Title

Computing Cyclotorsion In Refractive Cataract Surgery

Keywords

Cyclotorsion; Iris registration; Medical image analysis; Ophthalmology; Refractive cataract surgery; Surgical guidance

Abstract

Goal: In refractive surgery, astigmatism-correcting treatments are generally planned with the aid of some diagnostic imaging device and often executed by some computer guided laser system. In the transition from sitting down at a diagnostic device to lying down beneath a laser system, a phenomenon known as cyclotorsion (rotation of the eye within the socket) occurs. Hence, registration between lasers and diagnostic devices is necessary. The purpose of this paper is to present a newly developed algorithm that accomplishes robust registration using images of the patient's iris in the context of laser-assisted cataract surgery, and evaluate its efficacy. Methods: The proposed iris registration algorithm was tested on real cataract patient images obtained from commercially available devices. Accuracy was measured against manual registrations performed by trained humans. Conservative bounds on success and failure rates were computed using novel statistical methods. Results: The algorithm better approximated the cyclotorsion as averaged over manual measurements from three trained humans than any of the three individual humans, with a 95% tolerance interval of ±1.36°. In addition, a success rate ≥99.0% was observed for an acceptance threshold setting that allowed for a false registration rate ≤1.00 ∗ 10-3%. Conclusion: The proposed iris registration algorithm accurately and consistently compensates for cyclotorsion in laser-assisted cataract surgery. Significance: This paper details the first algorithm to be used for iris registration in laser-assisted cataract surgery. Enabling surgeons to make use of this algorithm in real surgeries is expected to have a significant impact on astigmatism management in cataract surgery.

Publication Date

10-1-2016

Publication Title

IEEE Transactions on Biomedical Engineering

Volume

63

Issue

10

Number of Pages

2155-2168

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/TBME.2015.2511759

Socpus ID

84990909328 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84990909328

This document is currently not available here.

Share

COinS