融合注意力谱非局部块的视网膜图像质量分级

doi:10.19665/j.issn1001-2400.20231101

摘要/Abstract

摘要：

视网膜图像质量评估(RIQA)是筛查糖尿病视网膜病变的关键组成部分之一。针对视网膜图像质量差异大且质量评估模型泛化能力不足等问题,提出一种融合注意力谱非局部块的多特征算法来对RIQA进行预测分级。首先采用融合光谱非局部块的ResNet50网络对输入图像进行特征提取;其次引入高效通道注意力用于提升模型对数据的表达能力,有效捕获通道间特征信息关系;再次利用特征迭代注意力融合模块对各局部特征信息融合;最后联合焦点损失和正则损失进一步提高质量分级的效果。在Eye-Quality数据集上准确率为88.59%,精确度为87.56%,敏感度和F1值分别为86.10%和86.74%。在RIQA-RFMiD数据集上准确率和F1值分别为84.22%和67.17%,仿真实验表明,文中算法对视网膜图像质量评估任务中具有较好的泛化能力。

关键词: 视网膜图像质量分级, 谱非局部块, 注意力机制, 特征迭代融合, 组合损失

Abstract:

Retinal image quality assessment(RIQA) is one of the key components of screening for diabetic retinopathy.Aiming at the problems of large differences in retinal image quality and insufficient generalization ability of quality evaluation models,a multi-feature algorithm that combines non-local blocks of the attention spectrum is proposed to predict and rank RIQA.First,the ResNet50 network of fused spectral non-local blocks is used to extract the features of the input images;Second,efficient channel attention is introduced to improve the model's ability to express data and effectively capture the characteristic information relationship between channels;Then,the feature iterative attention fusion module is used to fuse the local feature information.Finally,the combined focus loss and regular loss further improve the effect of quality classification.On the Eye-Quality dataset,the accuracy rate is 88.59%,the precision is 87.56%,the sensitivity and F1 value are 86.10% and 86.74%,respectively.The accuracy and F1 values on the RIQA-RFMiD dataset are 84.22% and 67.17%,respectively,and simulation experiments show that the proposed algorithm has a good generalization ability for retinal image quality assessment tasks.

Key words: retinal image quality grading, spectral non-local blocks, attention mechanisms, feature iterative fusion, combined losses

中图分类号:

TP391

梁礼明, 董信, 雷坤, 夏雨辰, 吴健. 融合注意力谱非局部块的视网膜图像质量分级[J]. 西安电子科技大学学报, 2024, 51(4): 102-113.

LIANG Liming, DONG Xin, LEI Kun, XIA Yuchen, WU Jian. Retinal image quality grading for fused attention spectrum non-local blocks[J]. Journal of Xidian University, 2024, 51(4): 102-113.

图/表 12

图1

图2

图3

图4

图5

图6

表1

表2

表3

图7

图8

图9

参考文献 25

[1]	王朝宇, 郭继昌, 王天保. 融合显著性信息的水下图像清晰化算法[J]. 西安电子科技大学学报, 2022, 49(3):137-146.
	WANG Zhaoyu, GUO Jichang, WANG Tianbao, et al. Algorithm for Clarification of the Underwater Image Combining Saliency Information[J]. Journal of Xidian University, 2022, 49(3):137-146.
[2]	KAUSU T R, GOPI V P, WAHID K A, et al. Combination of Clinical and Multiresolution Features for Glaucoma Detection and Its Classification Using Fundus Images[J]. Biocybernetics and Biomedical Engineering, 2018, 38(2):329-341.
[3]	LI X, HU X, QI X, et al. Rotation-Oriented Collaborative Self-Supervised Learning for Retinal Disease Diagnosis[J]. IEEE Transactions on Medical Imaging, 2021, 40(9):2284-2294.
[4]	董慧妍. 基于机器学习的糖尿病性视网膜病变图像分级研究[D]. 北京: 北京邮电大学, 2019.
[5]	AL-BANDER B, AL-NUAIMY W, WILLIAMS B M, et al. Multiscale Sequential Convolutional Neural Networks for Simultaneous Detection of Fovea and Optic Disc[J]. Biomedical Signal Processing and Control, 2018,40:91-101.
[6]	ZAGO G T, ANDREAO R V, DORIZZI B, et al. Retinal Image Quality Assessment Using Deep Learning[J]. Computers in Biology and Medicine, 2018,103:64-70.
[7]	FU H, WANG B, SHEN J, et al. Evaluation of Retinal Image Quality Assessment Networks in Different Color-Spaces[C]//Medical Image Computing and Computer Assisted Intervention. Heidelberg:Springer, 2019:48-56.
[8]	SHI C, LEE J, WANG G, et al. Assessment of Image Quality on Color Fundus Retinal Images Using the Automatic Retinal Image Analysis[J]. Scientific Reports, 2022, 12(1):10455. doi: 10.1038/s41598-022-13919-2 pmid: 35729197
[9]	GUO T, LIANG Z, GU Y, et al. Learning for Retinal Image Quality Assessment with Label Regularization[J]. Computer Methods and Programs in Biomedicine, 2023,228:107238.
[10]	HE K, SUN J. Convolutional Neural Networks at Constrained Time Cost[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway:IEEE, 2015:5353-5360.
[11]	LUO W, LI Y, URTASUN R, et al. Understanding the Effective Receptive Fifield in Deep Convolutional Neural Networks[C]//Neural Information Processing Systems(NeurIPS). San Diego: NeurIPS, 2016:4898-4906.
[12]	LIU Z, LIN Y, CAO Y, et al. Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE, 2021:10012-10022.
[13]	KHAN S, NASEER M, HAYAT M, et al. Transformers in Vision:A Survey[J]. ACM Computing Surveys(CSUR), 2022, 54(10s):1-41.
[14]	SHUMAN D I, NARANG S K, FROSSARD P, et al. The Emerging Field of Signal Processing on Graphs:Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains[J]. IEEE Signal Processing Magazine, 2013, 30(3):83-98.
[15]	WANG Q, WU B, ZHU P, et al. ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2020:11534-11542.
[16]	SUN M, YUAN Y, ZHOU F, et al. Multi-Attention Multi-Class Constraint for Fine-Grained Image Recognition[C]//Proceedings of the European Conference on Computer Vision(ECCV). Heidelberg:Springer, 2018:805-821.
[17]	SUN G, CHOLAKKAL H, KHAN S, et al. Fine-Grained Recognition:Accounting for Subtle Differences Between Similar Classes[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020:12047-12054.
[18]	CUADROS J, BRESNICK G. EyePACS:An Adaptable Telemedicine System for Diabetic Retinopathy Screening[J]. Journal of Diabetes Science and Technology, 2009, 3(3):509-516.
[19]	PACHADE S, PORWAL P, THULKAR D, et al. Retinal Fundus Multi-Disease Image Dataset(RFMID):A Dataset for Multi-Disease Detection Research[J]. Data, 2021, 6(2):14.
[20]	XU Z, ZOU B, LIU Q. A Dark and Bright Channel Prior Guided Deep Network for Retinal Image Quality Assessment[J]. Biocybernetics and Biomedical Engineering, 2022, 42(3):772-783.
[21]	梁礼明, 董信, 李仁杰, 等. 基于注意力机制多特征融合的视网膜病变分级算法[J]. 光电工程, 2023, 50(1):100-112.
	LIANG Liming, DONG Xin, LI Renjie, et al. Classification Algorithm of Retinopathy Based on Attention Mechanism and Multi Feature Fusion[J]. Opto-Electronic Engineering, 2023, 50(1):100-112.
[22]	OU F Z, WANG Y G, ZHU G. A Novel Blind Image Quality Assessment Method Based on Refined Natural Scene Statistics[C]//2019 IEEE International Conference on Image Processing(ICIP).Piscataway:IEEE, 2019: 1004-1008.
[23]	YAN Q, GONG D, ZHANG Y. Two-Stream Convolutional Networks for Blind Image Quality Assessment[J]. IEEE Transactions on Image Processing, 2018, 28(5):2200-2211.
[24]	梁礼明, 雷坤, 詹涛, 等. 基于锐度感知最小化与多色域双级融合的视网膜图片质量分级[J]. 科学技术与工程, 2022, 22(32):14289-14297.
	LIANG Liming, LEI Kun, ZHAN Tao, et al. Retinal Image Quality Based on Sharpness Perception Minimization and Multi-Gamut Bi-Level Fusion[J]. Science Technology and Engineering, 2022, 22(32):14289-14297.
[25]	SONG J, YANG R. Feature Boosting,Suppression,and Diversification for Fine-Grained Visual Classification[C]//2021 International Joint Conference on Neural Networks(IJCNN).Piscataway:IEEE, 2021: 1-8.

实验	准确率/%	精确率/%	召回率/%	F1/%
M1	88.05	86.70	85.82	86.20
M2	88.08	86.57	85.72	86.13
M3	88.28	87.04	85.80	86.30
M4	88.47	87.77	85.64	86.61
M5	88.59	87.56	86.10	86.74

模型	准确率/%	精确率/%	召回率/%	F1/%
NBIQA^[22]	79.17	76.41	75.09	74.41
TS-CNN^[23]	79.26	79.76	74.46	74.81
DenseNet121-RGB^[7]	85.68	84.81	82.39	83.15
DenseNet121-MCF^[7]	87.22	85.63	84.82	85.06
ResNeSt^[24]	87.35	85.87	85.07	85.44
Dual-path CNN^[9]	—	88.68	87.86	88.20
文中方法	88.59	87.56	86.10	86.74

模型	准确率/%	精确率/%	召回率/%	F1/%
ResNet50^[25]	83.75	77.84	56.49	61.84
DenseNet121-RGB^[7]	83.13	71.87	57.41	60.42
DenseNet121-MCF^[7]	82.81	75.13	61.31	65.53
文中算法	84.22	73.95	62.94	67.17