Fundus tessellation segmentation and quantization based on the deep convolution neural network_Chinese Journal of Ocular Fundus Diseases

Authors：

Guo Zhen ¹ , Chen Lingzhi ² , Wang Lilong ² , Lyu Chuanfeng ² , Xie Guotong ² , Gao Yan ¹ ,  Li Jun ¹

1. Qingdao Eye Hospital of Shandong Firs t Medical University, Shandong Eye Institute, State Key Laboratory Cultivation Base, Shandong Provincial Key Laboratory of Ophthalmology, Qingdao 266071, China;
2. Ping An Healthcare Technology, Beijing 100010, China;

Corresponding author：

Li Jun, Email: doctor_li@126.com

Keywords：

Myopia; Neural networks (computer); Color fundus image; Tessellation density

DOI：

10.3760/cma.j.cn511434-20220110-00021

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To propose automatic measurement of global and local tessellation density on color fundus images based on a deep convolutional neural network (DCNN) method. Methods An applied study. An artificial intelligence (AI) database was constructed, which contained 1 005 color fundus images captured from 1 024 eyes of 514 myopic patients in the Northern Hospital of Qingdao Eye Hospital from May to July, 2021. The images were preprocessed by using RGB color channel re-calibration method (CCR algorithm), CLAHE algorithm based on Lab color space, Retinex algorithm for multiple iterative illumination estimation, and multi-scale Retinex algorithm. The effects on the segmentation of tessellation by adopting the abovemetioned image enhancement methods and utilizing the Dice, Edge Overlap Rate and clDice loss were compared and observed. The tessellation segmentation model for extracting the tessellated region in the full fundus image as well as the tissue detection model for locating the optic disc and macular fovea were built up. Then, the fundus tessellation density (FTD), macular tessellation density (MTD) and peripapillary tessellation density (PTD) were calculated automatically. Results When applying CCR algorithm for image preprocessing and the training losses combination strategy, the Dice coefficient, accuracy, sensitivity, specificity and Jordan index for fundus tessellation segmentation were 0.723 4, 94.25%, 74.03%, 96.00% and 70.03%, respectively. Compared with the manual annotations, the mean absolute errors and root mean square errors of FTD, MTD, PTD automatically measured by the model were 0.014 3, 0.020 7, 0.026 7 and 0.017 8, 0.032 3, 0.036 5, respectively. Conclusion The DCNN-based segmentation and detection method can automatically measure the tessellation density in the global and local regions of the fundus of myopia patients, which can more accurately assist clinical monitoring and evaluation of the impact of fundus tessellation changes on the development of myopia.

Citation： Guo Zhen, Chen Lingzhi, Wang Lilong, Lyu Chuanfeng, Xie Guotong, Gao Yan, Li Jun. Fundus tessellation segmentation and quantization based on the deep convolution neural network. Chinese Journal of Ocular Fundus Diseases, 2022, 38(2): 114-119. doi: 10.3760/cma.j.cn511434-20220110-00021 Copy

1.	Ohno-Matsui K, Kawasaki R, Jonas JB, et al. International photographic classification and grading system for myopic maculopathy[J]. Am J Ophthalmol, 2015, 159(5): 877-883. DOI: 10.1016/j.ajo.2015.01.022.
2.	Yan YN, Wang YX, Xu L, et al. Fundus tessellation: prevalence and associated factors: The Beijing Eye Study 2011[J]. Ophthalmology, 2015, 122(9): 1873-1880. DOI: 10.1016/j.ophtha.2015.05.031.
3.	Guo Y, Liu L, Zheng D, et al. Prevalence and associations of fundus tessellation among junior students from greater Beijing[J]. Invest Ophthalmol Vis Sci, 2019, 60(12): 4033-4040. DOI: 10.1167/iovs.19-27382.
4.	Yan YN, Wang YX, Yang Y, et al. Ten-year progression of myopic maculopathy: the Beijing Eye Study 2001-2011[J]. Ophthalmology, 2018, 125(8): 1253-1263. DOI: 10.1016/j.ophtha.2018.01.035.
5.	Yamashita T, Iwase A, Kii Y, et al. Location of ocular tessellations in Japanese: Population-Based Kumejima Study[J]. Invest Ophthalmol Vis Sci, 2018, 59(12): 4963-4967. DOI: 10.1167/iovs.18-25007.
6.	Tan TE, Anees A, Chen C, et al. Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study[J/OL]. Lancet Digit Health, 2021, 3(5): e317-e329[2021-06-09]. https://pubmed.ncbi.nlm.nih.gov/33890579/. DOI: 10.1016/S2589-7500(21)00055-8.
7.	Lu L, Ren P, Tang X, et al. AI-model for identifying pathologic myopia based on deep learning algorithms of myopic maculopathy classification and "plus" lesion detection in fundus images[J/OL]. Front Cell Dev Biol, 2021, 9: 719262[2021-10-15]. https://pubmed.ncbi.nlm.nih.gov/34722502/. DOI: 10.3389/fcell.2021.719262.
8.	Du R, Xie S, Fang Y, et al. Deep learning approach for automated detection of myopic maculopathy and pathologic myopia in fundus images[J]. Ophthalmol Retina, 2021, 5(12): 1235-1244. DOI: 10.1016/j.oret.2021.02.006.
9.	Shao L, Zhang QL, Long TF, et al. Quantitative assessment of fundus tessellated density and associated factors in fundus images using artificial intelligence[J]. Transl Vis Sci Technol, 2021, 10(9): 23. DOI: 10.1167/tvst.10.9.23.
10.	中国医药教育协会智能医学专委会智能眼科学组, 国家重点研发计划“眼科多模态成像及人工智能诊疗系统的研发和应用”项目组. 基于眼底照相的糖尿病视网膜病变人工智能筛查系统应用指南[J]. 中华实验眼科杂志, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.Intelligent Medicine Special Committee of China Medicine Education Association, National Key Research and Development Program of China "Development and Application of Ophthalmic Multimodal Imaging and Artificial Intelligence Diagnosis and Treatment System" Project Team. Guidelines for artificial intelligent diabetic retinopathy screening system based on fundus photography[J]. Chin J Exp Ophthalmol, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.
11.	Zhou M, Jin K, Wang S, et al. Color retinal image enhancement based on luminosity and contrast adjustment[J]. IEEE Trans Biomed Eng, 2018, 65(3): 521-527. DOI: 10.1109/TBME.2017.2700627.
12.	Funt B, Ciurea F, Mccann J. Retinex in MATLAB™[J]. J Electron Imaging, 2004, 13(1): 112-121. DOI: 10.1117/1.1636761.
13.	Petro AB, Sbert C, Morel JM. Multiscale Retinex[J]. Image Process on Lin, 2014, 4: 71-88. DOI: 10.5201/ipol.2014.107.
14.	Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Cham: Springer, 2015: 234-241.
15.	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C/OL]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016[2016-06-26]. https://www.computer.org/csdl.
16.	Milletari F, Navab N, Ahmadi S. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C/OL]//2016 Fourth International Conference on 3D Vision (3DV), Stanford, USA, 2016[2016-10-25]. http://arxiv.org/pdf/1606.04797.
17.	Guo Y, Wang R, Zhou X, et al. Lesion-aware segmentation network for atrophy and detachment of pathological myopia on fundus images[C]. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Calcutta, India, 2020.
18.	Shit S, Paetzold JC, Sekuboyina A, et al. clDice-a topology-preserving loss function for tubular structure segmentation[EB/OL]. (2022-01-10) [2020-03-16]. https://arxiv.org/abs/2003.07311.
19.	Lin TY, Dollar P, Girshick R, et al. Feature pyramid networks for object detection[C/OL]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, Honolulu, 2017[2017-04-10]. https://www.computer.org/csdl.
20.	Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs[J]. JAMA, 2016, 316(22): 2402-2410. DOI: 10.1001/jama.2016.17216.
21.	Burlina PM, Joshi N, Pekala M, et al. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks[J]. JAMA Ophthalmol, 2017, 135(11): 1170-1176. DOI: 10.1001/jamaophthalmol.2017.3782.
22.	Li Z, He Y, Keel S, et al. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs[J]. Ophthalmology, 2018, 125(8): 1199-1206. DOI: 10.1016/j.ophtha.2018.01.023.
23.	Tong Y, Lu W, Deng QQ, et al. Automated identification of retinopathy of prematurity by image-based deep learning[J]. Eye Vis (Lond), 2020, 7: 40. DOI: 10.1186/s40662-020-00206-2.
24.	Ting DSW, Peng L, Varadarajan AV, et al. Deep learning in ophthalmology: the technical and clinical considerations[J/OL]. Prog Retin Eye Res, 2019, 72: 100759[2019-04-29]. https://pubmed.ncbi.nlm.nih.gov/31048019/. DOI: 10.1016/j.preteyeres.2019.04.003.

1. Ohno-Matsui K, Kawasaki R, Jonas JB, et al. International photographic classification and grading system for myopic maculopathy[J]. Am J Ophthalmol, 2015, 159(5): 877-883. DOI: 10.1016/j.ajo.2015.01.022.
2. Yan YN, Wang YX, Xu L, et al. Fundus tessellation: prevalence and associated factors: The Beijing Eye Study 2011[J]. Ophthalmology, 2015, 122(9): 1873-1880. DOI: 10.1016/j.ophtha.2015.05.031.
3. Guo Y, Liu L, Zheng D, et al. Prevalence and associations of fundus tessellation among junior students from greater Beijing[J]. Invest Ophthalmol Vis Sci, 2019, 60(12): 4033-4040. DOI: 10.1167/iovs.19-27382.
4. Yan YN, Wang YX, Yang Y, et al. Ten-year progression of myopic maculopathy: the Beijing Eye Study 2001-2011[J]. Ophthalmology, 2018, 125(8): 1253-1263. DOI: 10.1016/j.ophtha.2018.01.035.
5. Yamashita T, Iwase A, Kii Y, et al. Location of ocular tessellations in Japanese: Population-Based Kumejima Study[J]. Invest Ophthalmol Vis Sci, 2018, 59(12): 4963-4967. DOI: 10.1167/iovs.18-25007.
6. Tan TE, Anees A, Chen C, et al. Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study[J/OL]. Lancet Digit Health, 2021, 3(5): e317-e329[2021-06-09]. https://pubmed.ncbi.nlm.nih.gov/33890579/. DOI: 10.1016/S2589-7500(21)00055-8.
7. Lu L, Ren P, Tang X, et al. AI-model for identifying pathologic myopia based on deep learning algorithms of myopic maculopathy classification and "plus" lesion detection in fundus images[J/OL]. Front Cell Dev Biol, 2021, 9: 719262[2021-10-15]. https://pubmed.ncbi.nlm.nih.gov/34722502/. DOI: 10.3389/fcell.2021.719262.
8. Du R, Xie S, Fang Y, et al. Deep learning approach for automated detection of myopic maculopathy and pathologic myopia in fundus images[J]. Ophthalmol Retina, 2021, 5(12): 1235-1244. DOI: 10.1016/j.oret.2021.02.006.
9. Shao L, Zhang QL, Long TF, et al. Quantitative assessment of fundus tessellated density and associated factors in fundus images using artificial intelligence[J]. Transl Vis Sci Technol, 2021, 10(9): 23. DOI: 10.1167/tvst.10.9.23.
10. 中国医药教育协会智能医学专委会智能眼科学组, 国家重点研发计划“眼科多模态成像及人工智能诊疗系统的研发和应用”项目组. 基于眼底照相的糖尿病视网膜病变人工智能筛查系统应用指南[J]. 中华实验眼科杂志, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.Intelligent Medicine Special Committee of China Medicine Education Association, National Key Research and Development Program of China "Development and Application of Ophthalmic Multimodal Imaging and Artificial Intelligence Diagnosis and Treatment System" Project Team. Guidelines for artificial intelligent diabetic retinopathy screening system based on fundus photography[J]. Chin J Exp Ophthalmol, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.
11. Zhou M, Jin K, Wang S, et al. Color retinal image enhancement based on luminosity and contrast adjustment[J]. IEEE Trans Biomed Eng, 2018, 65(3): 521-527. DOI: 10.1109/TBME.2017.2700627.
12. Funt B, Ciurea F, Mccann J. Retinex in MATLAB™[J]. J Electron Imaging, 2004, 13(1): 112-121. DOI: 10.1117/1.1636761.
13. Petro AB, Sbert C, Morel JM. Multiscale Retinex[J]. Image Process on Lin, 2014, 4: 71-88. DOI: 10.5201/ipol.2014.107.
14. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Cham: Springer, 2015: 234-241.
15. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C/OL]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016[2016-06-26]. https://www.computer.org/csdl.
16. Milletari F, Navab N, Ahmadi S. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C/OL]//2016 Fourth International Conference on 3D Vision (3DV), Stanford, USA, 2016[2016-10-25]. http://arxiv.org/pdf/1606.04797.
17. Guo Y, Wang R, Zhou X, et al. Lesion-aware segmentation network for atrophy and detachment of pathological myopia on fundus images[C]. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Calcutta, India, 2020.
18. Shit S, Paetzold JC, Sekuboyina A, et al. clDice-a topology-preserving loss function for tubular structure segmentation[EB/OL]. (2022-01-10) [2020-03-16]. https://arxiv.org/abs/2003.07311.
19. Lin TY, Dollar P, Girshick R, et al. Feature pyramid networks for object detection[C/OL]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, Honolulu, 2017[2017-04-10]. https://www.computer.org/csdl.
20. Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs[J]. JAMA, 2016, 316(22): 2402-2410. DOI: 10.1001/jama.2016.17216.
21. Burlina PM, Joshi N, Pekala M, et al. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks[J]. JAMA Ophthalmol, 2017, 135(11): 1170-1176. DOI: 10.1001/jamaophthalmol.2017.3782.
22. Li Z, He Y, Keel S, et al. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs[J]. Ophthalmology, 2018, 125(8): 1199-1206. DOI: 10.1016/j.ophtha.2018.01.023.
23. Tong Y, Lu W, Deng QQ, et al. Automated identification of retinopathy of prematurity by image-based deep learning[J]. Eye Vis (Lond), 2020, 7: 40. DOI: 10.1186/s40662-020-00206-2.
24. Ting DSW, Peng L, Varadarajan AV, et al. Deep learning in ophthalmology: the technical and clinical considerations[J/OL]. Prog Retin Eye Res, 2019, 72: 100759[2019-04-29]. https://pubmed.ncbi.nlm.nih.gov/31048019/. DOI: 10.1016/j.preteyeres.2019.04.003.

Chinese Journal of Ocular Fundus Diseases

Fundus tessellation segmentation and quantization based on the deep convolution neural network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content