Cross-camera Performance of Deep Learning Algorithms to Diagnose Common Ophthalmic Diseases: A Comparative Study Highlighting Feasibility to Portable Fundus Camera Use

References

• Grassmann F, Mengelkamp J, Brandl C, Harsch S, Zimmermann ME, Linkohr B, Peters A, Heid IM, Palm C, Weber BHF. A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography. Ophthalmology. 2018;125(9):1410–1420. doi:10.1016/j.ophtha.2018.02.037.
   PubMed Web of Science ®Google Scholar
• Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Cuadros J, et al. Development and validation of a deep learning algorithm for the detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402–2410. doi:10.1001/jama.2016.17216.
   PubMed Web of Science ®Google Scholar
• Phene S, Dunn RC, Hammel N, Liu Y, Krause J, Kitade N, Schaekermann M, Sayres R, Wu DJ, Bora A, et al. Deep learning and glaucoma specialists: the relative importance of optic disc features to predict glaucoma referral in fundus photographs. Ophthalmology. 2019;126(12):1627–1639. doi:10.1016/j.ophtha.2019.07.024.
   PubMed Web of Science ®Google Scholar
• Liu H, Li L, Wormstone IM, Qiao C, Zhang C, Liu P, Li S, Wang H, Mou D, Pang R, et al. Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs. JAMA Ophthalmol. 2019;137(12):1353–1360. doi:10.1001/jamaophthalmol.2019.3501.
   PubMed Web of Science ®Google Scholar
• Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol. 2019;103(2):167–175. doi:10.1136/bjophthalmol-2018-313173.
   PubMed Web of Science ®Google Scholar
• Li Z, He Y, Keel S, Meng W, Chang RT, He M. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology. 2018;125(8):1199–1206. doi:10.1016/j.ophtha.2018.01.023.
   PubMed Web of Science ®Google Scholar
• Keel S, Li Z, Scheetz J, Robman L, Phung J, Makeyeva G, Aung K, Liu C, Yan X, Meng W, et al. Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs. Clin Exp Ophthalmol. 2019;47(8):1009–1018. doi:10.1111/ceo.13575.
   PubMed Web of Science ®Google Scholar
• He T, Zhou Q, Zou Y. Automatic detection of age-related macular degeneration based on deep learning and local outlier factor algorithm. Diagnostics. 2022;12(2):532. doi:10.3390/diagnostics12020532.
   Web of Science ®Google Scholar
• Rim TH, Lee AY, Ting DS, Teo K, Betzler BK, Teo ZL, Yoo TK, Lee G, Kim Y, Lin AC, et al. Detection of features associated with neovascular age-related macular degeneration in ethnically distinct data sets by an optical coherence tomography: trained deep learning algorithm. Br J Ophthalmol. 2021;105(8):1133–1139. doi:10.1136/bjophthalmol-2020-316984.
   PubMed Web of Science ®Google Scholar
• Ibrahim MH, Hacibeyoglu M, Agaoglu A, Ucar F. Glaucoma disease diagnosis with an artificial algae-based deep learning algorithm. Med Biol Eng Comput. 2022;60(3):785–796. doi:10.1007/s11517-022-02510-6.
   PubMed Web of Science ®Google Scholar
• Jammal AA, Thompson AC, Mariottoni EB, Berchuck SI, Urata CN, Estrela T, Wakil SM, Costa VP, Medeiros FA. Human versus machine: comparing a deep learning algorithm to human gradings for detecting glaucoma on fundus photographs. Am J Ophthalmol. 2020;211:123–131. doi:10.1016/j.ajo.2019.11.006.
   PubMed Web of Science ®Google Scholar
• Abràmoff MD, Lou Y, Erginay A, Clarida W, Amelon R, Folk JC, Niemeijer M. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest Ophthalmol Vis Sci. 2016;57(13):5200–5206. doi:10.1167/iovs.16-19964.
   PubMed Web of Science ®Google Scholar
• Keel S, Wu J, Lee PY, Scheetz J, He M. Visualizing deep learning models for the detection of referable diabetic retinopathy and glaucoma. JAMA Ophthalmol. 2019;137(3):288–292. doi:10.1001/jamaophthalmol.2018.6035.
   PubMed Web of Science ®Google Scholar
• Panwar A, Semwal G, Goel S, Gupta S. Stratification of the lesions in color fundus images of diabetic retinopathy patients using deep learning models and machine learning classifiers In Patgiri R, Bandyopadhyay S, Borah MD, Emilia Balas V (Eds). Edge Analytics. Lecture Notes in Electrical Engineering, vol. 869. Springer, Singapore. 2022. doi:10.1007/978-981-19-0019-8_49.
   Google Scholar
• Wongchaisuwat N, Trinavarat A, Rodanant N, Thoongsuwan S, Phasukkijwatana N, Prakhunhungsit S, Preechasuk L, Wongchaisuwat P. In-Person verification of deep learning algorithm for diabetic retinopathy screening using different techniques across fundus image devices. Transl Vis Sci Technol. 2021;10(13):17. doi:10.1167/tvst.10.13.17.
   PubMed Web of Science ®Google Scholar
• He M, Li Z, Liu C, Shi D, Tan Z. Deployment of artificial intelligence in real-world practice: opportunity and challenge. Asia Pac J Ophthalmol. 2020;9(4):299–307. doi:10.1097/APO.0000000000000301.
   PubMed Web of Science ®Google Scholar
• Tsai M-J, Hsieh Y-T, Tsai C-H, Chen M, Hsieh A-T, Tsai C-W, Chen M-L. Cross-camera external validation for artificial intelligence software in diagnosis of diabetic retinopathy. J Diabetes Res. 2022;2022:5779276. doi:10.1155/2022/5779276.
   PubMed Web of Science ®Google Scholar
• Li Z, Keel S, Liu C, He Y, Meng W, Scheetz J, Lee PY, Shaw J, Ting D, Wong TY, et al. An automated grading system for detection of vision-threatening referable diabetic retinopathy on the basis of color fundus photographs. Diabetes Care. 2018;41(12):2509–2516. doi:10.2337/dc18-0147.
   PubMed Web of Science ®Google Scholar
• Wang Y, Shi D, Tan Z, Niu Y, Jiang Y, Xiong R, Peng G, He M. Screening referable diabetic retinopathy using a semi-automated deep learning algorithm assisted approach. Front Med. 2021;8:740987. doi:10.3389/fmed.2021.740987.
   Web of Science ®Google Scholar
• Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977;33(1):159–174. doi:10.2307/2529310.
   PubMed Web of Science ®Google Scholar
• Ting DSW, Peng L, Varadarajan AV, Keane PA, Burlina PM, Chiang MF, Schmetterer L, Pasquale LR, Bressler NM, Webster DR, et al. Deep learning in ophthalmology: the technical and clinical considerations. Prog Retin Eye Res. 2019;72:100759. doi:10.1016/j.preteyeres.2019.04.003.
   PubMed Web of Science ®Google Scholar
• Raumviboonsuk P, Krause J, Chotcomwongse P, Sayres R, Raman R, Widner K, Campana BJL, Phene S, Hemarat K, Tadarati M, et al. Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program. NPJ Digit Med. 2019;2:25. doi:10.1038/s41746-019-0099-8.
   PubMed Web of Science ®Google Scholar
• Tufail A, Rudisill C, Egan C, Kapetanakis VV, Salas-Vega S, Owen CG, Lee A, Louw V, Anderson J, Liew G, et al. Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost-effectiveness compared with human graders. Ophthalmology. 2017;124(3):343–351. doi:10.1016/j.ophtha.2016.11.014.
   PubMed Web of Science ®Google Scholar
• Abràmoff MD, Lavin PT, Birch M, Shah N, Folk JC. Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. NPJ Digit Med. 2018;1:39. doi:10.1038/s41746-018-0040-6.
   PubMed Web of Science ®Google Scholar
• Li T, Bo W, Hu C, Kang H, Liu H, Wang K, Fu H. Applications of deep learning in fundus images: a review. Med Image Anal [Internet]. 2021;69:101971. doi:10.1016/j.media.2021.101971.
   PubMed Web of Science ®Google Scholar
• Aurangzeb K, Aslam S, Alhussein M, Naqvi RA, Arsalan M, Haider SI. Contrast enhancement of fundus images by employing modified PSO for improving the performance of deep learning models. IEEE Access. 2021;9(99):47930–47945. doi:10.1109/ACCESS.2021.3068477.
   Web of Science ®Google Scholar
• Tky A, Ihrb C, Jin K, Isl B, Jsk B, Hong K, Jyc E. Deep learning can generate traditional retinal fundus photographs using ultra-widefield images via generative adversarial networks. Comput Methods Programs Biomed. 2020;197:105761. doi:10.1016/j.cmpb.2020.105761.
   PubMed Web of Science ®Google Scholar
• Tahghighi P, Zoroofi RA, Saffi S, Ramezani A. Heightmap reconstruction of macula on color fundus images using conditional generative adversarial networks. In 2021 26th International Computer Conference, Computer Society of Iran (CSICC) (pp. 1–6), Tehran, Iran. 2021, doi:10.48550/arXiv.2009.01601.
   Google Scholar
• Kamran SA, Hossain KF, Tavakkoli A, Zuckerbrod SL, Baker SA, Sanders KM. Fundus2Angio: a conditional GAN architecture for generating fluorescein angiography images from retinal fundus photography. Advances in Visual Computing. ISVC 2020. Lecture Notes in Computer Science, vol. 12510. Springer, Cham. 2020. doi:10.1007/978-3-030-64559-5_10.
   Google Scholar
• Yi X, Walia E, Babyn P. Generative adversarial network in medical imaging: a review. Med Image Anal. 2019;58:101552. doi:10.1016/j.media.2019.101552.
   PubMed Web of Science ®Google Scholar
• Zhong Z, Zheng L, Zheng Z, Li S, Yang Y. Camera style adaptation for person re-identification. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5157–5166), Salt Lake City, UT, USA. 2018. doi:10.1109/CVPR.2018.00541.
   Google Scholar
• Liu J, Liu H, Gong S, Tang Z, Xie Y, Yin H, Niyoyita JP. Automated cardiac segmentation of cross-modal medical images using unsupervised multi-domain adaptation and spatial neural attention structure. Med Image Anal. 2021;72:102135. doi:10.1016/j.media.2021.102135.
   PubMed Web of Science ®Google Scholar