基于深度卷积集成网络的视网膜多种疾病筛查和识别方法

doi:10.11959/j.issn.2096-6652.202127

智能科学与技术学报 ›› 2021, Vol. 3 ›› Issue (3): 259-267.doi: 10.11959/j.issn.2096-6652.202127

• 专刊：目标智能检测与识别 • 上一篇下一篇

基于深度卷积集成网络的视网膜多种疾病筛查和识别方法

王禾扬, 杨启鸣, 朱旗

南京航空航天大学计算机科学与技术学院，江苏南京 211100

修回日期:2021-07-08 出版日期:2021-09-15 发布日期:2021-09-01
作者简介:王禾扬（1996− ），男，南京航空航天大学计算机科学与技术学院硕士生，主要研究方向为模式识别、医学影像处理
杨启鸣（1996− ），男，南京航空航天大学计算机科学与技术学院硕士生，主要研究方向为模式识别、医学影像处理
朱旗（1985− ），男，博士，南京航空航天大学计算机科学与技术学院副教授，主要研究方向为模式识别、医学影像分析、生物特征识别
基金资助:
中央高校基本科研业务费专项资金项目(NT2020024)

Retinal multi-disease screening and recognition method based on deep convolution ensemble network

Heyang WANG, Qiming YANG, Qi ZHU

College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211100, China

Revised:2021-07-08 Online:2021-09-15 Published:2021-09-01
Supported by:
Fundamental Research Funds for the Central Universities(NT2020024)

摘要/Abstract

摘要：

针对视网膜疾病种类繁多、病灶位置不固定等特点，提出一种基于深度卷积集成网络的视网膜多种疾病筛查和识别方法。首先，根据视网膜眼底图像裁剪掉两侧黑色边框，并去除图像中的噪声，以降低对眼底图像的干扰，提高图像的清晰度；之后，通过对处理完成的视网膜眼底图像使用裁剪、旋转等数据增强方法来扩增数据集；再建立基于深度卷积神经网络的模型进行特征提取，并在网络模型微调后完成视网膜疾病筛查和识别任务，最终将多个模型的结果进行集成。实验结果表明，该方法针对视网膜疾病的筛查和识别的问题取得了较好的效果，视网膜疾病筛查的准确率达到96.05%，视网膜疾病识别的准确率达到72.55%。

关键词: 视网膜眼底图像, 疾病筛查, 疾病识别, 深度卷积网络, 集成模型

Abstract:

As for the characteristics of various types of retinal diseases and uncertainty of the location of the lesions, a retinal multi-disease screening and recognition method based on deep convolutional ensemble network was proposed.Firstly, the black borders on both sides of the retinal fundus image were cut off, and the noise in the image was removed to reduce the interference to the retinal image and increase the clarity of the image.After that, data augmentation methods such as cropping and rotating were performed to process retinal fundus image to amplify the dataset.Then, a model based on deep convolutional neural network was built for feature extraction, and the network model was fine-tuned to complete the task of screening and identifying retinal diseases.Finally, the results of multiple models were ensembled.The experimental results show that this method has achieved good results for the screening and recognition of retinal diseases, the accuracy of retinal disease screening is 96.05%, and the accuracy of retinal disease recognition is 72.55%.

Key words: retinal fundus image, disease screening, disease recognition, deep convolutional network, ensemble model

中图分类号:

TP391.4

王禾扬,杨启鸣,朱旗. 基于深度卷积集成网络的视网膜多种疾病筛查和识别方法[J]. 智能科学与技术学报, 2021, 3(3): 259-267.

Heyang WANG,Qiming YANG,Qi ZHU. Retinal multi-disease screening and recognition method based on deep convolution ensemble network[J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(3): 259-267.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

本文方法和对比方法的实验结果"

方法	多种疾病筛查结果ACC	多种疾病筛查结果AUC	多种疾病识别结果ACC	多种疾病识别结果mAP
Three-Stream^[12]	91.57%	91.36%	63.47%	62.98%
ResNet50^[23]	93.77%	93.54%	60.55%	61.09%
VGG16^[24]	88.24%	89.12%	57.43%	56.21%
EfficientNet-B5	94.35%	93.89%	67.88%	65.73%
EfficientNet-B6	94.74%	95.33%	68.74%	67.35%
EfficientNet-B7	95.16%	95.32%	70.45%	69.89%
本文方法	$96 . 05 %$	$97 . 18 %$	$72 . 55 %$	$73 . 24 %$

表1

图10

图11

参考文献 24

[1]	STEINMETZ J D , BOURNE R R A , BRIANT P S ,et al. Causes of blindness and vision impairment in 2020 and trends over 30 years,and prevalence of avoidable blindness in relation to VISION 2020:the right to sight:an analysis for the global burden of disease study[J]. The Lancet Global Health, 2021,9(2): 144-160.
[2]	王诗惠, 郝晓凤, 谢立科 . 人工智能在视网膜疾病中应用的研究现状与展望[J]. 中华眼科医学杂志(电子版), 2020,10(6): 374-379.
	WANG S H , HAO X F , XIE L K . Research status and prospects of ap-plication of artificial intelligence in retinal diseases[J]. Chinese Journal of Ophthalmologic Medicine (Electronic Edition), 2020,10(6): 374-379.
[3]	PRATT H , COENEN F , BROADBENT D M ,et al. Convolutional neural networks for diabetic retinopathy[J]. Procedia Computer Science, 2016,90: 200-205.
[4]	COLAS E , BESSE A , ORGOGOZO A ,et al. Deep learning approach for diabetic retinopathy screening[J]. Acta Ophthalmologica, 2016,94.
[5]	WORRALL D E , WILSON C M , BROSTOW G J . Automated retinopathy of prematurity case detection with convolutional neural networks[C]// Proceedings of the Deep Learning and Data Labeling for Medical Applications. Cham:Springer, 2016: 68-76.
[6]	BURLINA P , PACHECO K D , JOSHI N ,et al. Comparing humans and deep learning performance for grading AMD:a study in using universal deep features and transfer learning for automated AMD analysis[J]. Computers in Biology and Medicine, 2017,82: 80-86.
[7]	ALTAF T , ANWAR S M , GUL N ,et al. Multi-class Alzheimer’s disease classification using image and clinical features[J]. Biomedical Signal Processing and Control, 2018,43: 64-74.
[8]	LIAO H F , LI Y C , LUO J B . Skin disease classification versus skin lesion characterization:achieving robust diagnosis using multi-label deep neural networks[C]// Proceedings of the 2016 23rd International Conference on Pattern Recognition. Piscataway:IEEE Press, 2016: 355-360.
[9]	SIDDIQUI M , MUJTABA G , REZA A ,et al. Multi-class disease classification in brain MRIs using a computer-aided diagnostic system[J]. Symmetry, 2017,9(3): 37.
[10]	LEE C S , BAUGHMAN D M , LEE A Y . Deep learning is effective for classifying normal versus age-related macular degeneration OCT images[J]. Ophthalmology Retina, 2017,1(4): 322-327.
[11]	ARUNKUMAR R , KARTHIGAIKUMAR P . Multi-retinal disease classification by reduced deep learning features[J]. Neural Computing and Applications, 2017,28(2): 329-334.
[12]	WANG X , JU L , ZHAO X ,et al. Retinal abnormalities recognition using regional multitask learning[C]// Proceedings of the Lecture Notes in Computer Science. Cham:Springer, 2019: 30-38.
[13]	CHOI J Y , YOO T K , SEO J G ,et al. Multi-categorical deep learning neural network to classify retinal images:a pilot study employing small database[J]. PLoS One, 2017,12(11): e0187336.
[14]	曲毅, 张焕开, 宋先 ,等. 人工智能诊断系统在视网膜疾病的研究进展[J]. 山东大学学报(医学版), 2020,58(11): 39-44.
	QU Y , ZHANG H K , SONG X ,et al. Research progress of artificial intelligence diagnosis system in retinal diseases[J]. Journal of Shan-dong University (Health Sciences), 2020,58(11): 39-44.
[15]	ZUIDERVELD K . Contrast limited adaptive histogram equalization[M]// Graphics gems. Amsterdam: Elsevier, 1994: 474-485.
[16]	YUN S , HAN D , CHUN S ,et al. CutMix:regularization strategy to train strong classifiers with localizable features[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE Press, 2019: 6022-6031.
[17]	TAN M X , LE Q V . EfficientNet:rethinking model scaling for convolutional neural networks[C]// Proceedings of the International Conference on Machine Learning.[S.l.:s..n.], 2019: 6105-6114.
[18]	HOWARD A , SANDLER M , CHEN B ,et al. Searching for MobileNetV3[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE Press, 2019: 1314-1324.
[19]	RAMACHANDRAN P , ZOPH B , LE Q V . Searching for activation functions[J]. arXiv preprint,2017,arXiv:1710.05941.
[20]	HU J , SHEN L , SUN G . Squeeze-and-excitation networks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 7132-7141.
[21]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016: 770-778.
[22]	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.
[23]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016: 770-778.
[24]	SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint,2014,arXiv:1409,1556.

基于深度卷积集成网络的视网膜多种疾病筛查和识别方法

Retinal multi-disease screening and recognition method based on deep convolution ensemble network

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 24

相关文章 10

Metrics

推荐阅读 0

[1]	于航, 付彦伟, 姜柏言, 薛向阳. 基于少量图像的三维重建综述[J]. 智能科学与技术学报, 2022, 4(4): 544-559.
[2]	邵虹, 张鸣坤, 崔文成. 基于分层卷积神经网络的皮肤镜图像分类方法[J]. 智能科学与技术学报, 2021, 3(4): 474-481.
[3]	李颖, 陈龙, 黄钊宏, 孙杨, 蔡国榕. 基于多尺度卷积神经网络特征融合的植株叶片检测技术[J]. 智能科学与技术学报, 2021, 3(3): 304-311.
[4]	田庆, 胡蓉, 李佐勇, 蔡远征, 余兆钗. 基于SE-YOLOv5s的绝缘子检测[J]. 智能科学与技术学报, 2021, 3(3): 312-321.
[5]	余沁茹, 卢桂馥. 一种基于最大相关熵和局部约束的协同表示分类器[J]. 智能科学与技术学报, 2021, 3(3): 334-341.
[6]	姚裕, 万鸣华. 鲁棒的非负监督低秩鉴别嵌入算法[J]. 智能科学与技术学报, 2021, 3(3): 342-350.
[7]	石林瑞, 黄祎婧, 符进武, 郭心悦, 范自柱. 特征空间中基于半遗传稀疏表示的图像识别[J]. 智能科学与技术学报, 2021, 3(3): 359-369.
[8]	崔文成, 张鹏霞, 邵虹. 基于深度可分离卷积网络的皮肤镜图像病灶分割方法[J]. 智能科学与技术学报, 2020, 2(4): 385-393.
[9]	杜宏庆,陈德旺,黄允浒,朱凤华,李灵犀. 基于改进遗传算法与支持度的模糊系统优化建模方法[J]. 智能科学与技术学报, 2020, 2(2): 179-185.
[10]	陈德旺,蔡际杰,黄允浒. 面向可解释性人工智能与大数据的模糊系统发展展望[J]. 智能科学与技术学报, 2019, 1(4): 327-334.