基于对抗学习和迭代优化的视网膜血管分割

doi:10.1007/s12204-022-2479-5

J Shanghai Jiaotong Univ Sci ›› 2024, Vol. 29 ›› Issue (1): 73-80.doi: 10.1007/s12204-022-2479-5

所属专题：医学图像

基于对抗学习和迭代优化的视网膜血管分割

顾闻，徐奕

（上海交通大学电子信息与电气工程学院，上海200240）

接受日期:2021-02-26 出版日期:2024-01-24 发布日期:2024-01-24

Retinal Vessel Segmentation via Adversarial Learning and Iterative Refinement

GU Wen (顾闻), XU Yi^∗ (徐奕)

(School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China)

Accepted:2021-02-26 Online:2024-01-24 Published:2024-01-24

摘要/Abstract

摘要： 由于数据量小、血管细小、图像对比度低等特点，视网膜血管分割是一项具有挑战性的医学任务。为了解决这些问题，文中引入了一种新的卷积神经网络，同时利用了对抗学习和循环神经网络的优势。采用递归单元迭代设计网络，逐步优化输入视网膜图像的分割结果。循环单元保留高级语义信息，用于特征重用，从而输出足够精细的分割图，而不是粗掩码。此外，对抗性损失对分割的血管区域施加了完整性和连通性约束，从而大大减少了分割的拓扑错误。在DRIVE数据集上的实验结果表明，该方法的AUC和灵敏度分别达到98.17%和80.64%。与其他现有的最先进方法相比，该方法在视网膜血管分割方面取得了更好的效果。

关键词: 医学图像处理，视网膜图像分割，对抗学习，迭代优化

Abstract: Retinal vessel segmentation is a challenging medical task owing to small size of dataset, micro blood vessels and low image contrast. To address these issues, we introduce a novel convolutional neural network in this paper, which takes the advantage of both adversarial learning and recurrent neural network. An iterative design of network with recurrent unit is performed to refine the segmentation results from input retinal image gradually. Recurrent unit preserves high-level semantic information for feature reuse, so as to output a sufficiently refined segmentation map instead of a coarse mask. Moreover, an adversarial loss is imposing the integrity and connectivity constraints on the segmented vessel regions, thus greatly reducing topology errors of segmentation. The experimental results on the DRIVE dataset show that our method achieves area under curve and sensitivity of 98.17% and 80.64%, respectively. Our method achieves superior performance in retinal vessel segmentation compared with other existing state-of-the-art methods.

Key words: medical image processing, retinal image segmentation, adversarial learning, iterative refinement

中图分类号:

TP29

顾闻，徐奕. 基于对抗学习和迭代优化的视网膜血管分割[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 73-80.

GU Wen (顾闻), XU Yi∗ (徐奕). Retinal Vessel Segmentation via Adversarial Learning and Iterative Refinement[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 73-80.

参考文献

[1] CHATZIRALLI I P, KANONIDOU E D, KERYTTOPOULOS P, et al. The value of fundoscopy in general practice [J]. The Open Ophthalmology Journal, 2012, 6: 4-5.
[2] STAAL J, ABRAMOFF M D, NIEMEIJER M, et al. Ridge-based vessel segmentation in color images of the retina [J]. IEEE Transactions on Medical Imaging, 2004, 23(4): 501-509.
[3] OWEN C G, RUDNICKA A R, MULLEN R, et al. Measuring retinal vessel tortuosity in 10-year-old children: Validation of the Computer-Assisted Image Analysis of the Retina (CAIAR) program [J]. Investigative Ophthalmology & Visual Science, 2009, 50(5): 2004-2010.
[4] HOOVER A D, KOUZNETSOVA V, GOLDBAUM M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response [J]. IEEE Transactions on Medical Imaging, 2002, 19(3): 203-210.
[5] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[M]//Advances in neural information processing systems 27. Red Hook, NY: Curran Associates, 2014: 2672-2680.
[6] VASU S, KOZINSKI M, CITRARO L, et al. TopoAL: An adversarial learning approach for topology-aware road segmentation [M]//Computer vision-ECCV 2020. Cham: Springer, 2020: 224-240.
[7] LUC P, COUPRIE C, CHINTALA S, et al. Semantic segmentation using adversarial networks [EB/OL]. (2016-11-25). https://arxiv.org/abs/1611.08408.
[8] RONNEBERGER O, FISCHER P, BROX T. U-net: Convolutional networks for biomedical image segmentation [M]//Medical image computing and computerassisted intervention-MICCAI 2015. Cham: Springer,2015: 234-241.
[9] LI L Z, VERMA M, NAKASHIMA Y, et al. IterNet: retinal image segmentation utilizing structural redundancy in vessel networks [C]//2020 IEEE Winter Conference on Applications of Computer Vision. Snowmass, CO: IEEE, 2020: 3645-3654.
[10] WANG W, YU K C, HUGONOT J, et al. Recurrent UNet for resource-constrained segmentation [C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 2142-2151.
[11] WU Y C, XIA Y, SONG Y, et al. Multiscale network followed network model for retinal vessel segmentation [M]//Medical image computing and computer assisted intervention-MICCAI 2018. Cham: Springer, 2018: 119-126.
[12] MA W A, YU S, MA K, et al. Multi-task neural networks with spatial activation for retinal vessel segmentation and artery/vein classification [M]//Medical image computing and computer assisted interventionMICCAI 2019. Cham: Springer, 2019: 769-778.
[13] KINGMA D P, BA J. Adam: A method for stochastic optimization [EB/OL]. (2014-12-22). https://arxiv.org/abs/1412.6980.
[14] JIN Q G, MENG Z P, PHAM T D, et al. DUNet: A deformable network for retinal vessel segmentation [J]. Knowledge-Based Systems, 2019, 178: 149-162.
[15] LI X M, CHEN H, QI X J, et al. H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes [J]. IEEE Transactions on Medical Imaging, 2018, 37(12): 2663-2674.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	48

来源	本网站	其他网站

次数	31	17
比例	65%	35%

摘要

345

最新录用	在线预览	正式出版

0	0	345

来源	本网站	其他网站

次数	40	305
比例	12%	88%

基于对抗学习和迭代优化的视网膜血管分割

Retinal Vessel Segmentation via Adversarial Learning and Iterative Refinement

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐 0

Metrics

本文评价

[1]	. 基于呼气末二氧化碳感知的气管插管方法[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 582-590.
[2]	詹何庆1，韩贵来1，魏传安1，李治群2. 人工智能结合磁共振成像和计算建模在心脏电生理与临床诊断中的应用[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(1): 53-65.
[3]	杨坚1，李聪敏2，洪道鉴1，卢东祁1，林秋佳3，方兴其2，喻谦1，张乾1. 基于人体关键点的室内电力人员安全行为实时检测技术[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(2): 309-315.
[4]	HAN Yi (韩毅), CAI Jian-hu (蔡建湖), IKOU Kaku, LI Yan-lai (李延来) CHE. Evolutionary Algorithms for Solving Unconstrained Multilevel Lot-Sizing Problem with Series Structure[J]. 上海交通大学学报（英文版）, 2012, 17(1): 39-044.