基于高分辨率网络的视杯和视盘的联合分割

doi:10.13229/j.cnki.jdxbgxb.20211082

Abstract

Abstract:

Measuring cup to disk ratio（CDR） by segmenting optic disc（OD） and optic cup（OC） is an effective method for diagnosis of glaucoma. Compared with OD segmentation，OC segmentation still faces difficulties in segmentation accuracy. In this paper，a deep learning architecture MS-HRNET is proposed for joint segmentation of OC and OD. It is an improved architecture based on HRNET. By adding multi-scale input to HRNET，information loss during feature extraction can be compensated. Combined with multi-scale spatial and channel attention mechanism，deep image features are extracted. By adding a side output layer，the early training of the network is guided. Experimental results show that the proposed model performs better than the existing OC and OD segmentation methods on Drishti-GS1 and REFUGE datasets.

Key words: optic cup and optic disc segmentation, high-resolution network, multi-scale input, attention mechanism

CLC Number:

TP391.4

Xiao-xin GUO,Jia-hui LI,Bao-liang ZHANG. Joint segmentation of optic cup and disc based on high resolution network[J].Journal of Jilin University(Engineering and Technology Edition), 2023, 53(8): 2350-2357.

Figures/Tables 16

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Table 2

Table 3

Table 4

Table 5

Table 6

Table 7

Table 8

Table 9

Segmentation comparison of each model on REFUGE dataset"

方法	$J A C C O D$	$J A C C O C$	MIoU
U-Net	0.8750	0.7760	0.8516
M-Net	0.8826	0.7897	0.8605
SegNet	0.8816	0.7906	0.8597
cGANs	0.8843	0.8000	0.8655
CDED-Net	0.8837	0.8111	0.8705
本文	0.9757	0.8891	0.9463

Table 9

Fig.5

Table 10

Fig.6

References 24

1	Tham Y C, Li X, Wong T Y, et al. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis[J]. Ophthalmology, 2014, 121(11): 2081-2090.
2	Michelson G, Simone W, Hornegger J, et al. The papilla as screening parameter for early diagnosis of glaucoma[J]. Deutsches Rzteblatt International, 2008, 105(34/35):583-589.
3	Wong D W K, Liu J, Lim J H, et al. Level-set based automatic cup-to-disc ratio determination using retinal fundus images in ARGALI[C]∥30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vancourer, 2008: 2266-2269.
4	Inoue N, Yanashima K, Magatani K, et al. Development of a simple diagnostic method for the glaucoma using ocular Fundus pictures[C]∥IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China, 2006: 3355-3358.
5	Blanco M, Penedo M G, Barreira N, et al. Localization and extraction of the optic disc using the fuzzy circular hough transform[C]∥International Conference on Artificial Intelligence and Soft Computing, Berlin, Heidelberg, 2006: 712-721.
6	Sevastopolsky A. Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network[J]. Pattern Recognition and Image Analysis, 2017, 27(3): 618-624.
7	Fu H, Cheng J, Xu Y, et al. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation[J]. IEEE Transactions on Medical Imaging, 2018, 37(7): 1597-1605.
8	Wang S, Yu L, Yang X, et al. Patch-based output space adversarial learning for joint optic disc and cup segmentation[J]. IEEE Transactions on Medical Imaging, 2019, 38(11): 2485-2495.
9	Zilly J, Buhmann J M, Mahapatra D. Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation[J]. Computerized Medical Imaging and Graphics, 2017, 55: 28-41.
10	Gu Z, Cheng J, Fu H, et al. Ce-net: context encoder network for 2d medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2019, 38(10): 2281-2292.
11	Tabassum M, Khan T M, Arsalan M, et al. CDED-Net: Joint segmentation of optic disc and optic cup for glaucoma screening[J]. IEEE Access, 2020, 8: 102733-102747.
12	Sun K, Xiao B, Liu D, et al. Deep high-resolution representation learning for human pose estimation[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,Long Beach, 2019: 5693-5703.
13	Zhao H S, Qi X J, Shen X Y, et al. Icnet for real-time semantic segmentation on high-resolution images[C]∥Proceedings of the European Conference on Computer Vision, 2018: 405-420.
14	Sun K, Zhao Y, Jiang B, et al. High-resolution representations for labeling pixels and regions[J]. arXiv Preprint Arxiv:.
15	Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2017: 4700-4708.
16	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Veges, 2016: 770-778.
17	Wang Q L, Wu B G, Zhu P E, et al. ECA-net: efficient channel attention for deep convolutional neural networks[J]. arXiv preprint arXiv:.
18	袁伟,许文波,周甜.一种深度学习分割遥感影像道路的损失函数[J].中国空间科学技术,2021,41(4):134-141.
	Yuan Wei, Xu Wen-bo, Zhou Tian. A loss function of road segmentation in remote sensing image by deep learning[J]. Chinese Space Science and Technology, 2021,41(4):134-141.
19	Orlando J I, Fu H, Breda J B, et al. Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs[J]. Medical Image Analysis, 2020, 59: 101570.
20	Sivaswamy J, Krishnadas S R, Joshi G D, et al. Drishti-gs: retinal image dataset for optic nerve head (onh) segmentation[C]∥IEEE 11th International Symposium on Biomedical Imaging,Beijing, China, 2014: 53-56.
21	Fu H, Cheng J, Xu Y, et al. Disc-aware ensemble network for glaucoma screening from fundus image[J]. IEEE Transactions on Medical Imaging, 2018, 37(11): 2493-2501.
22	Badrinarayanan V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
23	Liu S, Hong J, Lu X, et al. Joint optic disc and cup segmentation using semi-supervised conditional GANs[J]. Computers in Biology and Medicine, 2019, 115: 103485.
24	Xu Y, Lu S, Li H, et al. Mixed maximum loss design for optic disc and optic cup segmentation with deep learning from imbalanced samples[J]. Sensors, 2019, 19(20): 19204401.

Related Articles 15

[1]	Fei-fei TANG,Hai-lian ZHOU,Tian-jun TANG,Hong-zhou ZHU,Yong WEN. Multi⁃step prediction method of landslide displacement based on fusion dynamic and static variables [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(6): 1833-1841.
[2]	Yan-tao TIAN,Xing HUANG,Hui-qiu LU,Kai-ge WANG,Fu-qiang XU. Multi⁃mode behavior trajectory prediction of surrounding vehicle based on attention and depth interaction [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(5): 1474-1480.
[3]	Wei LYU,Jia-ze HAN,Jing-hui CHU,Pei-guang JING. Multi⁃modal self⁃attention network for video memorability prediction [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1211-1219.
[4]	Yan-tao TIAN,Fu-qiang XU,Kai-ge WANG,Zi-xu HAO. Expected trajectory prediction of vehicle considering surrounding vehicle information [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 674-681.
[5]	Ji-hong OUYANG,Ze-qi GUO,Si-guang LIU. Dual⁃branch hybrid attention decision net for diabetic retinopathy classification [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 648-656.
[6]	Xian-tong LI,Wei QUAN,Hua WANG,Peng-cheng SUN,Peng-jin AN,Yong-xing MAN. Route travel time prediction on deep learning model through spatiotemporal features [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 557-563.
[7]	Xiao⁃lei CHEN,Yong⁃feng SUN,Ce LI,Dong⁃mei LIN. Stable anti⁃noise fault diagnosis of rolling bearing based on CNN⁃BiLSTM [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 296-309.
[8]	Da-ke ZHOU,Chao ZHANG,Xin YANG. Self-supervised 3D face reconstruction based on multi-scale feature fusion and dual attention mechanism [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(10): 2428-2437.
[9]	De-xing WANG,Ruo-you WU,Hong-chun YUAN,Peng GONG,Yue WANG. Underwater image restoration based on multi-scale attention fusion and convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1396-1404.
[10]	Ya-hui ZHAO,Fei-yang YANG,Zhen-guo ZHANG,Rong-yi CUI. Korean text structure discovery based on reinforcement learning and attention mechanism [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1387-1395.
[11]	Yuan-ning LIU,Di WU,Xiao-dong ZHU,Qi-xian ZHANG,Shuang-shuang LI,Shu-jun GUO,Chao WANG. User interface components detection algorithm based on improved YOLOv3 [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(3): 1026-1033.
[12]	Hai-ying ZHAO,Wei ZHOU,Xiao-gang HOU,Xiao-li ZHANG. Double-layer annotation of traditional costume images based on multi-task learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(1): 293-302.
[13]	Hong-wei ZHAO,Xiao-han LIU,Yuan ZHANG,Li-li FAN,Man-li LONG,Xue-bai ZANG. Clothing classification algorithm based on landmark attention and channel attention [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(5): 1765-1770.
[14]	Dan⁃tong OUYANG,Jun XIAO,Yu⁃xin YE. Distant supervision for relation extraction with weakconstraints of entity pairs [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 912-919.
[15]	SUN Jin-Qiu, ZHANG Yan-Ning, ZHOU Jun, JIANG Lei. Small and dim target detection based on selective visual attention mechanism and curve detection method [J]. 吉林大学学报(工学版), 2010, 40(06): 1683-1687.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

方法	视杯		视盘		MIoU
方法	JACC	Dice	JACC	Dice	MIoU
网络（无多尺度输入）	0.8570	0.9218	0.9497	0.9738	0.9187
网络（多尺度输入）	0.8808	0.9358	0.9658	0.9825	0.9368

方法	视杯		视盘		MIoU
方法	JACC	Dice	JACC	Dice	MIoU
网络（无多尺度输入）	0.8686	0.9263	0.9752	0.9874	0.9340
网络（多尺度输入）	0.8757	0.9299	0.9759	0.9878	0.9374

方法	视杯		视盘		MIoU
方法	JACC	Dice	JACC	Dice	MIoU
网络（无MCCAM模块）	0.8570	0.9218	0.9497	0.9738	0.9187
网络（有MCCAM模块）	0.8818	0.9368	0.9668	0.9835	0.9378

方法	视杯		视盘		MIoU
方法	JACC	Dice	JACC	Dice	MIoU
网络（无MCCAM模块）	0.8686	0.9263	0.9752	0.9874	0.9340
网络（有MCCAM模块）	0.8758	0.9295	0.9720	0.9858	0.9326

方法	视杯		视盘		MIoU
方法	JACC	Dice	JACC	Dice	MIoU
网络（无MCCAM模块）	0.8714	0.9266	0.9754	0.9875	0.9352
网络（有MCCAM模块）	0.8812	0.9328	0.9773	0.9885	0.9398

Joint segmentation of optic cup and disc based on high resolution network

RICH HTML

PDF (PC)