In The international journal of medical robotics + computer assisted surgery : MRCAS
Robotic ophthalmic endoscope holders allow surgeons to execute dual-hand operations in eye surgery. To prevent needle-like endoscopes from invading the retina when moving, surgeons expect visual and real-time information about the relative special relationship between the endoscope and fundus. This study develops a real-time fundus reconstruction method to map the position of the endoscope inside the eyeball. First, using deep learning, the method estimates the distance between the fundus part corresponding to every pixel of the RGB endoscopic image and the endoscope. Then, by combining the estimated distance with the kinematics of a robotic holder, the point cloud representing the present fundus area is generated, and by which the size and position of the eyeball are estimated. This method shows a real-time frequency of 10 Hz, which is robust to eyeball movement. The error of fundus reconstruction is about 0.5 mm, and the error of eyeball estimation is about 1 mm, which satisfies the requirements of ophthalmologists. This article is protected by copyright. All rights reserved.
Zhou Dongbo, Takeyama Hayato, Nakao Shintaro, Koh-Hei Sonoda, Tadano Kotaro
2023-Jan-10
