Investigating keypoint descriptors for camera relocalization in endoscopy surgery.

Isabela Hernández Roger D Soberanis-Mukul Jan Emily Mangulabnan Manish Sahu Jonas Winter S Swaroop VedulaMasaru IshiiGregory D Hager Russell H Taylor Jie Ying Wu

Published in: International journal of computer assisted radiology and surgery (2023)

Patient-specific learning-based descriptors can relocalize images that are well distributed across the inspected anatomy, even where the anatomy is modified. However, camera relocalization in endoscopic sequences remains a persistently challenging problem, and future research is necessary to increase the robustness and accuracy of this technique.

Keyphrases

convolutional neural network
minimally invasive
high speed
deep learning
coronary artery bypass
ultrasound guided
current status
optical coherence tomography
neural network
high resolution
acute coronary syndrome
machine learning
mass spectrometry