Abstract
Age-related macular degeneration (AMD) is an illness involving the degeneration of the macula of the retina. Fundus photography is the most affordable and convenient way to monitor individuals, in which AMD symptoms segmentation is necessary to assist clinical diagnosis. This study conducted a large number of experimental discussions on the annotation quality and symptoms categories to find a reliable learning strategy, and then applied it to early detection of AMD. Specifically, we discuss the inference of the representational power of the deep neural network, loss function selection, the preprocessing scheme of annotation augmentation, and the annotation quality of the dataset on prediction performance. This paper verified that different learning strategies need to be selected for the AMD symptoms segmentation tasks with varying characteristics of database, which can be used as a reference for developing the related research in the future. On the other hand, we demonstrated that current medical datasets suffer from annotation quality uncertainty, leading to limited learning capabilities. In the future, it is necessary to develop methods to overcome the impact of datasets with poor annotation quality.
Similar content being viewed by others
References
Jager RD, Mieler WF, Miller JW (2008) Age-related macular degeneration. N Engl J Med 358:2606–2617
Fine SL, Berger JW, Maguire MG, Ho AC (2000) Age-related macular degeneration. N Engl J Med 342:483–492
Bressler NM, Bressler SB, Fine SL (1988) Age-related macular degeneration. Surv Ophthalmol 32:375–413
Walter T, Massin P, Erginay A et al (2007) Automatic detection of microaneurysms in color fundus images. Med Image Anal 11:555–566
Quellec G, Charrière K, Boudi Y et al (2017) Deep image mining for diabetic retinopathy screening. Med Image Anal 39:178–193
Fleming AD, Philip S, Goatman KA et al (2007) Automated detection of exudates for diabetic retinopathy screening. Phys Med Biol 52:7385
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. pp. 234–241
Tajbakhsh N, Jeyaseelan L, Li Q et al (2020) Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation. Med Image Anal 63:101693
Karimi D, Dou H, Warfield SK, Gholipour A (2020) Deep learning with noisy labels: exploring techniques and remedies in medical image analysis. Med Image Anal 65:101759
Heller N, Dean J, Papanikolopoulos N (2018) Imperfect segmentation labels: how much do they matter? In: Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Springer, pp. 112–120
Zhang X, Thibault G, Decencière E et al (2014) Exudate detection in color retinal images for mass screening of diabetic retinopathy. Med Image Anal 18:1026–1043
Joshi S, Karule PT (2020) Mathematical morphology for microaneurysm detection in fundus images. Eur J Ophthalmol 30:1135–1142
Cárdenas JM, Martinez-Perez ME, March F, Hevia-Montiel N (2013) Mean shift based automatic detection of exudates in retinal images. In: Image Processing and Communications Challenges 4. Springer, pp 73–82
Marino C, Ares E, Penedo MG et al (2008) Automated three stage red lesions detection in digital color fundus images. WSEAS Trans Comput 7:207–215
Sopharak A, Uyyanonvara B, Barman S (2009) Automatic exudate detection from non-dilated diabetic retinopathy retinal images using fuzzy c-means clustering. Sensors 9:2148–2161
Yazid H, Arof H, Isa HM (2012) Automated identification of exudates and optic disc based on inverse surface thresholding. J Med Syst 36:1997–2004
Yan Z, Han X, Wang C, et al (2019) Learning mutually local-global U-Nets for high-resolution retinal lesion segmentation in fundus images. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). pp 597–600
Badar M, Shahzad M, Fraz MM (2018) Simultaneous segmentation of multiple retinal pathologies using fully convolutional deep neural network. In: Annual Conference on Medical Image Understanding and Analysis. pp. 313–324
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3431–3440
Chen L-C, Papandreou G, Kokkinos I, et al (2014) Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv Prepr arXiv14127062
Chen L-C, Papandreou G, Kokkinos I et al (2017) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40:834–848
Chen L-C, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv Prepr arXiv170605587
Chen L-C, Zhu Y, Papandreou G, et al (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV). pp 801–818
Zabihollahy F, Lochbihler A, Ukwatta E (2019) Deep learning based approach for fully automated detection and segmentation of hard exudate from retinal images. In: Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging. p 1095308
Kou C, Li W, Liang W et al (2019) Microaneurysms segmentation with a U-net based on recurrent residual convolutional neural network. J Med Imaging 6:25008
Li D, Dharmawan DA, Ng BP, Rahardja S (2019) Residual u-net for retinal vessel segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP). pp 1425–1429
Yu W, Fang B, Liu Y, et al (2019) Liver vessels segmentation based on 3d residual U-NET. In: 2019 IEEE International Conference on Image Processing (ICIP). pp 250–254
Khanna A, Londhe ND, Gupta S, Semwal A (2020) A deep residual U-net convolutional neural network for automated lung segmentation in computed tomography images. Biocybern Biomed Eng 40:1314–1327
Kerfoot E, Clough J, Oksuz I, et al (2018) Left-ventricle quantification using residual U-Net. In: International Workshop on Statistical Atlases and Computational Models of the Heart. pp. 371–380
Francia GA, Pedraza C, Aceves M, Tovar-Arriaga S (2020) Chaining a U-net with a residual U-net for retinal blood vessels segmentation. IEEE Access 8:38493–38500
Zhang J, Lv X, Zhang H, Liu B (2020) AResU-net: attention residual U-net for brain tumor segmentation. Symmetry (Basel) 12:721
Shen W, Xu W, Zhang H et al (2020) Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net. Inverse Probl Imaging 15:1333
Guo S, Li T, Kang H et al (2019) L-Seg: an end-to-end unified framework for multi-lesion segmentation of fundus images. Neurocomputing 349:52–63
Peng Y, Dharssi S, Chen Q et al (2019) DeepSeeNet: a deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs. Ophthalmology 126:565–575
Yan F, Cui J, Wang Y, et al (2018) Deep random walk for drusen segmentation from fundus images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 48–55
Bertasius G, Torresani L, Yu SX, Shi J (2017) Convolutional random walk networks for semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 858–866
Pham Q, Ahn S, Song SJ, Shin J (2020) Automatic Drusen segmentation for age-related macular degeneration in fundus images using deep learning. Electronics 9:1617
Spanhol FA, Oliveira LS, Petitjean C, Heutte L (2016) Breast cancer histopathological image classification using convolutional neural networks. In: 2016 international joint conference on neural networks (IJCNN). pp 2560–2567
Grassmann F, Mengelkamp J, Brandl C et al (2018) A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography. Ophthalmology 125:1410–1420
Hu K, Zhang Z, Niu X et al (2018) Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function. Neurocomputing 309:179–191
Lin T-Y, Goyal P, Girshick R, et al (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. pp. 2980–2988
Zong Y, Chen J, Yang L et al (2020) U-net based method for automatic hard exudates segmentation in fundus images using inception module and residual connection. IEEE Access 8:167225–167235
Kats E, Goldberger J, Greenspan H (2019) Soft labeling by distilling anatomical knowledge for improved ms lesion segmentation. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). pp 1563–1566
Fu H, Li F, Orlando JI, Bogunović H, Sun X, Liao J, Xu Y, Zhang S, Zhang X January(2020) Adam: automatic detection challenge on age-related macular degeneration. IEEE Data Port. https://doi.org/10.21227/dt4f-rt59 Accessed 28 March 2021
Porwal P, Pachade S, Kamble R, Kokare M, Deshmukh G, Sahasrabuddhe V, Meriaudeau F (2019) Indian diabetic retinopathy image dataset (IDRID). IEEE Data Port https://doi.org/10.21227/H25W98. Accessed 28 March 2021
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770–778
Author information
Authors and Affiliations
Corresponding author
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
Hsu, CC., Lee, CY., Lin, CJ. et al. A comprehensive study of age-related macular degeneration detection. Multimed Tools Appl 81, 11897–11916 (2022). https://doi.org/10.1007/s11042-021-11896-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11896-8