Abstract
Purpose
To develop and evaluate an automated deep learning model to predict the anatomical outcome of rhegmatogenous retinal detachment (RRD) surgery.
Methods
Six thousand six hundred and sixty-one digital images of RRD treated by vitrectomy and internal tamponade were collected from the British and Eire Association of Vitreoretinal Surgeons database. Each image was classified as a primary surgical success or a primary surgical failure. The synthetic minority over-sampling technique was used to address class imbalance. We adopted the state-of-the-art deep convolutional neural network architecture Inception v3 to train, validate, and test deep learning models to predict the anatomical outcome of RRD surgery. The area under the curve (AUC), sensitivity, and specificity for predicting the outcome of RRD surgery was calculated for the best predictive deep learning model.
Results
The deep learning model was able to predict the anatomical outcome of RRD surgery with an AUC of 0.94, with a corresponding sensitivity of 73.3% and a specificity of 96%.
Conclusion
A deep learning model is capable of accurately predicting the anatomical outcome of RRD surgery. This fully automated model has potential application in surgical care of patients with RRD.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Mitry D, Charteris DG, Fleck BW, Campbell H, Singh J (2010) The epidemiology of rhegmatogenous retinal detachment: geographical variation and clinical associations. Br J Ophthalmol 94:678–684
Wickham L, Bunce C, Wong D, Charteris DG (2011) Retinal detachment repair by vitrectomy: simplified formulae to estimate the risk of failure. Br J Ophthalmol 95:1239–1244
Wickham L, Ho-Yen GO, Bunce C, Wong D, Charteris DG (2011) Surgical failure following primary retinal detachment surgery by vitrectomy: risk factors and functional outcomes. Br J Ophthalmol 95:1234–1238
Williamson TH, Lee EJK, Shunmugam M (2014) Characteristics of rhegmatogenous retinal detachment and their relationship to success rates of surgery. Retina 34:1421–1427
Mitry D, Awan MA, Borooah S et al (2012) Surgical outcome and risk stratification for primary retinal detachment repairs: results from the Scottish Retinal Detachment study. Br J Ophthalmol 96:730–734
Thompson JA, Snead MP, Billington BM, Barrie T, Thompson JR, Sparrow JM (2002) National audit of the outcome of primary surgery for rhegmatogenous retinal detachment. II Clinical outcomes. Eye (Lond) 16:771–777
Pastor JC, Fernandez I, Rodriguez de la Rua E et al (2008) Surgical outcomes for primary rhegmatogenous retinal detachments in phakic and pseudophakic patients: the Retina 1 project – report 2. Br J Ophthalmol 92:378–382
Feltgen N, Heimann H, Hoerauf H, Walter P, Hilgers R-D, Heussen N (2013) Scleral buckling versus primary vitrectomy in rhegmatogenous retinal detachment study (SPR study): risk assessment of anatomical outcome. SPR study report no.7. Acta Ophthalmol 91:282–287
Adelman RA, Parnes AJ, Michalewska Z, Ducournau D (2014) Clinical variables associated with failure of retinal detachment repair: the European vitreo-retinal society retinal detachment study report number 4. Ophthalmology 121:1715–1719
Haugstad M, Moosmayer S, Bragadottir R (2017) Primary rhegmatogenous retinal detachment – surgical methods and anatomical outcome. Acta Ophthalmol 95:247–251
Bonde A, Varadarajan KM, Bonde N et al (2021) Assessing the utility of deep neural networks in predicting postoperative surgical complications: a retrospective study. Lancet Digit Health 3:e471-485
Ferrara M, Mehta A, Qureshi H et al (2021) Phenotype and outcomes of phakic versus pseudophakic primary rhegmatogenous retinal detachments: cataract or cataract surgery related? Am J Ophthalmol 222:318–327
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Fernandez A, Garcia S, Herrera F, Chawla NV (2018) SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J Artif Intell Res 61:863–905
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. ImageNet: a large-scale hierarchical image database. Paper presented at: 2009 Institute of Electrical and Electronics Engineers Conference on Computer Vision and Pattern Recognition; June 20–25, 2009; Miami, FL
Yosinski J, Clune J, Bengio Y, Lipson H. How transferable are features in deep neural networks? Paper presented at: 27th International Conference on Neural Information Processing Systems; December 8–13, 2014: Montreal, Quebec, Canada
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. Paper presented at: 2017 Institute of Electrical and Electronics Engineers International Conference on Computer Vision; October 22–29, 2017; Venice, Italy
Sinthanayothin C, Boyce JF, Cook HL, Williamson TH (1999) Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. Br J Ophthalmol 83:902–910
Gardner GG, Keating D, Williamson TH, Elliott AT (1996) Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool. Br J Ophthalmol 80:940–944
Usher D, Dumskyjs M, Himaga M, Williamson TH, Nussey S, Boyce J (2004) Automated detection of diabetic retinopathy in digital retinal images: a tool for diabetic retinopathy screening. Diabet Med 21:84–90
Gulshan V, Peng L, Coram M et al (2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316:2402–2410
Bellermo V, Lim ZW, Lim G et al (2019) Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study. Lancet Digit Health 1:e35–e44
Ting DSW, Cheung CY-L, Lim G et al (2017) Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 318:2211–2223
Burlina PM, Joshi N, Pekala M, Pacheco KD, Freund DE, Bressler NM (2017) Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol 135:1170–1176
Brown JM, Campbell JP, Beers A et al (2018) Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. JAMA Ophthalmol 136:803–810
Hu Y, Xiao Y, Quan W et al (2021) A multi-center study of prediction of macular hole status after vitrectomy and internal limiting membrane peeling by a deep learning model. Ann Transl Med 9:51
Chattopadhay A, Sarkar A, Howlader P, Balasubramanian VN. Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. Paper presented at: 2018 Institute of Electrical and Electronics Engineers Winter Conference on Applications of Computer Vision; March 12–15, 2018; Lake Tahoe, NV
Draelos RL, Carin L. Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks. arXiv:2011.08891 [Pre-print]. November 21, 2021 [cited 2022 Apr 11] https://doi.org/10.48550/arXiv.2011.08891
Kornberg DL, Klufas MA, Yannuzzi NA, Orlin A, D’Amico DJ, Kiss S (2016) Clinical utility of ultra-widefield imaging with the optos optomap compared with indirect ophthalmoscopy in the setting of non-traumatic rhegmatogenous retinal detachment. Semin Ophthalmol 31:505–512
Khandhadia S, Madhusudhana KC, Kostakou A, Forrester JV, Newsom RSB (2009) Use of optomap for retinal screening within an eye casualty setting. Br J Ophthalmol 93:52–55
Acknowledgements
Members of the BEAVRS Retinal Detachment Outcomes Group: A.G. Casswell, Andrew H.C. Morris, Assad Jalil, Atiq R. Babar, Craig Goldsmith, David H.W. Steel, Diego Sanchez-Chicharro, E.D. Hughes, E.N. Herbert, Huw Jenkins, Imran J. Khan, John D. Ellis, Jonathan Smith, Kamaljit S. Balaggan, Kurt Spiteri Cornish, Laura Wakeley, Mark Costen, Sonali Tarafdar, Stephen J. Charles, Stephen Winder, Timothy Cochrane, Tsveta Ivanova, Vasileios T. Papastavrou, Vaughan Tanner, David Yorston, D. Alistair Laidlaw, Tom H. Williamson
Author information
Authors and Affiliations
Consortia
Corresponding author
Ethics declarations
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fung, T.H.M., John, N.C.R.A., Guillemaut, JY. et al. Artificial intelligence using deep learning to predict the anatomical outcome of rhegmatogenous retinal detachment surgery: a pilot study. Graefes Arch Clin Exp Ophthalmol 261, 715–721 (2023). https://doi.org/10.1007/s00417-022-05884-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00417-022-05884-3