Joint Optic Disc and Optic Cup Segmentation Based on Adversarial Learning and Guidance Mechanism

doi:10.19678/j.issn.1000-3428.0068734

Abstract

Abstract:

Accurate segmentation of the Optic Disc(OD) and Optic Cup(OC) effectively assists in diagnosing and monitoring glaucoma, thereby improving treatment outcomes. However, existing methods do not consider the differences between the various channels of fundus images, making it challenging to achieve accurate segmentation of the OC boundary. To address this problem, a network framework based on adversarial learning and a guidance mechanism, termed ALG-Net, is proposed to improve OD and OC segmentation performance. ALG-Net comprises two main components: a segmentation network and a discriminator. The segmentation network includes a Guidance Fusion Module(GFM) designed to merge single-channel feature information with RGB image features. This allows the network to learn the differences among the various channels of the fundus image, guiding the segmentation network to focus on key regions. The framework also incorporates a discriminator, which encourages the segmentation network to generate more realistic results through adversarial learning. Extensive experimental evaluations are conducted on the REFUGE and Drishti-GS datasets. The results show that ALG-Net achieved balanced accuracies of 98.6% and 95.9% for OD and OC segmentation, respectively, on the RUFUGE dataset and demonstrated better performance on the Drishti-GS dataset. In addition, applying ALG-Net's segmentation results to glaucoma classification tasks yielded an Area Under the ROC Curve(AUC) of 0.983 on the REFUGE dataset, surpassing the classic UNet algorithm by 0.015. This demonstrates ALG-Net's strong support for early diagnosis and monitoring of glaucoma.

Key words: glaucoma diagnosis, Optic Disc(OD) segmentation, Optic Cup(OC) segmentation, UNet model, attention mechanism, guidance mechanism, adversarial learning

摘要：

准确的视盘(OD)和视杯(OC)分割能够有效地辅助青光眼的诊断和监测, 从而进一步提高治疗效果。然而, 现有方法没有考虑到眼底图像不同通道之间的差异, 并且难以实现对OC边界的精确分割。针对这个问题, 提出一种基于对抗学习和引导机制的网络框架ALG-Net, 旨在提高OD和OC的分割性能。ALG-Net由分割网络和鉴别器两部分组成。在分割网络中, 构建引导融合模块(GFM), 该模块将单通道特征信息与RGB图像特征融合, 使网络充分学习眼底图像不同通道之间的差异信息, 引导分割网络聚焦于关键区域。ALG-Net网络框架还采用了鉴别器, 通过对抗学习的方式促进分割网络生成更真实的分割结果。在REFUGE和Drishti-GS数据集上进行广泛的实验评估, 实验结果表明, ALG-Net在RUFUGE数据集上OD和OC分割的平衡精度分别达到了98.6%和95.9%, 在Drishti-GS数据集上也表现出优异的性能。此外, ALG-Net的分割结果应用于青光眼分类任务, 在RUFUGE数据集上ROC曲线下面积(AUC)为0.983, 相较于经典UNet算法提高了0.015, 为青光眼的早期诊断和监测提供了有力的支持。

关键词: 青光眼诊断, 视盘分割, 视杯分割, UNet模型, 注意力机制, 引导机制, 对抗学习

MA Xiaoyue, CHEN Yuanyuan. Joint Optic Disc and Optic Cup Segmentation Based on Adversarial Learning and Guidance Mechanism[J]. Computer Engineering, 2024, 50(12): 59-69.

马晓月, 陈媛媛. 基于对抗学习和引导机制的视盘和视杯联合分割[J]. 计算机工程, 2024, 50(12): 59-69.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0068734

https://www.ecice06.com/EN/Y2024/V50/I12/59

Figures/Tables 14

Fig.1 The training process of ALG-Net

Fig.2 Segmentation network in ALG-Net

Fig.3 Structure of GFM and DFOM

Fig.4 Coordinate attention mechanism

Fig.5 Discriminator in ALG-Net

Fig.6 Dice loss curves of different algorithms on the Drishti-GS dataset

Fig.7 Visualization example of optic disc and optic cup segmentation

Fig.8 ROC curve and AUC value of glaucoma screening based on CDR

References 39

1	PACHADE S , PORWAL P , KOKARE M , et al. NENet: nested EfficientNet and adversarial learning for joint optic disc and cup segmentation. Medical Image Analysis, 2021, 74, 102253. doi: 10.1016/j.media.2021.102253
2	JIANG Y M , DUAN L X , CHENG J , et al. JointRCNN: a region-based convolutional neural network for optic disc and cup segmentation. IEEE Transactions on Bio-Medical Engineering, 2020, 67 (2): 335- 343. doi: 10.1109/TBME.2019.2913211
3	SHELHAMER E , LONG J , DARRELL T . Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39 (4): 640- 651. doi: 10.1109/TPAMI.2016.2572683
4	RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of MICCAI 2015. Berlin, Germany: Springer, 2015: 234-241.
5	ISSAC A , PARTHA SARATHI M , DUTTA M K . An adaptive threshold based image processing technique for improved glaucoma detection and classification. Computer Methods and Programs in Biomedicine, 2015, 122 (2): 229- 244. doi: 10.1016/j.cmpb.2015.08.002
6	ORLANDO J I , FU H Z , BARBOSA B J , et al. REFUGE challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Medical Image Analysis, 2020, 59, 101570. doi: 10.1016/j.media.2019.101570
7	SIVASWAMY J, KRISHNADAS S R, DATT J G, et al. Drishti-GS: retinal image dataset for Optic Nerve Head(ONH) segmentation[C]//Proceedings of the 11th International Symposium on Biomedical Imaging(ISBI). Washington D. C., USA: IEEE Press, 2014: 53-56.
8	EDUPUGANTI V G, CHAWLA A, KALE A. Automatic optic disk and cup segmentation of fundus images using deep learning[C]//Proceedings of the 25th IEEE International Conference on Image Processing. Washington D. C., USA: IEEE Press, 2018: 2227-2231.
9	SHANKARANARAYANA S M , RAM K , MITRA K , et al. Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation. IEEE Journal of Biomedical and Health Informatics, 2019, 23 (4): 1417- 1426. doi: 10.1109/JBHI.2019.2899403
10	FU H Z , CHENG J , XU Y W , et al. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Transactions on Medical Imaging, 2018, 37 (7): 1597- 1605. doi: 10.1109/TMI.2018.2791488
11	CHENG J , LI Z G , GU Z W , et al. Structure-preserving guided retinal image filtering and its application for optic disk analysis. IEEE Transactions on Medical Imaging, 2018, 37 (11): 2536- 2546. doi: 10.1109/TMI.2018.2838550
12	YU S , XIAO D , FROST S , et al. Robust optic disc and cup segmentation with deep learning for glaucoma detection. Computerized Medical Imaging and Graphics, 2019, 74, 61- 71. doi: 10.1016/j.compmedimag.2019.02.005
13	XIE Z , LING T H , YANG Y Y , et al. Optic disc and cup image segmentation utilizing contour-based transformation and sequence labeling networks. Journal of Medical Systems, 2020, 44 (5): 96. doi: 10.1007/s10916-020-01561-2
14	YIN P S , XU Y W , ZHU J H , et al. Deep level set learning for optic disc and cup segmentation. Neurocomputing, 2021, 464, 330- 341. doi: 10.1016/j.neucom.2021.08.102
15	YUAN X , ZHOU L X , YU S Y , et al. A multi-scale convolutional neural network with context for joint segmentation of optic disc and cup. Artificial Intelligence in Medicine, 2021, 113, 102035. doi: 10.1016/j.artmed.2021.102035
16	GUO W , ZHANG G D , GONG Z X , et al. Effective integration of object boundaries and regions for improving the performance of medical image segmentation by using two cascaded networks. Computer Methods and Programs in Biomedicine, 2021, 212, 106423. doi: 10.1016/j.cmpb.2021.106423
17	SHANMUGAM P , RAJA J , PITCHAI R . An automatic recognition of glaucoma in fundus images using deep learning and random forest classifier. Applied Soft Computing, 2021, 109, 107512. doi: 10.1016/j.asoc.2021.107512
18	HASAN M K , ALAM M A , ELAHI M T E , et al. DRNet: segmentation and localization of optic disc and fovea from diabetic retinopathy image. Artificial Intelligence in Medicine, 2021, 111, 102001. doi: 10.1016/j.artmed.2020.102001
19	HERVELLA Á S , ROUCO J , NOVO J , et al. End-to-end multi-task learning for simultaneous optic disc and cup segmentation and glaucoma classification in eye fundus images. Applied Soft Computing, 2022, 116, 108347. doi: 10.1016/j.asoc.2021.108347
20	ZHOU W , PENG Y H , JI J H , et al. RMSDSC-Net: a robust multiscale feature extraction with depthwise separable convolution network for optic disc and cup segmentation. International Journal of Intelligent Systems, 2022, 37 (12): 11482- 11505. doi: 10.1002/int.23051
21	蒋芸, 高静, 王发林. SAG-Net: 用于联合视盘和视杯分割的新型跳过注意力指导网络. 计算机工程与科学, 2021, 43 (7): 1273- 1282. doi: 10.3969/j.issn.1007-130X.2021.07.017
	JIANG Y , GAO J , WANG F L . SAG-Net: a new skip attention guided network for joint disc and cup segmentation. Computer Engineering & Science, 2021, 43 (7): 1273- 1282. doi: 10.3969/j.issn.1007-130X.2021.07.017
22	徐蓬泉, 梁宇翔, 李英. 融合多尺度语义和剩余瓶颈注意力的医学图像分割. 计算机工程, 2023, 49 (10): 162- 170. doi: 10.3778/j.issn.1002-8331.2201-0405
	XU P Q , LIANG Y X , LI Y . Medical image segmentation fusing multi-scale semantic and residual bottleneck attention. Computer Engineering, 2023, 49 (10): 162- 170. doi: 10.3778/j.issn.1002-8331.2201-0405
23	刘洪普, 赵一浩, 侯向丹, 等. 融合上下文和注意力的视盘视杯分割. 中国图象图形学报, 2021, 26 (5): 1041- 1057. URL
	LIU H P , ZHAO Y H , HOU X D , et al. Optic disc and cup segmentation by combining context and attention. Journal of Image and Graphics, 2021, 26 (5): 1041- 1057. URL
24	刘然, 刘建霞, 王海翼. 改进U-net++的青光眼视盘视杯分割方法. 电子设计工程, 2023, 31 (1): 27- 33. URL
	LIU R , LIU J X , WANG H Y . The improved U-net++method for glaucoma optic disc and optic cup segmentation. Electronic Design Engineering, 2023, 31 (1): 27- 33. URL
25	IMTIAZ R , KHAN T M , NAQVI S S , et al. Screening of glaucoma disease from retinal vessel images using semantic segmentation. Computers & Electrical Engineering, 2021, 91, 107036. doi: 10.1016/j.compeleceng.2021.107036
26	HAIDER A , ARSALAN M , LEE M B , et al. Artificial intelligence-based computer-aided diagnosis of glaucoma using retinal fundus images. Expert Systems with Applications, 2022, 207, 117968. doi: 10.1016/j.eswa.2022.117968
27	WANG S J , YU L Q , YANG X , et al. Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Transactions on Medical Imaging, 2019, 38 (11): 2485- 2495. doi: 10.1109/TMI.2019.2899910
28	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[EB/OL]. [2023-09-20]. http://arxiv.org/abs/1406.2661.
29	BIAN X S , LUO X B , WANG C , et al. Optic disc and optic cup segmentation based on anatomy guided cascade network. Computer Methods and Programs in Biomedicine, 2020, 197, 105717. doi: 10.1016/j.cmpb.2020.105717
30	刘丽霞, 宣士斌, 刘畅, 等. 多专家注释的视杯和视盘不确定性量化. 计算机工程, 2023, 49 (1): 250-257, 269. doi: 10.19678/j.issn.1000-3428.0063897
	LIU L X , XUAN S B , LIU C , et al. Quantification of optic cup and optic disc uncertainty with multi-expert annotations. Computer Engineering, 2023, 49 (1): 250-257, 269. doi: 10.19678/j.issn.1000-3428.0063897
31	YANG L, ZHANG R Y, LI L, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of the 38th International Conference on Machine Learning. [S. l. ]: PMLR, 2021: 11863-11874.
32	HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 13713-13722.
33	崔博, 贾兆年, 姬鹏, 等. 基于改进EfficientNetV2网络的脑肿瘤分类方法. 吉林大学学报(理学版), 2023, 61 (5): 1169- 1177. URL
	CUI B , JIA Z N , JI P , et al. Brain tumor classification method based on improved EfficientNetV2 network. Journal of Jilin University(Science Edition), 2023, 61 (5): 1169- 1177. URL
34	ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein GAN[EB/OL]. [2023-09-20]. http://arxiv.org/abs/1701.07875.
35	ALMAZROA A, ALODHAYB S, OSMAN E, et al. Retinal fundus images for glaucoma analysis: the RIGA dataset[C]//Proceedings of Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications. [S. l. ]: SPIE, 2018: 55-62.
36	LIU B Y , PAN D R , SONG H . Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network. BMC Medical Imaging, 2021, 21 (1): 14. doi: 10.1186/s12880-020-00528-6
37	ZHOU W , JI J H , JIANG Y , et al. EARDS: EfficientNet and attention-based residual depth-wise separable convolution for joint OD and OC segmentation. Frontiers in Neuroscience, 2023, 17, 1139181. doi: 10.3389/fnins.2023.1139181
38	DEWA J K, RACHMAWATI E, KOSALA G. Investigating self-attention in Swin-UNet model for disc and cup segmentation[C]//Proceedings of the 10th International Conference on Information Technology, Computer, and Electrical Engineering(ICITACEE). Washington D. C., USA: IEEE Press, 2023: 1-10.
39	LI Z R , ZHAO C , HAN Z K , et al. TUNet and domain adaptation based learning for joint optic disc and cup segmentation. Computers in Biology and Medicine, 2023, 163, 107209. doi: 10.1016/j.compbiomed.2023.107209

[1]	ZHANG Tianpeng, HAN Jing, LÜ Xueqiang. Super-Resolution-Aided Small-Target Detection Based on Multi-Task Learning [J]. Computer Engineering, 2024, 50(9): 304-312.
[2]	GUO Min, ZHANG Xihan, LI Yang. Integrated Attentional Teacher Mutual Consistency Semi-Supervised Medical Image Segmentation [J]. Computer Engineering, 2024, 50(9): 313-323.
[3]	ZENG Yuqi, LIU Bo, ZHONG Baichang, ZHONG Jin. Student Classroom Behavior Detection Algorithm Based on Improved YOLOv8 in Smart Education [J]. Computer Engineering, 2024, 50(9): 344-355.
[4]	LI Junjun, DONG Jiangang, LI Kun. Research on Kubernetes-based Cluster Energy-Saving Strategy [J]. Computer Engineering, 2024, 50(9): 82-91.
[5]	LIN Chang, GUO Wei, REN Zhecong, JIN Haibo. Unification Algorithm for Object Tracking and Segmentation Based on Transformer [J]. Computer Engineering, 2024, 50(9): 130-141.
[6]	LI Zelin, LÜ Zhaofeng, CHEN Fuqiang, LI Ke. Entity Alignment Model Based on Multi-Hop Information Fusion [J]. Computer Engineering, 2024, 50(9): 142-152.
[7]	WANG Ruying, MA Jiajun, DONG Jianqiang, LIU Wanlong, ZHANG Haitao, YIN Kai, ZHAO Bochao. Industrial Load Forecasting Method Based on MTS-BiGRU-DMHSA [J]. Computer Engineering, 2024, 50(9): 169-178.
[8]	ZHU Kai, LI Li, ZHANG Tong, JIANG Sheng, BIE Yiming. Multi-Stage Motion Blur Image Restoration Network Based on Transformer [J]. Computer Engineering, 2024, 50(9): 276-285.
[9]	Suzhe WANG, Xueying ZHANG, Xiaoyu CHEN, Fenglian LI, Zeling WU. EEG Enhancement Algorithm Based on Combination of Effective Attention and GAN [J]. Computer Engineering, 2024, 50(8): 336-344.
[10]	Yu WANG, Qi QI, Chun WANG, Cai XU. High-Precision Fault Diagnosis Method for Energy Storage Inverter Signals [J]. Computer Engineering, 2024, 50(8): 389-396.
[11]	Rixin RAO, Yiwen WANG, Lizhi ZENG, Xintian TONG, Haitao ZHAO. Lightweight Network Model for Waste Cable Detection [J]. Computer Engineering, 2024, 50(8): 22-30.
[12]	Huayu LI, Zhikang ZHANG, Yang YAN, Yang YUE. Enhanced Domain Multi-modal Entity Recognition Based on Knowledge Graph [J]. Computer Engineering, 2024, 50(8): 31-39.
[13]	Lei WANG, Shipeng DANG, Feng PAN. Model for Predicting Concealed Accessory Pathway Based on Convolutional Neural Network [J]. Computer Engineering, 2024, 50(8): 40-49.
[14]	Han CHEN, Chunlei ZHAO, Haoda JIANG, Chundong WANG. Research on App User Intent Recognition Based on Fusion Model and Semantic Network [J]. Computer Engineering, 2024, 50(8): 50-63.
[15]	Ci XIAO, Yang XU, Yongdan ZHANG, Mingwen FENG, Yiqian HUANG. Nighttime Semantic Segmentation with Attention and Low-Light Enhancement [J]. Computer Engineering, 2024, 50(7): 271-281.

Please choose a citation manager

Content to export