Intraocular surgery is challenged by restricted environmental perception and difficulties in instrument depth estimation. The advent of autonomous intraocular surgery represents a milestone in medical technology, given that it can enhance surgical consistency that improves patient safety, shorten surgeon training periods so that more patients can undergo surgery, reduce dependency on human resources, and enable surgeries in remote or extreme environments. In this study, an autonomous robotic system for intraocular surgery (ARISE) was developed, achieving targeted retinal injections throughout the intraocular space. The robotic system achieves intelligent perception and macro/microprecision positioning of the instrument throughout the intraocular space through two key innovations. The first is a multiview spatial fusion that reconciles imaging feature disparities and corrects dynamic spatial misalignments. The second is a criterion-weighted fusion of multisensor data that mitigates inconsistencies in detection range, error magnitude, and sampling frequency. Subretinal and vascular injections were performed on eyeball phantoms, ex vivo porcine eyeballs, and in vivo animal eyeballs. In ex vivo porcine eyeballs, 100% success was achieved for subretinal ( n = 20), central retinal vein (CRV) ( n = 20), and branch retinal vein (BRV) ( n = 20) injections; in in vivo animal eyeballs, 100% success was achieved for subretinal ( n = 16), CRV ( n = 16), and BRV ( n = 16) injections. Compared with manual and teleoperated robotic surgeries, positioning errors were reduced by 79.87 and 54.61%, respectively. These results demonstrate the clinical feasibility of an autonomous intraocular microsurgical robot and its ability to enhance injection precision, safety, and consistency.
Bian et al. (Wed,) studied this question.