A dark and bright channel prior guided deep network for retinal image quality assessment

• Autorzy: Xu Ziwen , Zou Beiji , Liu Qing

Identyfikatory

DOI

10.1016/j.bbe.2022.06.002

• Języki publikacji: EN

Abstrakty

EN

Background and objective: Retinal image quality assessment is an essential task for the diagnosis of retinal diseases. Recently, there are emerging deep models to grade quality of retinal images. However, current models either directly transfer classification networks originally designed for natural images to quality classification of retinal images or introduce extra image quality priors via multiple CNN branches or independent CNNs. The purpose of this work is to address retinal image quality assessment by a simple deep model. Methods: We propose a dark and bright channel prior guided deep network for retinal image quality assessment named GuidedNet. It introduces dark and bright channel priors into deep network without extra parameters increasing and allows for training end-to-end. In detail, the dark and bright channel priors are embedded into the start layer of a deep network to improve the discriminate ability of deep features. Moreover, we re-annotate a new retinal image quality dataset called RIQA-RFMiD for further validation. Results: The proposed method is evaluated on a public retinal image quality dataset Eye-Quality and our re-annotated dataset RIQA-RFMiD. We obtain the average F-score of 88.03% on Eye-Quality and 66.13% on RIQA-RFMiD, respectively. Conclusions: We investigate the utility of the dark and bright channel priors for retinal image quality assessment. And we propose a GuidedNet by embedding the dark and bright channel priors into CNNs without much model burden. Moreover, to valid the GuidedNet, we re-create a new dataset RIQA-RFMiD. With the GuidedNet, we achieves state-of-the-art performances on a public dataset Eye-Quality and our re-annotated dataset RIQA-RFMiD.

Słowa kluczowe

EN

retinal image; quality assessment; deep network; dark channel prior; bright channel prior

PL

obraz siatkówki oka; ocena jakości; sieć głęboka

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 3
• Strony: 772--783
• Opis fizyczny: Bibliogr. 45 poz., rys., tab., wykr.

Twórcy

autor

Xu Ziwen

• School of Computer Science and Engineering, Central South University, Changsha, China

autor

Zou Beiji

• School of Computer Science and Engineering, Central South University, Changsha, China
• Hunan Province Engineering Technology Research Center of Computer Vision and Intelligent Medical Treatment, Changsha, China

autor

Liu Qing

• School of Computer Science and Engineering, Central South University, Changsha, China

Bibliografia

• [1] Sahlsten J, Jaskari J, Kivinen J, et al. Deep learning fundus image analysis for diabetic retinopathy and macular edema grading. Sci Rep 2019;9(1):1–11.
• [2] Kausu TR, Gopi VP, Wahid KA, et al. Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images. Biocybern Biomed Eng 2018;38(2):329–41.
• [3] Li XM, Hu X, Qi XJ, et al. Rotation-oriented collaborative self-supervised learning for retinal disease diagnosis. IEEE Trans Med Imaging 2021;40(9):2284–94.
• [4] Quellec G, Lamard M, Conze PH, Massin P, Cochener B. Automatic detection of rare pathologies in fundus photographs using few-shot learning. Med Image Anal 2020;61(13) 101660.
• [5] Murugan R, Roy P. Micronet: microaneurysm detection in retinal fundus images using convolutional neural network. Soft Comput 2022;26(3):1057–66.
• [6] Nergiz M, Akín M, Yíldíz A, et al. Automated fuzzy optic disc detection algorithm using branching of vessels and color properties in fundus images. Biocybern Biomed Eng 2018;38(4):850–67.
• [7] Andreini P, Ciano G, Bonechi S, et al. A Two-Stage GAN for High-Resolution Retinal Image Generation and Segmentation. Electronics 2021;11(1):60.
• [8] Sambyal N, Saini P, Syal R, Gupta V. Modified u-net architecture for semantic segmentation of diabetic retinopathy images. Biocybern Biomed Eng 2020;40(3):1094–109.
• [9] Toledo-Cortés S, Useche DH, Müller H, González F.A. Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression. Computers in Biology and Medicine 2022;145:105472.
• [10] Zhang GH, Sun B, Chen ZX, et al. Diabetic Retinopathy Grading by Deep Graph Correlation Network on Retinal Images Without Manual Annotations. Front Med 2022;9872214.
• [11] Niu Y, Gu L, Zhao Y, et al. Explainable Diabetic Retinopathy Detection and Retinal Image Generation. IEEE J Biomed Health Informatics 2021;26(1):44–55.
• [12] Hervella Á Rouco J, Novo J, et al. Multimodal image encoding pre-training for diabetic retinopathy grading. Computers in Biology and Medicine 2022;143:105302.
• [13] Zhu S, Lu B, Wang C, et al. Screening of common retinal diseases using six-category models based on EfficientNet.Front Med 2022;9 808402.
• [14] Badawi SA, Fraz MM, Shehzad M, et al. Detection and Grading of Hypertensive Retinopathy Using Vessels Tortuosity and Arteriovenous Ratio. J Digit Imaging 2022;35:281–301.
• [15] Wan C, Zhou X, You Q, et al. Retinal Image Enhancement Using Cycle-Constraint Adversarial Network[J]. Front Med 2021;8 793726.
• [16] Palanisamy G, Shankar NB, Ponnusamy P, et al. A hybrid feature preservation technique based on luminosity and edge based contrast enhancement in color fundus images. Biocybern Biomed Eng 2020;40(2):752–63.
• [17] Mittal A, Moorthy AK, Bovik AC. No-reference image quality assessment in the spatial domain. IEEE Trans Image Processing 2012;21(12):4695–708.
• [18] Ou FZ, Wang YG. Zhu G.A novel blind image quality assessment method based on refined natural scene statistics. In: IEEE International Conference on Image Processing. p. 1004–8.
• [19] Yan Q, Gong D, Zhang Y. Two-stream convolutional networks for blind image quality assessment. IEEE Trans Image Process 2018;28(5):2200–11.
• [20] Zago GT, Andreão RV, Dorizzi B, Salles EOT. Retinal image quality assessment using deep learning. Comput Biol Med 2018;103:64–70.
• [21] Yu F, Sun J, Li A, Cheng J, Wan C, Liu J. Image quality classification for dr screening using deep learning. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). p. 664–7.
• [22] Moorthy AK, Bovik AC. Blind image quality assessment: From natural scene statistics to perceptual quality. IEEE Trans Image Process 2011;20(12):3350–64.
• [23] Fu HZ, Wang B, Shen JB, Cui SS, Xu YW, Liu J, Shao L. Evaluation of retinal image quality assessment networks in different color-spaces. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. p. 48–56.
• [24] Muddamsetty SM, Moeslund TB. Multi-level quality assessment of retinal fundus images using deep convolution neural networks. In: International Joint Conference on Computer Vision Theory and Applications. p. 661–8.
• [25] Shen YX, Fang RG, Sheng B, Dai L, Li HT, Qin J, Wu Q, Jia WP. Multi-task fundus image quality assessment via transfer learning and landmarks detection. In: International Workshop on Machine Learning in Medical Imaging. p. 28–36.
• [26] He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition 2016:770–8.
• [27] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representation.
• [28] Shen YX, Sheng B, Fang RG, et al. Domain-invariant interpretable fundus image quality assessment. Med Image Anal 2020;61 101654.
• [29] He KM, Sun J, Tang XO. Single image haze removal using dark channel prior. IEEE Trans Pattern Analysis Mach Intell 2010;33(12):2341–53.
• [30] Pan JS, Sun DQ, Pfister H, Yang MH. Blind image deblurring using dark channel prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 1628–36.
• [31] Ge XY, Tan JP, Zhang L. Blind image deblurring using a nonlinear channel prior based on dark and bright channels. IEEE Trans Image Process 2021;30:6970–84.
• [32] Cai JR, Zuo WM, Zhang L. Dark and bright channel prior embedded network for dynamic scene deblurring. IEEE Trans Image Process 2020;29:6885–97.
• [33] Panagopoulos A, Wang CH, Samaras D, Paragios N. Estimating shadows with the bright channel cue. European Conference on Computer Vision 2010;6554:1–12.
• [34] Wang YT, Zhuo SJ, Tao DP, et al. Automatic local exposure correction using bright channel prior for under-exposed images. Signal Processing 2013;93(11):3227–38.
• [35] Li T, Zhu C, Song JW, et al. Low-light image enhancement using cnn and bright channel prior. In: IEEE International Conference on Image Processing. p. 3215–9.
• [36] Huang G, Liu Z, Der Maaten LV, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition 2017:4700–8.
• [37] Howard AG, Zhu ML, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
• [38] Pachade S, Porwal P, Thulkar D, et al. Retinal fundus multi-disease image dataset (rfmid): a dataset for multi-disease detection research. Data 2021;(6)2:14.
• [39] Deng J, Dong W, Socher R, et al. Imagenet: A large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition 2009:248–55.
• [40] He KM, Zhang XY, Ren SQ, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision 2015:1026–34.
• [41] Wang SZ, Jin K, Lu HT, et al. Human visual system-based fundus image quality assessment of portable fundus camera photographs. IEEE Trans Med Imaging 2015;35(4):1046–55.
• [42] Raj A, Shah NA, Tiwari AK, Martini MG. Multivariate regression-based convolutional neural network model for fundus image quality assessment. IEEE Access 2020;8:57810–21.
• [43] Abdel-Hamid L. Retinal image quality assessment using transfer learning: Spatial images vs. wavelet detail subbands. Ain Shams Eng J 2021;12(3):2799–807.
• [44] Selvaraju RR, Cogswell M, Das A, et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision 2017:618–26.
• [45] Antony M, Bru¨ ggemann S. Team o_O solution for the kaggle diabetic retinopathy detection challenge 2016. https://www.kaggle.com/c/diabetic-retinopathy-detection/discussion/15807.