[1] [1] RUBIDO J, CARRACEDO G, SUZAKI A, et al. Keratoconus: an updated review[J]. Contact Lens and Anterior Eye, 2022, 45(3): 101559.

[2] [2] SHARIF R, BAK-NIELSEN S, HJORTDAL J, et al. Pathogenesis of keratoconus: the intriguing therapeutic potential of prolactin-inducible protein[J]. Progress in Retinal and Eye Research, 2018, 67:150-167.

[4] [4] ATALAY E, ZALP O, YILDIRIM N. Advances in the diagnosis and treatment of keratoconus[J]. Therapeutic Advances in Ophthalmology, 2021, 13: 25158414211012796.

[5] [5] VINCIGUERRA R, AMBRSIO JR R, ROBERTS C J, et al. Biomechanical characterization of subclinical keratoconus without topographic or tomographic abnormalities[J]. Journal of Refractive Surgery, 2017, 33(6): 399-407.

[10] [10] LAVRIC A, POPA V, TAKAHASHI H, et al. Detecting keratoconus from corneal imaging data using machine learning[J]. IEEE Access, 2020, 8:149113-149121.

[12] [12] KIM D, HAN B. On the stability-plasticity dilemma of class-incremental learning[C] //IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-22, 2023, Vancouver, Canada. New York: IEEE, 2023: 20196-20204.

[13] [13] POLIKAR R, UPDA L, UPDA S S, et al. Learn++: an incremental learning algorithm for supervised neural networks[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 2001, 31(4): 497-508.

[14] [14] HAMOOD-UR-REHMAN, ALI B, JAVED M. Data incremental learning for fault detection and classification in photovoltaic arrays[C]//2021 IEEE 13th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (SDEMPED), August 22-25, 2021, Dallas, TX, USA. New York: IEEE, 2021: 310-315.

[15] [15] SONY S A, ZAMAN T, ISLAM M K, et al. eLearn++: An effective incremental learning approach for brain tumor detection[C]//2021 2nd International Conference for Emerging Technology(INCET), May 21-23, 2021, Belagavi, India. New York: IEEE, 2021:1-8.

[18] [18] WANG L, WU C. Dynamic imbalanced business credit evaluation based on Learn++ with sliding time window and weight sampling and FCM with multiple kernels[J]. Information Sciences, 2020, 520: 305-323.