检索结果-南通市图书馆

Automatic diagnosis of diabetic retinopathy using vision transformer based on wide-field optical coherence tomography angiography

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2024年第2期17卷 35-44页

作者： Zenan Zhou Huanhuan Yu Jiaqing Zhao Xiangning Wang Qiang Wu cuixia dai Shanghai Institute of Technology Shanghai P.R.China Shanghai Sixth People'sHospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai P.R.China

Diabetic retinopathy(DR)is one of the major causes of visual impairment in adults with *** coherence tomography angiography(OCTA)is nowadays widely used as the golden criterion for diagnosing ***,wide-field OCTA(WF-OCTA)provided more abundant information including that of the peripheral retinal degenerative changes and it can contribute in accurately diagnosing *** need for an automatic DR diagnostic system based on WF-OCTA pictures attracts more and more attention due to the large diabetic population and the prevalence of retinopathy *** this study,automatic diagnosis of DR using vision transformer was performed using WF-OCTA images(12 mm×12 mm single-scan)centered on the fovea as the ***-OCTA images were automatically classified into four classes:No DR,mild nonproliferative diabetic retinopathy(NPDR),moderate to severe NPDR,and proliferative diabetic retinopathy(PDR).The proposed method for detecting DR on the test set achieves accuracy of 99.55%,sensitivity of 99.49%,and specificity of 99.57%.The accuracy of the method for DR staging reaches up to 99.20%,which has been proven to be higher than that attained by classical convolutional neural network *** show that the automatic diagnosis of DR based on vision transformer and WF-OCTA pictures is more effective for detecting and staging DR.

关键词： Wide field optical coherence tomography angiography diabetic retinopathy vision transformer image classification

Computer-aided diagnosis of retinopathy based on vision transformer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2022年第2期15卷 49-57页

作者： Zhencun Jiang Lingyang Wang Qixin Wu Yilei Shao Meixiao Shen Wenping Jiang cuixia dai Shanghai Institute of Technology 100 Haiquan Road Shanghai 201418China School of Ophthalmology and Optometry Wenzhou Medical University Xueyuan Road 270 WenzhouZhejiang 325027China

Age-related Macular Degeneration(AMD)and Diabetic Macular Edema(DME)are two com-mon retinal diseases for elder people that may ultimately cause irreversible *** and accurate diagnosis is essential for the treatment of these *** recent years,computer-aided diagnosis(CAD)has been deeply investigated and effectively used for rapid and early *** this paper,we proposed a method of CAD using vision transformer to analyze optical co-herence tomography(OCT)images and to automatically discriminate AMD,DME,and normal eyes.A classification accuracy of 99.69%was *** the model pruning,the recognition time reached 0.010 s and the classification accuracy did not *** with the Con-volutional Neural Network(CNN)image classification models(VGG16,Resnet50,Densenet121,and EfficientNet),vision transformer after pruning exhibited better recognition *** show that vision transformer is an improved alternative to diagnose retinal diseases more accurately.

关键词： Vision transformer OCT image classi¯cation retinopathy computer-aided diagnosis model pruning

In vivo evaluation of laser-induced choroidal neovascularization in rats simultaneously using optical coherence tomography and photoacoustic microscopy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2021年第3期4卷 19-27页

作者： Fengxian Du Lei Gao Lin Li Qian Li Fenghua Wang Chuanqing Zhou cuixia dai Shanghai Institute of Technology ShanghaiP.R.China Shanghai Jiaotong University ShanghaiP.R.China

Determination of the precise location and the degree of the Choroidal neovascularization(CNV)lesion is essential for diagnosation Neovascular age-related macular degeneration(AMD)and evaluation the efficacy of *** imaging techniques with specific contrast for CNV evaluation are *** this paper,two noninvasive imaging techniques,namely Optical coherence tomography(OCT)and Photoacoustic microscopy(PAM),are combined to provide specific detection of CNV for their complimentary contrast *** vivo time-serial evaluation of Laser-induced CNV in rats is present at days 1,3,5,7,14,21 after laser photocoagulation is applied to the rat *** OCT and PAM show that the CNV increases to its maximum at day 7 and decreases at day *** of CNV area and CNV thickness is *** dual-modal information of CNV is consistent with the histologic evaluation by hematoxylin and eosin(H&E)staining.

关键词： Optical coherence tomography photoacoustic microscopy medical and biological imaging

Multi-class classification of pathological myopia based on fundus photography

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2024年第6期17卷 125-136页

作者： Jiaqing Zhao Guogang Cao Jiangnan He cuixia dai Shanghai Institute of Technology No.100 Haiquan RoadFengxian DistrictShanghaiP.R.China Shanghai Eye Diseases Prevention&Treatment Center Shanghai Eye HospitalSchool of MedicineTongji UniversityShanghai 200331P.R.China

Pathological myopia(PM)is a severe ocular disease leading to *** a traditional noninvasive diagnostic method,fundus color photography(FCP)is widely used in detecting PM due to its highfidelity and ***,manual examination of fundus photographs for PM is time-consuming and prone to high error *** automated detection technologies have yet to study the detailed classification in diagnosing different stages of PM *** this paper,we proposed an intelligent system which utilized Resnet101 technology to multi-categorically diagnose PM by classifying FCPs with different stages of *** system subdivided different stages of PM into eight subcategories,aiming to enhance the precision and efficiency of the diagnostic *** achieved an average accuracy rate of 98.86%in detection of PM,with an area under the curve(AUC)of 98.96%.For the eight subcategories of PM,the detection accuracy reached 99.63%,with an AUC of 99.98%.Compared with other widely used multi-class models such as VGG16,Vision Transformer(VIT),EfficientNet,this system demonstrates higher accuracy and *** artificial intelligence system is designed to be easily integrated into existing clinical diagnostic tools,providing an efficient solution for large-scale PM screening.

关键词： Fundus color photography pathological myopia deep learning Resnet101.

采用紫外光提高双掺杂铌酸锂晶体中全息记录的灵敏度和光栅强度

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

光学学报 2005年第12期25卷 1600-1605页

作者：戴翠霞刘立人刘德安柴志方周煜中国科学院上海光学精密机械研究所上海201800

提出了一种在双掺杂铌酸锂晶体中用调制的双紫外光进行非挥发全息记录的方法。与通常的用紫外光敏化的非挥发全息记录相比,这种方法可以大幅度地提高光栅强度和记录灵敏度。联立双中心物质方程和双光束耦合波方程,数值分析了光栅强度和... 详细信息

提出了一种在双掺杂铌酸锂晶体中用调制的双紫外光进行非挥发全息记录的方法。与通常的用紫外光敏化的非挥发全息记录相比,这种方法可以大幅度地提高光栅强度和记录灵敏度。联立双中心物质方程和双光束耦合波方程,数值分析了光栅强度和衍射效率随时间的变化并讨论了掺杂浓度和记录光强对紫外光非挥发全息记录机制下光折变效应的影响。研究发现,紫外光记录得到的深浅中心的光栅具有相同的相位,总的光栅(深浅中心光栅的叠加)强度为两光栅强度之和,固定过程中深中心的光栅得到增强;增大深浅中心掺杂的浓度可以提高光栅强度,增大记录紫外光的光强可以增加光栅的强度和记录灵敏度。理论模拟可以证实并预测实验结果。

关键词：全息非挥发全息记录紫外光记录双掺杂铌酸锂晶体灵敏度

LiNbO_3∶Ce∶Cu晶体中绿光非挥发全息记录优化

在线全文

学校读者我要写书评

暂无评论

中国激光 2008年第7期35卷 1045-1049页

作者：戴翠霞于瀛洁刘德安刘立人上海大学机械自动化学院精密机械工程系上海200072 中国科学院上海光学精密机械研究所信息光学实验室上海201800

为了对在LiNbO3∶Ce∶Cu晶体中绿光作为记录光的非挥发全息记录进行优化,联立求解了双中心物质方程和双光束耦合波方程,数值分析了平均空间电荷场(SCF)和衍射效率随晶体的氧化还原态、记录光与敏化光的光强比以及深浅中心的掺杂浓度的... 详细信息

为了对在LiNbO3∶Ce∶Cu晶体中绿光作为记录光的非挥发全息记录进行优化,联立求解了双中心物质方程和双光束耦合波方程,数值分析了平均空间电荷场(SCF)和衍射效率随晶体的氧化还原态、记录光与敏化光的光强比以及深浅中心的掺杂浓度的变化。结果表明,采用绿光作为记录光在LiNbO3∶Ce∶Cu晶体中进行非挥发全息记录,可以记录得到强光折变光栅,其空间电荷场高达107V/m;获得高达80%以上的固定衍射效率,各相关参量都有较大的优化空间。

关键词：全息非挥发全息记录光折变光栅 LiNbO3:Ce:Cu晶体衍射效率

SAU-Net:融合压缩注意力机制的多器官图像分割

在线全文

学校读者我要写书评

暂无评论

激光与光电子学进展 2022年第4期59卷 355-364页

作者：曹国刚毛红东张术陈颖戴翠霞上海应用技术大学计算机科学与信息工程学院上海201418 上海应用技术大学理学院上海201418

为了对头颈部多器官CT图像实现精准分割,减少放射治疗对人体正常组织的损伤,本文提出一种基于卷积神经网络的图像分割方法——SAU-Net算法,该算法基于加入残差连接的3D U-Net实现。针对器官尺寸差异较大而引起的分割精度不准确问题,引... 详细信息

为了对头颈部多器官CT图像实现精准分割,减少放射治疗对人体正常组织的损伤,本文提出一种基于卷积神经网络的图像分割方法——SAU-Net算法,该算法基于加入残差连接的3D U-Net实现。针对器官尺寸差异较大而引起的分割精度不准确问题,引入压缩注意力模块,通过非局部的空间注意力机制增加对全局特征的编码能力,聚合多尺度上下文信息,实现同一器官的体素分组。此外,该算法减少了卷积核数量及参数量,避免因额外的卷积运算造成堆叠局部信息过多而影响模型性能。结果表明,以Dice系数为评估指标,与3D U-Net和3D ResUNet算法相比,SAU-Net的分割精度分别提高了13.7%和8.2%,推理速度比FocusNetv2提升73%。SAU-Net算法显著提高了头颈部器官图像的分割精度和速度,能够快速准确实现全自动分割任务。

关键词：图像处理卷积神经网络 3D U-Net 残差连接压缩注意力

在线全文

学校读者我要写书评

暂无评论

光折变空间光孤子

激光与光电子学进展 2005年第9期42卷 17-21页

作者：戴翠霞刘立人刘德安中国科学院上海光学精密机械研究所信息光学实验室上海201800

回顾了光折变孤子的相关研究及最新进展,描述了光折变孤子的形成及特性,分析了光折变孤子形成的理论机理,展示了光折变孤子的相互作用,说明了光折变孤子的应用价值及缺陷。

关键词：光折变孤子光折变效应空间孤子空间光孤子光折变相互作用

在线全文

学校读者我要写书评

暂无评论

光折变相干散射噪声

激光与光电子学进展 2005年第10期42卷 14-17页

作者：戴翠霞刘立人刘德安中国科学院上海光学精密机械研究所信息光学实验室上海201800

全面介绍了光折变相干散射噪声的研究状况,描述并分析了形成散射噪声的必要条件及理论机制,说明了散射噪声的观测技术及评价标准;总结了抑制噪声的各种方案及噪声的相关应用,最后展望了光折变散射噪声的研究前景。

关键词：光折变效应散射噪声相干放大散射源光折变相干理论机制必要条件评价标准观测技术