Artificial Intelligence for Lamellar Keratoplasty

Abstract

The training of artificial intelligence (AI) is becoming increasingly popular. More and more studies on lamellar keratoplasty are also being published. In particular, the possibility of non-invasive and high-resolution imaging technology of optical coherence tomography predestines lamellar keratoplasty for the application of AI. Although it is technically easy to perform, there are only a few studies on the use of AI to optimise lamellar keratoplasty. The existing studies focus primarily on the prediction probability of rebubbling in DMEK and DSAEK and on their graft adherence, as well as on the formation of a big bubble in DALK. In addition, the automated recording of routine parameters such as corneal oedema, endothelial cell density or the size of the graft detachment is now possible using AI. The optimisation of lamellar keratoplasty using AI holds great potential. Nevertheless, there are limitations to the published algorithms, in that they can only be transferred between centres, surgeons and different device manufacturers to a limited extent.

Keywords

DALK - DMEK - DSAEK - DSEK - AI - lamellar keratoplasty

Publication History

Received: 14 February 2024

Accepted: 17 March 2024

Accepted Manuscript online:
19 March 2024

Article published online:
28 June 2024

• References/Literatur

• 1 Hüttmann G, Lankenau E, Schulz-Wackerbarth C. et al. [Optical coherence tomography: from retina imaging to intraoperative use – a review]. Klin Monbl Augenheilkd 2009; 226: 958-964
• 2 Hayashi T, Händel A, Matthaei M, Cursiefen C, Siebelmann S. Die OCT des vorderen Augenabschnitts bei Hornhauttransplantationen. In: Heindl LM, Siebelmann S. Hrsg. Optische Kohärenztomographie des vorderen Augenabschnitts: Atlas. Berlin, Heidelberg: Springer; 2023: 165-191
• 3 Melles GR. Posterior lamellar keratoplasty: DLEK to DSEK to DMEK. Cornea 2006; 25: 879-881
• 4 Ashworth N, De Champlain AF, Kain N. A review of multi-source feedback focusing on psychometrics, pitfalls and some possible solutions. SN Social Sciences 2021; 1: 1-12
• 5 Hayashi T, Masumoto H, Tabuchi H. et al. A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty. Sci Rep 2021; 11: 18559
• 6 Pan J, Liu W, Ge P. et al. Real-time segmentation and tracking of excised corneal contour by deep neural networks for DALK surgical navigation. Comput Methods Programs Biomed 2020; 197: 105679
• 7 Muijzer M, Hoven C, Frank L. et al. A machine learning approach to explore predictors of graft detachment following posterior lamellar keratoplasty: a nationwide registry study. Sci Rep 2022; 12: 17705
• 8 Siebelmann S, Kolb K, Scholz P. et al. The Cologne rebubbling study: a reappraisal of 624 rebubblings after Descemet membrane endothelial keratoplasty. Br J Ophthalmol 2021; 105: 1082-1086
• 9 Patefield A, Meng Y, Airaldi M. et al. Deep Learning Using Preoperative AS-OCT Predicts Graft Detachment in DMEK. Transl Vis Sci Technol 2023; 12: 14
• 10 Treder M, Lauermann JL, Alnawaiseh M. et al. Using deep learning in automated detection of graft detachment in Descemet membrane endothelial keratoplasty: a pilot study. Cornea 2019; 38: 157-161
• 11 Hayashi T, Tabuchi H, Masumoto H. et al. A deep learning approach in rebubbling after Descemetʼs membrane endothelial keratoplasty. Eye Contact Lens 2020; 46: 121-126
• 12 Hayashi T, Iliasian RM, Matthaei M. et al. Transferability of an artificial intelligence algorithm predicting rebubblings after descemet membrane endothelial keratoplasty. Cornea 2023; 42: 544-548
• 13 Vigueras-Guillén JP, van Rooij J, Engel A. et al. Deep learning for assessing the corneal endothelium from specular microscopy images up to 1 year after ultrathin-DSAEK surgery. Transl Vis Sci Technol 2020; 9: 49
• 14 Bitton K, Zéboulon P, Ghazal W. et al. Deep Learning Model for the Detection of Corneal Edema Before Descemet Membrane Endothelial Keratoplasty on Optical Coherence Tomography Images. Transl Vis Sci Technol 2022; 11: 19
• 15 Heslinga FG, Alberti M, Pluim JP. et al. Quantifying graft detachment after Descemetʼs membrane endothelial keratoplasty with deep convolutional neural networks. Transl Vis Sci Technol 2020; 9: 48
• 16 OʼBrien RC, Ishwaran H, Szczotka-Flynn LB. et al. Random survival forests analysis of intraoperative complications as predictors of Descemet stripping automated endothelial keratoplasty graft failure in the Cornea Preservation Time Study. JAMA Ophthalmol 2021; 139: 191-197
• 17 Yousefi S, Takahashi H, Hayashi T. Predicting the likelihood of need for future keratoplasty intervention using artificial intelligence. Ocul Surf 2020; 18: 320-325