WAMDS2: Early detection of wet AMD using Swin Transformer V2

Jorge Ernesto Gonzalez Diaz; Roberto Márquez Castro; José Luis  Sánchez Cervantes; Giner  Alor Hernández; Augusto Javier Reyes Delgado; Alfonso Flores Leal; Martin Mancilla Gomez

doi:10.17488/RMIB.46.SI-TAIH.1520

Autores/as

Jorge Ernesto Gonzalez Diaz Tecnologico Nacional de Mexico/Instituto Tecnologico de Orizaba https://orcid.org/0009-0001-2742-8600
Roberto Márquez Castro Tecnológico Nacional de México/I. T. Orizaba https://orcid.org/0009-0006-8327-5633
José Luis Sánchez Cervantes Tecnológico Nacional de México/I. T. Orizaba https://orcid.org/0000-0001-5194-1263
Giner Alor Hernández Tecnológico Nacional de México/I. T. Orizaba
Augusto Javier Reyes Delgado Tecnológico Nacional de México/I. T. Orizaba https://orcid.org/0009-0000-6863-3507
Alfonso Flores Leal Tecnológico Nacional de México/I. T. Orizaba
Martin Mancilla Gomez Facultad de Negocios y Tecnologías, Universidad Veracruzana https://orcid.org/0000-0001-5003-1620

DOI:

https://doi.org/10.17488/RMIB.46.SI-TAIH.1520

Palabras clave:

Degeneracion Macular Asociadala a la Edad, Transformador Swin, Transformador de Vision

Resumen

La degeneración macular asociada con la edad (DMAE) es una enfermedad ocular progresiva que afecta principalmente a personas mayores de 50 años. Entre sus variantes, la DMAE húmeda es la más grave, pues representa la evolución avanzada de la DMAE seca y puede causar una pérdida visual severa si no se detecta a tiempo. Este estudio se centra en el desarrollo de WAMDS2, un módulo web diseñado para identificar características asociadas con la DMAE húmeda, lo que facilita una detección temprana y precisa. Para ello, se llevó a cabo una revisión de literatura sobre la DMAE y técnicas avanzadas de visión por computadora y aprendizaje profundo. El modelo propuesto integra el Swin Transformer V2, un transformador de visión implementado en PyTorch, para analizar imágenes de fondo de ojo y clasificar los diferentes estadios de la enfermedad. El rendimiento del sistema se evaluó mediante métricas como precisión, sensibilidad y F1-Score, logrando una precisión del 84.76% en el conjunto de prueba, lo que sugiere su viabilidad en entornos clínicos. Los resultados obtenidos resaltan el potencial de WAMDS2 en el ámbito de la oftalmología y la visión por computadora, evidenciando su capacidad para mejorar el diagnóstico automatizado y la atención al paciente.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

W. L. Wong et al., "Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis," The Lancet Global Health, vol. 2, no. 2, pp. e106–e116, Feb. 2014, doi: https://doi.org/10.1016/S2214-109X(13)70145-1

T. D. L. Keenan, C. A. Cukras, and E. Y. Chew, "Age-Related Macular Degeneration: Epidemiology and Clinical Aspects," in Age-Related Macular Degeneration, M. F. Marmor and T. J. Wolfensberger, Eds., Springer, 2021, pp. 1–31, doi: https://doi.org/10.1007/978-3-030-66014-7_1

V. R. Cimarolli et al., "Anxiety and depression in patients with advanced macular degeneration: current perspectives," Clinical Ophthalmology, vol. 10, pp. 55–63, Jan. 2016, doi: https://doi.org/10.2147/OPTH.S80489

J. Bonastre et al., "The epidemiology, economics and quality of life burden of age-related macular degeneration in France, Germany, Italy and the United Kingdom," The European Journal of Health Economics, vol. 3, no. 2, pp. 74–85, 2003, doi: https://doi.org/10.1007/s10198-002-0104-y

A. K. Klettner and S. Dithmar, Eds., Retinal Pigment Epithelium in Health and Disease. Cham: Springer, 2020, doi: https://doi.org/10.1007/978-3-030-28384-1

R. F. Spaide, “Choroidal Neovascularization,” Retina, vol. 37, no. 4, pp. 609–610, Apr. 2017, doi: https://doi.org/10.1097/IAE.0000000000001575

S. Jabbehdari et al., "Age-related macular degeneration and neurodegenerative disorders: Shared pathways in complex interactions," Survey of Ophthalmology, vol. 69, no. 3, pp. 303–310, 2024, doi: https://doi.org/10.1016/j.survophthal.2023.11.003

T. He, Q. Zhou, and Y. Zou, “Automatic detection of age-related macular degeneration based on deep learning and local outlier factor algorithm,” Diagnostics, vol. 12, no. 2, p. 532, 2022. doi: https://doi.org/10.3390/diagnostics12020532

A. Dosovitskiy et al., "An image is worth 16x16 words: Transformers for image recognition at scale," arXiv:2010.11929, 2020, doi: https://doi.org/10.48550/arXiv.2010.11929

K. He et al., "Transformers in medical image analysis," Intelligent Medicine, vol. 3, no. 1, pp. 59–78, 2023, doi: https://doi.org/10.1016/j.imed.2022.07.002

Z. Liu et al., "Swin Transformer V2: Scaling Up Capacity and Resolution," 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022, pp. 11999-12009, doi: https://doi.org/10.1109/CVPR52688.2022.01170

W. Wei, J. Southern, K. Zhu, Y. Li, M. F. Cordeiro, and K. Veselkov, "Deep learning to detect macular atrophy in wet age-related macular degeneration using optical coherence tomography," Sci. Rep., vol. 13, 2023, doi: https://doi.org/10.1038/s41598-023-35414-y

İ. Kayadibi and G. E. Güraksın, "An Explainable Fully Dense Fusion Neural Network with Deep Support Vector Machine for Retinal Disease Determination," International Journal of Computational Intelligence Systems, vol. 16, 2023, doi: https://doi.org/10.1007/s44196-023-00210-z

N. N. El-Den et al., "Scale-adaptive model for detection and grading of age-related macular degeneration from color retinal fundus images," Sci. Rep., vol. 13, 2023, doi: https://doi.org/10.1038/s41598-023-35197-2

P. Dutta, K. A. Sathi, M. A. Hossain, and M. A. A. Dewan, "Conv-ViT: A Convolution and Vision Transformer-Based Hybrid Feature Extraction Method for Retinal Disease Detection," J Imaging., vol. 9, 2023, doi: https://doi.org/10.3390/jimaging9070140

E. López-Varela, P. L. Vidal, N. O. Pascual, J. Novo, and M. Ortega, "Fully-Automatic 3D Intuitive Visualization of Age-Related Macular Degeneration Fluid Accumulations in OCT Cubes," J Digit Imaging., vol. 35, pp. 1271–1282, 2022, doi: https://doi.org/10.1007/s10278-022-00643-6

P. Corazza et al., "Predicting wet age-related macular degeneration (AMD) using DARC (detecting apoptosing retinal cells) AI (artificial intelligence) technology," Expert Rev Mol Diagn., vol. 21, pp. 109–118, 2021, doi: https://doi.org/10.1080/14737159.2020.1865806

E. Haihong, J. Ding, and L. Yuan, "SAE-wAMD: A Self-Attention Enhanced convolution neural network for fine-grained classification of wet Age-Related Macular Degeneration using OCT Images," in Proc. 2022 Int. Conf. Image Process., Comput. Vis. Mach. Learn. (ICICML), Xi’an, China, 2022, pp. 619–627, doi: https://doi.org/10.1109/ICICML57342.2022.10009714

W. Wang et al., "Learning Two-Stream CNN for Multi-Modal Age-Related Macular Degeneration Categorization," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 8, pp. 4111-4122, Aug. 2022, doi: https://doi.org/10.1109/JBHI.2022.3171523

M. M. Abdullahi, S. Chakraborty, P. Kaushik, and B. S. Sami, "Detection of Dry and Wet Age-Related Macular Degeneration Using Deep Learning," 2022, doi: https://doi.org/10.2991/aisr.k.220201.037

S. D. Gummadi and A. Ghosh, "Classification of Ocular Diseases: A Vision Transformer-Based Approach," in Innovations in Computational Intelligence and Computer Vision, Lecture Notes in Networks and Systems, vol. 680, Springer, Oct. 2023, pp. 325–337, doi: https://doi.org/10.1007/978-981-99-2602-2_25

W. Feng et al., "Automated segmentation of choroidal neovascularization on optical coherence tomography angiography images of neovascular age-related macular degeneration patients based on deep learning," J Big Data., vol. 10, 2023, doi: https://doi.org/10.1186/s40537-023-00757-w

A. Haq, A. Fariza, and N. Ramadijanti, "Automatic Detection of Retinal Diseases in Optical Coherence Tomography Images using Convolutional Neural Network," 2021 International Electronics Symposium (IES), Surabaya, Indonesia, 2021, pp. 343-348, doi: https://doi.org/10.1109/IES53407.2021.9594003

M. Wu et al., "Classification of dry and wet macular degeneration based on the ConvNeXT model," Frontiers in Computational Neuroscience, vol. 16, Art. no. 1079155, 2022, doi: https://doi.org/10.3389/fncom.2022.1079155

J. Yim, R. Chopra, T. Spitz, et al., "Predicting conversion to wet age-related macular degeneration using deep learning," Nature Medicine, vol. 26, no. 6, pp. 892–899, 2020, doi: https://doi.org/10.1038/s41591-020-0867-7

A. Serener and S. Serte, "Dry and Wet Age-Related Macular Degeneration Classification Using OCT Images and Deep Learning," 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), Istanbul, Turkey, 2019, pp. 1-4, doi: https://doi.org/10.1109/EBBT.2019.8741768

S. Alayón, J. Hernández, J. F. Fumero, F. J. Sigut, and T. Díaz-Alemán, "Comparison of the performance of convolutional neural networks and vision transformer-based systems for automated glaucoma detection with eye fundus images," Appl. Sci., vol. 13, no. 23, p. 12722, 2023, doi: https://doi.org/10.3390/app132312722

J. He, J. Wang, Z. Han, J. Ma, C. Wang, and M. Qi, "An interpretable transformer network for retinal disease classification using optical coherence tomography," Sci. Rep., vol. 13, no. 1, 2023, doi: https://doi.org/10.1038/s41598-023-30853-z

M. Wassel, A. M. Hamdi, N. Adly, and M. Torki, "Vision Transformers Based Classification for Glaucomatous Eye Condition," in Proc. 2022 26th Int. Conf. Pattern Recognit. (ICPR), Montreal, QC, Canada, 2022, pp. 5082–5088, doi: https://doi.org/10.1109/ICPR56361.2022.9956086

J. E. Gonzalez Diaz et al., "Early detection of age-related macular degeneration using Vision Transformer-based Architectures – A comparative study with offline metrics and data augmenting," International Journal of Combinatorial Optimization Problems and Informatics, vol. 15, no. 4, pp. 72–84, Nov. 2024, doi: https://doi.org/10.61467/2007.1558.2024.v15i4.522

C. Shorten and T. M. Khoshgoftaar, "A survey on Image Data Augmentation for Deep Learning," J Big Data, vol. 6, no. 1, p. 60, Dec. 2019, doi: https://doi.org/10.1186/s40537-019-0197-0

Z. Liu et al., "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows," 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 2021, pp. 9992-10002, doi: https://doi.org/10.1109/ICCV48922.2021.00986

Z. Li, Y. Han, and X. Yang, "Multi-Fundus Diseases Classification Using Retinal Optical Coherence Tomography Images with Swin Transformer V2," Journal of Imaging, vol. 9, no. 10, p. 203, Sep. 2023, doi: https://doi.org/10.3390/JIMAGING9100203

CONDE DE VALENCIANA – Instituto de Oftalmología FAP, “Instituto de Oftalmología FAP,” 2025. Accessed: Feb. 7, 2025. [Online]. Available: http://www.institutodeoftalmologia.org

Fundación Oftalmológica, “Fundación Oftalmológica,” Com.mx, 2025. Accessed: Feb. 15, 2025. [Online]. Available: https://fundacionzurita.com.mx/

Baidu, “iChallenge-AMD Dataset,” AI Studio, 2023. Accessed: Aug. 31, 2023. [Online]. Available: https://aistudio.baidu.com/dataset/detail/88462/file

Rakhshanda Mujib, "ARMD curated dataset 2023," Kaggle. Accessed: Aug. 31, 2023. [Online]. Available: https://www.kaggle.com/datasets/rakhshandamujib/armd-curated-dataset-2023

Bleps Vision, "DiFO Adapter," Bleps Vision, 2024. Accessed: Feb. 7, 2025. [Online]. Available: https://blepsvision.com/difo/

C. Gonzalez-Gonzalez, B. Tysinger, D. P. Goldman, and R. Wong, "Projecting diabetes prevalence among Mexicans aged 50 years and older: the Future Elderly Model-Mexico (FEM-Mexico)," BMJ Open, vol. 7, no. 10, p. e017330, Oct. 2017, doi: https://doi.org/10.1136/bmjopen-2017-017330