详细信息
文献类型:期刊文献
中文题名:基于深度融合网络研究糖尿病视网膜病变
英文题名:Diabetic retinopathy research based on deep converged network
作者:张颖[1];赵祺旸[1];郗群[2]
第一作者:张颖
机构:[1]甘肃中医药大学信息工程学院,甘肃兰州730000;[2]兰州大学第二医院信息中心,甘肃兰州730000
第一机构:甘肃中医药大学信息工程学院(教育技术中心)
年份:2025
卷号:42
期号:3
起止页码:347
中文期刊名:中国医学物理学杂志
外文期刊名:Chinese Journal of Medical Physics
基金:甘肃省自然科学基金(20CX9JA145);兰州市科技计划项目(2023-4-36)。
语种:中文
中文关键词:糖尿病视网膜病变;深度学习;深度残差收缩网络;金字塔分割注意力模块
外文关键词:diabetic retinopathy;deep learning;deep residual shrinkage network;pyramid split attention module
摘要:基于深度学习提出一种融合网络,旨在高效、准确地辅助诊断糖尿病性视网膜病。采用数据增强技术与生成对抗网络相结合的手段,对EyePACS数据集内的眼底图像实施扩充操作,有效应对眼底图像分类不均衡的难题。使用Inception-Resnet-V2作为主网络,并融入深度残差收缩网络和金字塔分割注意力模块,有效地过滤掉特征学习过程中的无关信息,聚焦病灶信息,提高网络对重要特征的抓取能力。实验结果显示该优化模型能在无需事先指明病变特征的情况下,准确率、召回率、特异性、灵敏度以及F1分数达到0.951、0.950、0.990、0.950、0.950,表明本文模型在评价指标上都有较好的性能。
A converged network based on deep learning is proposed to realize the efficient and accurate diagnosis of diabetic retinopathy.Both data augmentation technology and generative adversarial network are used to augment the fundus images in EyePACS dataset for effectively addressing the problem of uneven classification of fundus images.The proposed model uses Inception-Resnet-V2 as the main network,and incorporates deep residual shrinkage network and pyramid split attention module for effectively filtering out the irrelevant information in the feature learning process and focusing on the lesion information,thereby improving the network's ability to capture important features.Experimental results show that the optimized model achieves accuracy,recall,specificity,sensitivity,and F1 score of 0.951,0.950,0.990,0.950,and 0.950,respectively,without the need to specify lesion characteristics in advance,demonstrating its superiority in evaluation indicators.
参考文献:
正在载入数据...