Deep Learning Innovations for Enhanced Drusen Detection in Retinal Images

doi:10.23940/ijpe.23.12.p2.779787

Abstract

Abstract: The aim of this study is to conduct an exploration of recent advancements in deep learning-based drusen detection, across a range of imaging modalities like fundus images, Optical Coherence Tomography (OCT), Fundus Autofluorescence (FAF), and Ultra-Widefield fundus (UWF) images. Drusen are yellow deposits of lipids and proteins beneath the retina and serve as a distinctive feature of age-related macular degeneration (AMD) [1]. Deep learning has revolutionized retinal image processing, particularly in drusen diagnosis. The techniques and methodologies reviewed in this paper range from refinement of established models such as VGG19 with enhanced transfer learning to innovative approaches like the seamless fusion of patch and image-level models. This survey goes beyond mere enumeration of techniques, instead focusing on a critical evaluation of their effectiveness and applicability on diverse datasets, including DRIVE, STARE, and AREDS. Furthermore, this study offers a comparative analysis of the papers reviewed, unveiling the unique contributions and intricacies of each approach while offering a comprehensive overview of the current state of the field, enhancing understanding of the complexities and potentials within drusen detection.

Key words: drusen detection, deep learning, convolutional neural networks (CNNs), age-related macular degeneration (AMD), fundus images

Pavneet Singh, Jigyasa Chopra, Amandeep Singh, Nikita Nijhawan, and Kritika. Deep Learning Innovations for Enhanced Drusen Detection in Retinal Images [J]. Int J Performability Eng, 2023, 19(12): 779-787.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] Jager R.D., Mieler W.F., andMiller J.W.Age-Related Macular Degeneration. New England Journal of Medicine, vol. 358, no. 24, pp. 2606-2617, 2008.
[2] Wong W.L., Su X., Li X., Cheung C.M.G., Klein R., Cheng C.Y., andWong, T.Y. Global Prevalence of Age-Related Macular Degeneration and Disease Burden Projection for2020 and 2040: A Systematic Review and Meta-Analysis. The Lancet Global Health, vol. 2, no. 2, pp. e106-e116, 2014.
[3] Hageman G.S., Gehrs K., Johnson L.V., andAnderson D.Age-Related Macular Degeneration (AMD).Webvision: The Organization of the Retina and Visual System [Internet], 2008.
[4] Holz F.G., Strauss E.C., Schmitz-Valckenberg, S., and van Lookeren Campagne, M. Geographic Atrophy: Clinical Features and Potential Therapeutic Approaches. Ophthalmology, vol. 121, no. 5, pp. 1079-1091, 2014.
[5] Lim L.S., Mitchell P., Seddon J.M., Holz F.G., andWong T.Y.Age-Related Macular Degeneration. The Lancet, vol. 379, no. 9827, pp. 1728-1738, 2012.
[6] Cohen S.Y., Dubois L., Tadayoni R., Delahaye-Mazza, C., Debibie, C., and Quentel, G. Prevalence of Reticular Pseudodrusen in Age-Related Macular Degeneration with Newly Diagnosed Choroidal Neovascularisation. British journal of ophthalmology, vol. 91, no. 3, pp. 354-359, 2007.
[7] Stahl A.The Diagnosis and Treatment of Age-Related Macular Degeneration. Deutsches Ärzteblatt International, vol.117, no. 29-30, pp. 513, 2020.
[8] Chaudhuri M., Hassan Y., Vemana P.P.S.B., Pattanashetty, M.S.B., Abdin, Z.U., Siddiqui, H.F., and CHAUDHURI, M. Age-Related Macular Degeneration: An Exponentially Emerging Imminent Threat of Visual Impairment and Irreversible Blindness. Cureus, vol. 15, no. 5, 2023.
[9] Gehrs K.M., Anderson D.H., Johnson L.V., andHageman G.S.Age‐Related Macular Degeneration—Emerging Pathogenetic and Therapeutic Concepts. Annals of medicine, vol. 38, no. 7, pp. 450-471, 2006.
[10] Algvere P.V., Kvanta A., andSeregard S.Drusen Maculopathy: A Risk Factor for Visual Deterioration. Acta ophthalmologica, vol. 94, no. 5, pp. 427-433, 2016.
[11] Kim, Y.J. and Kim, K.G.Automated Segmentation Methods of Drusen to Diagnose Age-Related Macular Degeneration Screening in Retinal Images. Computational and Mathematical Methods in Medicine, vol. 2018, 2018.
[12] Ferris III, F.L., Wilkinson, C.P., Bird, A., Chakravarthy, U., Chew, E., Csaky, K., Sadda, S.R., and Beckman Initiative for Macular Research Classification Committe. Clinical Classification of Age-Related Macular Degeneration. Ophthalmology, vol. 120, no. 4, pp. 844-851, 2013.
[13] Bakri S.J., Bektas M., Sharp D., Luo R., Sarda S.P., andKhan S.Geographic Atrophy: Mechanism of Disease, Pathophysiology, and Role of the Complement System. Journal of Managed Care & Specialty Pharmacy, vol.29, no. 5-a Suppl, pp. S2-S11, 2023.
[14] Ryan S.J., Schachat A.P., Wilkinson C.P., Hinton D.R., Sadda S.R., andWiedemann P.Retina: Expert Consult Premium Edition: Enhanced Online Features and Print, 5th edition, 2012.
[15] Zhao R., Camino A., Wang J., Hagag A.M., Lu Y., Bailey S.T., Flaxel C.J., Hwang T.S., Huang D., Li D., andJia Y.Automated Drusen Detection in Dry Age-Related Macular Degeneration by Multiple-Depth, En Face Optical Coherence Tomography. Biomedical optics express, vol. 8, no. 11, pp. 5049-5064, 2017.
[16] Khalid S., Akram M.U., Hassan T., Jameel A., andKhalil T.Automated Segmentation and Quantification of Drusen in Fundus and Optical Coherence Tomography Images for Detection of ARMD. Journal of digital imaging, vol. 31, pp. 464-476, 2018.
[17] Kim, Y.J. and Kim, K.G.AUtomated Segmentation Methods of Drusen to Diagnose Age-Related Macular Degeneration Screening in Retinal Images. Computational and Mathematical Methods in Medicine, vol. 2018, 2018.
[18] Ren X., Zheng Y., Zhao Y., Luo C., Wang H., Lian J., andHe Y.Drusen Segmentation from Retinal Images via Supervised Feature Learning. IEEE Access, vol. 6, pp. 2952-2961, 2017.
[19] Mohaimin S.M., Saha S.K., Khan A.M., Mohammad Arif, A.S., and Kanagasingam, Y. Automated Method for the Detection and Segmentation of Drusen in Colour Fundus Image for the Diagnosis of Age‐Related Macular Degeneration. IET Image Processing, vol. 12, no. 6, pp. 919-927, 2018.
[20] Schwartz R., Khalid H., Liakopoulos S., Ouyang Y., de Vente, C., González-Gonzalo, C., Lee, A.Y., Guymer, R., Chew, E.Y., Egan, C., and Wu, Z. A Deep Learning Framework for the Detection and Quantification of Reticular Pseudodrusen and Drusen on Optical Coherence Tomography. Translational Vision Science & Technology, vol. 11, no. 12, pp. 3-3, 2022.
[21] Ren X., Zheng X., Dong X., andCui X.Deep Feature Extraction via Adaptive Collaborative Learning for Drusen Segmentation from Fundus Images. Signal, Image and Video Processing, vol. 15, pp. 895-902, 2021.
[22] Li Z., Guo C., Nie D., Lin D., Cui T., Zhu Y., Chen C., Zhao L., Zhang X., Dongye M., andWang D.Automated Detection of Retinal Exudates and Drusen in Ultra-Widefield Fundus Images Based on Deep Learning. Eye, vol. 36, no. 8, pp. 1681-1686, 2022.
[23] Pham Q.T., Ahn S., Song S.J., andShin J.Automatic Drusen Segmentation for Age-Related Macular Degeneration in Fundus Images using Deep Learning. Electronics, vol. 9, no. 10, pp. 1617, 2020.
[24] Morelle O., Wintergerst M.W., Finger R.P., andSchultz T.Accurate Drusen Segmentation in Optical Coherence Tomography via Order-Constrained Regression of Retinal Layer Heights. Scientific Reports, vol. 13, no. 1, pp. 8162, 2023.
[25] Choudhary A., Ahlawat S., Urooj S., Pathak N., Lay-Ekuakille, A., and Sharma, N. A Deep Learning-Based Framework for Retinal Disease Classification. In Healthcare, MDPI, vol. 11, no. 2, pp. 212, 2023.
[26] Keenan T.D., Chen Q., Peng Y., Domalpally A., Agron E., Hwang C.K., Thavikulwat A.T., Lee D.H., Li D., Wong W.T., andLu Z.Deep Learning Automated Detection of Reticular Pseudodrusen from Fundus Autofluorescence Images or Color Fundus Photographs in AREDS2. Ophthalmology, vol. 127, no. 12, pp. 1674-1687, 2020.