检索结果-南通市图书馆

Mixed-decomposed convolutional network:A lightweight yet efficient convolutional neural network for ocular disease recognition

引用

CAAI Transactions on Intelligence Technology 2024年第2期9卷 319-332页

作者： Xiaoqing Zhang Xiao Wu Zunjie Xiao Lingxi Hu Zhongxi Qiu Qingyang Sun Risa Higashita Jiang Liu Research institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhenChina Tomey Corporation NagoyaJapan Guangdong Provincial Key Laboratory of Brain‐inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhenChina Singapore eye Research institute SingaporeSingapore

eye health has become a global health concern and attracted broad *** the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseases efficiently and ***,most existing methods were dedicated to constructing sophisticated CNNs,inevitably ignoring the trade-off between performance and model *** alleviate this paradox,this paper proposes a lightweight yet efficient network architecture,mixeddecomposed convolutional network(MDNet),to recognise ocular *** MDNet,we introduce a novel mixed-decomposed depthwise convolution method,which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low-resolution and high-resolution patterns by using fewer computations and fewer *** conduct extensive experiments on the clinical anterior segment optical coherence tomography(AS-OCT),LAG,University of California San Diego,and CIFAR-100 *** results show our MDNet achieves a better trade-off between the performance and model complexity than efficient CNNs including MobileNets and ***,our MDNet outperforms MobileNets by 2.5%of accuracy by using 22%fewer parameters and 30%fewer computations on the AS-OCT dataset.

关键词： artificial intelligence deep learning deep neural networks image analysis image classification medical applications medical image processing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Pain perception enhancement in consecutive secondeye phacoemulsification cataract surgeries under topical anesthesia

引用

International Journal of Ophthalmology(English edition) 2024年第8期17卷 1510-1518页

作者： Jia-Wei Luo Yan-Hua Chen Jian-Feng Yu Yi-Xun Chen Min Ji Huai-Jin Guan eye institute Affiliated Hospital of Nantong UniversityMedical School of Nantong UniversityNantong 226001Jiangsu ProvinceChina Nantong Center for Disease Control and Prevention Nantong 226001Jiangsu ProvinceChina

Cataract is the main cause of visual impairment and blindness worldwide while the only effective cure for cataract is still *** phacoemulsification under topical anesthesia has been the routine procedure for cataract ***,patients often grumbled that they felt more painful during the second-eye surgery compared to the first-eye *** intraoperative pain experience has negative influence on satisfaction and willingness for second-eye cataract surgery of patients with bilateral *** ocular pain is a complicated process induced by the nociceptors activation in the peripheral nervous ***,neuropsychological,and pharmacological factors work together in the enhancement of intraoperative *** published literatures have focused on the pain enhancement during the secondeye phacoemulsification *** this review,we searched PubMed database for articles associated with pain perception differences between consecutive cataract surgeries published up to Feb.1,*** summarized the recent research progress in mechanisms and interventions for pain perception enhancement in consecutive secondeye phacoemulsification cataract *** review aimed to provide novel insights into strategies for improving patients’intraoperative experience in second-eye cataract surgeries.

关键词： ocular pain cataract surgery topical anesthesia intraoperative experience second-eye phacoemulsification

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Determination of the time of refractive stability after uneventful phacoemulsification in Indian eyes

引用

World Journal of Experimental Medicine 2024年第2期14卷 89-96页

作者： Ashok Kumar Nanda Bijnya Birajita Panda Asish Swain Logesh Balakrishnan Department of Ophthalmology Kar Vision Eye HospitalBhubaneswar 751013OdishaIndia Department of Ophthalmology All India Institute of Medical SciencesBhubaneswar 751019OdishaIndia Department of Optometry Kar Vision Eye HospitalBhubaneswar 751013OdishaIndia Department of Statistics Apollo HospitalsChennai 823104India

BACKGROUND Knowledge about refractive stabilization and the accuracy of postoperative refractive error measurements are crucial for improved patient outcomes after *** guidelines typically recommend waiting 4-6 wk before prescribing corrective *** research focused on identifying factors that influence refractive errors in the early stages of post-cataract surgery,thus contributing to the existing literature on this *** To investigate the time required for refraction stability after uneventful phacoemulsification *** We compared the variation and statistical significance of the difference in spherical,cylindrical components,and the spherical equivalent between the 1-and 6-wk follow-up period in a group of 257 eyes that underwent uneventful phacoemulsification with foldable intraocular lens implantation,all performed by a single experienced *** Wilcoxon-Signed Rank Test was utilized to assess the magnitude of the change and determine its statistical *** refractive stability was defined as the point at which the change in spherical equivalent was within±0.5 dioptres for two consecutive *** The average age of the patients was 64.9±8.9 *** differences observed in both the visits in spherical power(0.1±0.2),cylinder power(0.3±0.4),and spherical equivalent(0.2±0.2)were minimal and not statistically *** majority of eyes(93.4%)achieved refractive stability within 6 wk after the *** cylindrical power differed between age groups at the 6th wk post-operative and the difference was statistically significant(P value 0.013).There were no significant differences in refractive stability when considering sex and axial *** Phacoemulsification with foldable intraocular lens implantation results in no significant changes in refraction for the majority of cases during the 6-wk follow-up ***,a spectacle prescription can be given at the completion of 1 wk.

关键词： Cataract surgery Phacoemulsification Refraction stability Visual acuity Spherical equivalent

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Emerging insights into the function of very long chain fatty acids at cerebellar synapses

引用

Neural Regeneration Research 2025年第6期20卷 1709-1710页

作者： Martin-Paul Agbaga Mohiuddin Ahmad Department of Cell Biology and Ophthalmology University of Oklahoma Health Sciences Centerand Dean McGee Eye InstituteOklahoma CityOKUSA

Very long chain-saturated and-polyunsaturated fatty acids(VLC-SFA and VLC-PUFA, respectively) are a functionally important class of fatty acids containing 28 carbons or more in their acyl chain. They are synthesized by the elongation of very long fatty acids-4(ELOVL4) enzyme, expressed mainly in the brain, retina, skin, testes, and meibomian gland, where these fatty acids are found(Agbaga et al., 2008). Further, these organs exhibit tissuespecific VLC-PUFA and VLC-SFA biosynthesis and incorporation into complex lipids for specific functions. In the brain, skin, and Meibomian glands, the ELOVL4 mainly makes VLC-SFA, which are incorporated into complex sphingolipids. In the retina, the ELOVL4 makes VLC-PUFA that are incorporated into phosphatidylcholine, that are critical for visual function, while in testes and sperm, the VLC-PUFA are incorporated into sphingolipids that are critical for fertility(Yeboah et al., 2021).

关键词： functions function insight

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Ophthalmic exam and ophthalmology residents’ subspecialty preference

引用

International Journal of Ophthalmology(English edition) 2024年第2期17卷 359-364页

作者： Ari Leshno Daf Shalev Daphna Landau Prat Goldschleger eye institute Sheba Medical CenterTel Hashomer 5262000Israel Sackler Faculty of Medicine Tel Aviv UniversityTel Aviv 6997801Israel Department of Ophthalmology Edith Wolfson Medical CenterHolon 5822012Israel

AIM:To evaluate residents’perceptions and attitudes toward the various aspects of a comprehensive ophthalmic examination,and to determine if these factors correlate with their choices for fellowship and future career ***:This is a cross-sectional study.A questionnaire on the perception of the ophthalmic exam was sent via SurveyMonkey to ophthalmology residents throughout *** of them(one-half of all ophthalmology residents in 2019)completed *** first part related to how they perceived each component of the ophthalmic *** second part related to their future fellowship *** Chi-squared test was used to compare categorical variables and Student’s t-test and One-way ANOVA were used to compare continuous *** logistic regression analysis was applied as needed to detect interactions between variables and to exclude confounder ***:Slit-lamp examination of the anterior and posterior segments ranked as the most likeable aspects,whereas gonioscopy,ocular motility examination and visual acuity assessment were least *** segment and retina subspecialties were the ones most sought ***-nine respondents(61.3%)noted a direct correlation between their preferred parts of comprehensive ophthalmic evaluations and their choice of *** of selected components of those evaluations were significantly associated with responders’intentions to pursue anterior segment,retina,or oculoplastic fellowships(P<0.05).CONCLUSION:Perspectives of residents toward the ophthalmic examination,and most specifically its individual components,play an important role in their choice of subspecialty training.

关键词： residency subspecialty ophthalmic examination career choice ophthalmology

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

PVR update:pathophysiology and clinical management

引用

International Journal of Ophthalmology(English edition) 2024年第9期17卷 1577-1580页

作者： Peter Wiedemann Yan-Nian Hui Medical Faculty Leipzig UniversityLeipzig 04103Germany Department of Ophthalmology Eye Institute of Chinese PLAXijing HospitalFourth Military Medical UniversityXi’an 710032Shaanxi ProvinceChina

Wound-healing diseases present complex challenges,and proliferative vitreoretinopathy(PVR)has been a problem in the surgical retina for *** is a prolonged and abnormal healing response to retinal injury,such as primary retinal detachment(RD)or post-RD surgery,characterized by the formation of pre/subretinal membranes,retinal gliosis and shortening,retinal pigment epithelium cell(RPE)proliferation,and increased activity of glial cells(mainly Müller cells).

关键词： healing epithelium diseases

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent diagnostic model for pterygium by combining attention mechanism and MobileNetV2

引用

International Journal of Ophthalmology(English edition) 2024年第7期17卷 1184-1192页

作者： Mao-Nian Wu Kai He Yi-Bei Yu Bo Zheng Shao-Jun Zhu Xiang-Qian Hong Wen-Qun Xi Zhe Zhang School of Information Engineering Huzhou UniversityHuzhou 313000Zhejiang ProvinceChina Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources Huzhou UniversityHuzhou 313000Zhejiang ProvinceChina School of Mathematical Information Shaoxing UniversityShaoxing 312000Zhejiang ProvinceChina Shenzhen eye institute Shenzhen Eye HospitalJinan UniversityShenzhen 518040Guangdong ProvinceChina

AIM:To evaluate the application of an intelligent diagnostic model for ***:For intelligent diagnosis of pterygium,the attention mechanisms—SENet,ECANet,CBAM,and Self-Attention—were fused with the lightweight MobileNetV2 model structure to construct a tri-classification *** study used 1220 images of three types of anterior ocular segments of the pterygium provided by the eye Hospital of Nanjing Medical *** classification models—VGG16,ResNet50,MobileNetV2,and EfficientNetB7—were trained on the same dataset for *** evaluate model performance in terms of accuracy,Kappa value,test time,sensitivity,specificity,the area under curve(AUC),and visual heat map,470 test images of the anterior segment of the pterygium were ***:The accuracy of the MobileNetV2+Self-Attention model with 281 MB in model size was 92.77%,and the Kappa value of the model was 88.92%.The testing time using the model was 9ms/image in the server and 138ms/image in the local *** sensitivity,specificity,and AUC for the diagnosis of pterygium using normal anterior segment images were 99.47%,100%,and 100%,respectively;using anterior segment images in the observation period were 88.30%,95.32%,and 96.70%,respectively;and using the anterior segment images in the surgery period were 88.18%,94.44%,and 97.30%,***:The developed model is lightweight and can be used not only for detection but also for assessing the severity of pterygium.

关键词： deep learning attention mechanism pterygium intelligent diagnosis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

MCSTransWnet:A new deep learning process for postoperative corneal topography prediction based on raw multimodal data from the Pentacam HR system

引用

Medicine in Novel Technology and Devices 2024年第1期21卷 53-63页

作者： Nan Cheng Zhe Zhang Jing Pan Xiao-Na Li Wei-Yi Chen Guang-Hua Zhang Wei-Hua Yang College of Biomedical Engineering Taiyuan University of TechnologyTaiyuan 030600ShanxiChina Shenzhen eye Hospital Jinan UniversityShenzhen Eye InstituteShenzhen 518040GuangdongChina Department of Intelligence and Automation Taiyuan UniversityTaiyuan 030032ShanxiChina Graphics and Imaging Laboratory University of GironaGirona 17004Spain

This work provides a new multimodal fusion generative adversarial net(GAN)model,Multiple Conditions Transform W-net(MCSTransWnet),which primarily uses femtosecond laser arcuate keratotomy surgical parameters and preoperative corneal topography to predict postoperative corneal topography in astigmatism-corrected *** MCSTransWnet model comprises a generator and a discriminator,and the generator is composed of two *** first sub-generator extracts features using the U-net model,vision transform(ViT)and a multi-parameter conditional module branch.The second sub-generator uses a U-net network for further image *** discriminator uses the pixel discriminator in ***,most GAN models are convolutional neural networks;however,due to their feature extraction locality,it is difficult to comprehend the relationships among global ***,we added a vision Transform network as the model branch to extract the global *** is normally difficult to train the transformer,and image noise and geometric information loss are ***,we adopted the standard U-net fusion scheme and transform network as the generator,so that global features,local features,and rich image details could be obtained *** experimental results clearly demonstrate that MCSTransWnet successfully predicts postoperative corneal topographies(structural similarity=0.765,peak signal-to-noise ratio=16.012,and Fréchet inception distance=9.264).Using this technique to obtain the rough shape of the postoperative corneal topography in advance gives clinicians more references and guides changes to surgical planning and improves the success rate of surgery.

关键词： Deep learning Generative adversarial networks Corneal topography Transformer W-net U-net Medical imaging Multimodal fusion

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in teleophthalmology and artificial intelligence for diabetic retinopathy screening:a narrative review

引用

Annals of eye Science 2024年第2期9卷 24-37页

作者： Tanvi Chokshi Maria Jessica Cruz Jonathon Ross Glenn Yiu Tschannen eye institute Department of OphthalmologyUniversity of CaliforniaDavis HealthSacramentoCAUSA Department of Research College of MedicineCalifornia Northstate UniversityElk GroveCAUSA

Background and Objective:Advances in teleophthalmology and artificial intelligence(AI)for diabetic retinal screening is of growing public health ***,only 30–40%of patients with diabetes adhere to recommended diabetes screening *** enhance early detection and reduce vision threatening complications,there has been a growing number of teleophthalmology programs and novel AI algorithms with the aim to improve eye care *** purpose of this review is to assess current literature on teleophthalmology and AI for use in diabetic retinopathy(DR)screening,and to discuss advances and barriers to these innovative ***:Literature review involving teleophthalmology and AI for DR screening,with focus on the past *** Content and Findings:Teleophthalmology has demonstrated the ability to increase DR screening rates,enable earlier eye care access,and reduce healthcare *** AI-based DR screening programs appear accurate and effective,but detection of other ocular pathologies is still under development and not yet approved in the United ***,technological,financial,and legal barriers limit widespread adoption and long-term sustainability of teleophthalmology ***:The use of teleophthalmology and AI algorithms expands eye care access and helps prevent vision loss from DR and potentially other sight threatening *** in the process utilized for arriving at a particular diagnosis or decision to refer,often referred to as the“black box”,remains a multifaceted issue within the field of telemedicine for developing trust and improving patient-centered outcomes.

关键词： Teleophthalmology artificial intelligence(AI) diabetic retinopathy(DR) screening public health

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Automated detection of myopic maculopathy from color fundus photographs using deep convolutional neural networks

引用

eye and Vision 2024年第4期10卷 11-22页

作者： Jun Li Lilong Wang Yan Gao Qianqian Liang Lingzhi Chen Xiaolei Sun Huaqiang Yang Zhongfang Zhao Lina Meng Shuyue Xue Qing Du zhichun Zhang Chuanfeng LV Haifeng Xu Zhen Guo Guotong Xie Lixin Xie Qingdao eye Hospital of Shandong First Medical University 5 Yanerdao RoadQingdao 266071China State Key Laboratory Cultivation Base Shandong Provincial Key Laboratory of OphthalmologyShandong Eye InstituteShandong First Medical University&Shandong Academy of Medical SciencesQingdao 266071China Ping An Healthcare Technology 9F Building BPingAn IFCNo.1-3 Xinyuan South RoadBejing 100027China Shandong eye Hospital of Shandong First Medical University Jinan 250021China Rongcheng eye Hospital Weihai 264200China Hospital of PLA Navy Qingdao 266071China Qilu Hospital of Shandong University(Qingdao) Qingdao 266035China Ping An Healthcare and Technology Company Limited hanghai 200030China ping An International Smart City Technology Company Limited Shenzhen 518000China.

Background:Myopic maculopathy(MM)has become a major cause of visual impairment and blindness worldwide,especially in East Asian *** learning approaches such as deep convolutional neural networks(DCNN)have been successfully applied to identify some common retinal diseases and show great potential for the intelligent analysis of *** study aimed to build a reliable approach for automated detection of MM from retinal fundus images using DCNN ***:A dual-stream DCNN(DCNN-DS)model that perceives features from both original images and corresponding processed images by color histogram distribution optimization method was designed for classification of no MM,tessellated fundus(TF),and pathologic myopia(PM).A total of 36,515 gradable images from four hospitals were used for DCNN model development,and 14,986 gradable images from the other two hospitals for external *** also compared the performance of the DCNN-DS model and four ophthalmologists on 3000 randomly sampledfundus ***:The DCNN-DS model achieved sensitivities of 93.3%and 91.0%,specificities of 99.6%and 98.7%,areas under the receiver operating characteristic curves(AUCs)of 0.998 and 0.994 for detecting PM,whereas sensitivities of 98.8%and 92.8%,specificities of 95.6%and 94.1%,AUCs of 0.986 and 0.970 for detecting TF in two external testing *** the sampled testing dataset,the sensitivities of four ophthalmologists ranged from 88.3%to 95.8%and 81.1%to 89.1%,and the specificities ranged from 95.9%to 99.2%and 77.8%to 97.3%for detecting PM and TF,***,the DCNN-DS model achieved sensitivities of 90.8%and 97.9%and specificities of 99.1%and 94.0%for detecting PMand T,***:The proposed DCNN-DS approach demonstrated reliable performance with high sensitivity,specificity,and AUC to classify different MM levels on fundus photographs sourced from *** can help identify MM automatically among the large myopic groups and show great potenti

关键词： Myopic maculopathy Tessellated fundus Pathologic myopia Deep convolutional neural network Color fundus image

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：