Ultra-wide field and new wide field composite retinal image registration with AI-enabled pipeline and 3D distortion correction algorithm.

Autor: Kalaw FGP; Jacobs Retina Center, University of California, San Diego, CA, USA.; Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, CA, USA.; Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, CA, USA., Cavichini M; Jacobs Retina Center, University of California, San Diego, CA, USA.; Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, CA, USA., Zhang J; Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA., Wen B; Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA., Lin AC; Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, CA, USA., Heinke A; Jacobs Retina Center, University of California, San Diego, CA, USA.; Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, CA, USA., Nguyen T; Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA., An C; Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA., Bartsch DG; Jacobs Retina Center, University of California, San Diego, CA, USA., Cheng L; Jacobs Retina Center, University of California, San Diego, CA, USA., Freeman WR; Jacobs Retina Center, University of California, San Diego, CA, USA. wrfreeman@health.ucsd.edu.; Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, CA, USA. wrfreeman@health.ucsd.edu.; Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, CA, USA. wrfreeman@health.ucsd.edu.; Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA. wrfreeman@health.ucsd.edu.
Jazyk: angličtina
Zdroj: Eye (London, England) [Eye (Lond)] 2024 Apr; Vol. 38 (6), pp. 1189-1195. Date of Electronic Publication: 2023 Dec 19.
DOI: 10.1038/s41433-023-02868-3
Abstrakt: Purpose: This study aimed to compare a new Artificial Intelligence (AI) method to conventional mathematical warping in accurately overlaying peripheral retinal vessels from two different imaging devices: confocal scanning laser ophthalmoscope (cSLO) wide-field images and SLO ultra-wide field images.
Methods: Images were captured using the Heidelberg Spectralis 55-degree field-of-view and Optos ultra-wide field. The conventional mathematical warping was performed using Random Sample Consensus-Sample and Consensus sets (RANSAC-SC). This was compared to an AI alignment algorithm based on a one-way forward registration procedure consisting of full Convolutional Neural Networks (CNNs) with Outlier Rejection (OR CNN), as well as an iterative 3D camera pose optimization process (OR CNN + Distortion Correction [DC]). Images were provided in a checkerboard pattern, and peripheral vessels were graded in four quadrants based on alignment to the adjacent box.
Results: A total of 660 boxes were analysed from 55 eyes. Dice scores were compared between the three methods (RANSAC-SC/OR CNN/OR CNN + DC): 0.3341/0.4665/4784 for fold 1-2 and 0.3315/0.4494/4596 for fold 2-1 in composite images. The images composed using the OR CNN + DC have a median rating of 4 (out of 5) versus 2 using RANSAC-SC. The odds of getting a higher grading level are 4.8 times higher using our OR CNN + DC than RANSAC-SC (p < 0.0001).
Conclusion: Peripheral retinal vessel alignment performed better using our AI algorithm than RANSAC-SC. This may help improve co-localizing retinal anatomy and pathology with our algorithm.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz: