurality of fluoroscopic images captured by a fluoroscope rotated about a patient, generating a three-dimensional (3D) volumetric reconstruction from the fluoroscopic images, deleting values in the 3D volumetric reconstruction beyond a region of interest about an object, generating 2D images from a remaining 3D volumetric reconstruction following the deleting of values: detecting the object in the 2D images to determine an initial position of the object, and refining the detected initial position of the object.
