[1]梁冰雪,王文婧,王皓祺,等.面向糖尿病视网膜病变分级的多层特征关注增强网络[J].中国医学物理学杂志,2025,42(9):1174-1183.[doi:DOI:10.3969/j.issn.1005-202X.2025.09.008]
　LIANG Bingxue,WANG Wenjing,WANG Haoqi,et al.Multi-layer feature attention enhanced network for diabetic retinopathy staging[J].Chinese Journal of Medical Physics,2025,42(9):1174-1183.[doi:DOI:10.3969/j.issn.1005-202X.2025.09.008]
点击复制

面向糖尿病视网膜病变分级的多层特征关注增强网络()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
42
期数:
2025年第9期
页码:
1174-1183
栏目:
医学影像物理
出版日期:
2025-09-30

文章信息/Info

Title:
Multi-layer feature attention enhanced network for diabetic retinopathy staging
文章编号:
1005-202X（2025）09-1174-10
作者:
梁冰雪1; 王文婧1; 王皓祺2; 关权1; 秦玉华1
1.青岛科技大学信息科学技术学院， 山东 青岛 266061； 2.华东理工大学商学院， 上海 200237
Author(s):
LIANG Bingxue1;  WANG Wenjing1;  WANG Haoqi2;  GUAN Quan1;  QIN Yuhua1
1. School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China 2. School of Business, East China University of Science and Technology, Shanghai 200237, China
关键词:
糖尿病视网膜病变; 图像分类; 特征融合; 计算机辅助诊断
Keywords:
Keywords: diabetes retinopathy image classification feature fusion computer-aided diagnosis
分类号:
R318；TP391.41
DOI:
DOI:10.3969/j.issn.1005-202X.2025.09.008
文献标志码:
A
摘要:
为进一步提高对糖尿病视网膜病变严重程度的诊断准确率，提出一种多层特征关注增强网络（MFAE-Net）。针对处理糖尿病视网膜病变图像时全局与局部特征的统一表达方面不足的问题，采用双分支并行的ResNet-50和DeiT-S模型作为骨干架构，并在网络末端位置设计特征融合模块。同时，设计多尺度位置感知增强模块，通过空洞卷积结合位置注意力机制提取多尺度信息，增强眼底图像中病变的特征表示；设计局部特征增强模块，强化对局部信息的提取能力，从而提高模型识别小病变和微小变化的能力。实验结果表明，本研究提出的MFAE-Net达到87.61%的准确率，表现出优异的分类效果，为进一步推动糖尿病视网膜病变检测技术的发展提供有力的支持。
Abstract:
Abstract: A multi-layer feature attention enhanced network is proposed to further improve the diagnostic accuracy of the severity of diabetic retinopathy. To address the inconsistent expression of global and local features when processing diabetic retinopathy images, a dual-branch parallel model combining ResNet-50 and DeiT-S is employed as the backbone architecture, and a feature fusion module is designed at the end of the network. Concurrently, a multi-scale location awareness enhancement module is developed to extract multi-scale information through dilated convolution with positional attention mechanism for enhancing the feature representation of lesions in fundus images, and a local feature enhancement module is constructed to strengthen the models capability in extracting local information, thus improving models capability to identify small lesions and minor changes. The experimental results show that the proposed multi-layer feature attention enhanced network achieves an accuracy of 87.61%, exhibiting excellent classification performance. This advancement provides a strong support for further development of diabetic retinopathy detection technology.

相似文献/References:

[1]张育,赵轶峰,苏卓彬,等.基于卷积神经网络的胃癌癌前病变图像分类方法[J].中国医学物理学杂志,2022,39(2):209.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.014]
　ZHANG Yu,ZHAO Yifeng,SU Zhuobin,et al.Image classification of gastric precancerous lesions based on convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(9):209.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.014]
[2]蒋杰伟,雷舒陶,耿苗苗,等.融合可解释性特征的糖尿病视网膜病变自动诊断[J].中国医学物理学杂志,2022,39(5):640.[doi:DOI:10.3969/j.issn.1005-202X.2022.05.020]
　JIANG Jiewei,LEI Shutao,GENG Miaomiao,et al.Automatic diagnosis of diabetic retinopathy based on interpretable features fusion[J].Chinese Journal of Medical Physics,2022,39(9):640.[doi:DOI:10.3969/j.issn.1005-202X.2022.05.020]
[3]申思源,罗冬梅.糖尿病视网膜病变的风险揭示与关键因素分析[J].中国医学物理学杂志,2022,39(6):783.[doi:DOI:10.3969/j.issn.1005-202X.2022.06.021]
　SHEN Siyuan,LUO Dongmei.Risk disclosure and key factors analysis of diabetic retinopathy[J].Chinese Journal of Medical Physics,2022,39(9):783.[doi:DOI:10.3969/j.issn.1005-202X.2022.06.021]
[4]孙晓晗,孔祥勇,吴滢,等.基于卷积神经网络的肾小球病理图像分类算法[J].中国医学物理学杂志,2022,39(10):1313.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.023]
　SUN Xiaohan,KONG Xiangyong,WU Ying,et al.Glomerular pathological image classification algorithm based on convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(9):1313.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.023]
[5]杨东旭,赵红东,耿立新,等.双线性非局部特征结合中继监督网络用于视网膜血管分割[J].中国医学物理学杂志,2022,39(12):1516.[doi:DOI:10.3969/j.issn.1005-202X.2022.12.010]
　YANG Dongxu,ZHAO Hongdong,GENG Lixin,et al.Bilinear non-local features combined with intermediate supervision network for retinal vessel segmentation[J].Chinese Journal of Medical Physics,2022,39(9):1516.[doi:DOI:10.3969/j.issn.1005-202X.2022.12.010]
[6]王怡伟,李晓兵,聂生东,等.基于深度学习的超声多模态乳腺肿块良恶性分类[J].中国医学物理学杂志,2023,40(8):988.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.011]
　WANG Yiwei,LI Xiaobing,NIE Shengdong,et al.Deep learning-based classification for benign and malignant breast masses using multimodal ultrasound images[J].Chinese Journal of Medical Physics,2023,40(9):988.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.011]
[7]曹佳悦,罗冬梅.基于Null Importance与GS-LGBM的糖尿病视网膜病变因素分析与风险预测[J].中国医学物理学杂志,2023,40(8):1033.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.018]
　CAO Jiayue,LUO Dongmei.Risk factors analysis and prediction of diabetic retinopathy based on Null Importance and GS-LGBM[J].Chinese Journal of Medical Physics,2023,40(9):1033.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.018]
[8]张子宇,赵可辉,牛慧芳,等.基于轻量级RG-DenseNet的COVID-19 CT图像分类[J].中国医学物理学杂志,2023,40(12):1494.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.007]
　ZHANG Ziyu,ZHAO Kehui,NIU Huifang,et al.COVID-19 classification on CT image using lightweight RG DenseNet[J].Chinese Journal of Medical Physics,2023,40(9):1494.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.007]
[9]王志鲁,池越,周亚同,等.融合密集空洞注意力金字塔和多尺度的视网膜病变分割[J].中国医学物理学杂志,2024,41(8):1000.[doi:DOI:10.3969/j.issn.1005-202X.2024.08.013]
　WANG Zhilu,CHI Yue,ZHOU Yatong,et al.Diabetic retinopathy segmentation using dense dilated attention pyramid and multi-scale features[J].Chinese Journal of Medical Physics,2024,41(9):1000.[doi:DOI:10.3969/j.issn.1005-202X.2024.08.013]
[10]张颖,赵祺旸,郗群.基于深度融合网络研究糖尿病视网膜病变[J].中国医学物理学杂志,2025,42(3):347.[doi:10.3969/j.issn.1005-202X.2025.03.010]
　ZHANG Ying,ZHAO Qiyang,XI Qun.Diabetic retinopathy research based on deep converged network[J].Chinese Journal of Medical Physics,2025,42(9):347.[doi:10.3969/j.issn.1005-202X.2025.03.010]
[11]王文静,张莉钏,王欣,等.融合改进Retinex图像增强与深度学习的糖尿病视网膜分类检测方法[J].中国医学物理学杂志,2024,41(9):1086.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.005]
　WANG Wenjing,ZHANG Lichuan,WANG Xin,et al.Classification and detection method for diabetic retinopathy based on the combination of improved Retinex image enhancement and deep learning[J].Chinese Journal of Medical Physics,2024,41(9):1086.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.005]

备注/Memo

备注/Memo:
【收稿日期】2025-03-11 【基金项目】青岛市科技惠民示范项目（23-2-8-smjk-20-nsh） 【作者简介】梁冰雪，硕士，研究方向：医学图像处理、智慧医疗，E-mail: lbx_1209@163.com 【通信作者】秦玉华，博士，教授，研究方向：人工智能及应用、数据挖掘与分析，E-mail: yqin@qust.edu.cn
更新日期/Last Update: 2025-09-30