Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy

Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually det...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Microscopy research and technique Jg. 86; H. 11; S. 1443 - 1460
Hauptverfasser:	Manan, Malik Abdul, Jinchao, Feng, Khan, Tariq M., Yaqub, Muhammad, Ahmed, Shahzad, Chuhan, Imran shabir
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States Wiley Subscription Services, Inc 01.11.2023
Schlagworte:	Accuracy Artificial neural networks Benchmarks Blood vessels Coders Computer architecture Deep learning Diabetes Diabetes mellitus Diabetic retinopathy Diagnosis Edema Exudates Exudation Health services Image contrast Image processing Image segmentation Lesions Machine learning Medical imaging Neural networks Ophthalmology Parameters Performance enhancement Retina Retinal images Retinopathy Screening Semantic segmentation Semantics Vision retinal image data augmentation exudates residual network semantic segmentation diabetic retinopathy convolution neural network
ISSN:	1059-910X, 1097-0029, 1097-0029
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer-assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E-ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively. RESEARCH HIGHLIGHTS: The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time-consuming and requires intense effort. The authors compare qualitative results of the state-of-the-art convolutional neural network (CNN) architectures and propose a computer-assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening.
AbstractList	Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer-assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E-ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively. RESEARCH HIGHLIGHTS: The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time-consuming and requires intense effort. The authors compare qualitative results of the state-of-the-art convolutional neural network (CNN) architectures and propose a computer-assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening.Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer-assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E-ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively. RESEARCH HIGHLIGHTS: The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time-consuming and requires intense effort. The authors compare qualitative results of the state-of-the-art convolutional neural network (CNN) architectures and propose a computer-assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening. Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer-assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E-ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively. RESEARCH HIGHLIGHTS: The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time-consuming and requires intense effort. The authors compare qualitative results of the state-of-the-art convolutional neural network (CNN) architectures and propose a computer-assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening. Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time‐consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer‐assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E‐ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively.Research HighlightsThe research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina.Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment.Currently, manual detection is time‐consuming and requires intense effort.The authors compare qualitative results of the state‐of‐the‐art convolutional neural network (CNN) architectures and propose a computer‐assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters.The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening.
Author	Chuhan, Imran shabir Yaqub, Muhammad Jinchao, Feng Khan, Tariq M. Manan, Malik Abdul Ahmed, Shahzad
Author_xml	– sequence: 1 givenname: Malik Abdul surname: Manan fullname: Manan, Malik Abdul organization: Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology Beijing University of Technology Beijing China – sequence: 2 givenname: Feng orcidid: 0000-0001-5603-8874 surname: Jinchao fullname: Jinchao, Feng organization: Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology Beijing University of Technology Beijing China – sequence: 3 givenname: Tariq M. surname: Khan fullname: Khan, Tariq M. organization: School of IT, Deakin University Waurn Ponds Australia – sequence: 4 givenname: Muhammad surname: Yaqub fullname: Yaqub, Muhammad organization: Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology Beijing University of Technology Beijing China – sequence: 5 givenname: Shahzad surname: Ahmed fullname: Ahmed, Shahzad organization: Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology Beijing University of Technology Beijing China – sequence: 6 givenname: Imran shabir surname: Chuhan fullname: Chuhan, Imran shabir organization: Interdisciplinary Research Institute, Faculty of Science Beijing University of Technology Beijing China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37194727$$D View this record in MEDLINE/PubMed
BookMark	eNptkctq3TAQhkVJaS7tpg9QBN2EghNdLNtalpBeINBFU-hOjKVxooMtn0gyNLu-Q94wT1L5nGQTCgMzo_nmB81_TA7CHJCQ95ydccbE-QanfCZqWatX5Igz3VblVR-stdKV5uz3ITlOacMY54rXb8ihbLmuW9EekbufOEHI3tKENxOGDNnPgc4DjZh9gJHin8VBxkSX5MMNhTJI3i3rJNjZYXz8--BwV1GI9tZntHmJSH2gzkOPq_hObN5Cvr1_S14PMCZ895RPyK8vl9cX36qrH1-_X3y-qqzkKlcd8r5pBtULwB5LVzsnOEdgtulE3agauHQKusYqOyinhl4o0G3NtdSgQJ6Q073uNs53C6ZsJp8sjiMEnJdkRMfrEm0nC_rxBbqZl1g-v1KtZJpJwQv14Yla-gmd2UY_Qbw3z8csANsDNs4pRRyM9ft75gh-NJyZ1S-z-mV2fpWVTy9WnlX_A_8DKZmZJA
CitedBy_id	crossref_primary_10_1002_ima_70144 crossref_primary_10_1016_j_artmed_2025_103167
Cites_doi	10.1007/s10044-017-0661-4 10.1167/iovs.06-0996 10.1016/j.neucom.2018.10.103 10.1109/ACCESS.2019.2953259 10.1049/ipr2.12007 10.1109/JTEHM.2018.2835315 10.3390/photonics9120923 10.1109/ICCKE.2012.6395375 10.1016/j.media.2011.07.004 10.1109/IRI.2018.00074 10.1109/CVPR.2008.4587503 10.1109/EMBC.2018.8512354 10.1109/ACCESS.2018.2794463 10.1134/S0006350915020220 10.1046/j.1464-5491.2003.01085.x 10.5244/C.21.15 10.1016/j.ins.2017.08.050 10.1016/j.compeleceng.2021.107036 10.1007/s10439-009-9707-0 10.1109/IJCNN48605.2020.9207668 10.1109/TMI.2002.806290 10.1038/eye.1994.66 10.1109/EMBC.2012.6347349 10.1007/s10044-017-0630-y 10.1016/j.ins.2014.10.059 10.1016/j.medengphy.2007.04.010 10.1007/978-3-642-15561-1_31 10.1088/0031-9155/52/24/012 10.1016/j.media.2014.05.004 10.1364/BOE.9.004863 10.1016/j.compbiomed.2022.106277 10.1117/12.2293549 10.1109/CVPR.2016.90 10.1167/iovs.11-7275 10.1007/978-3-319-70093-9_76 10.1007/s10044-018-0696-1 10.1016/j.cmpb.2016.09.018 10.1016/j.eswa.2018.12.008 10.1016/j.cmpb.2014.01.010 10.1613/jair.953 10.1007/978-3-030-63820-7_18 10.1038/s41598-021-81539-3 10.1038/s41598-022-26482-7 10.3390/diagnostics11010114 10.1109/IVCNZ.2016.7804441 10.1109/DICTA52665.2021.9647320 10.1007/s11760-017-1114-7 10.1109/ACCESS.2020.2998635 10.1109/TBME.2003.820400 10.1109/CVPR.2015.7298965 10.1016/j.bspc.2021.103169 10.1109/IJCNN48605.2020.9207411 10.1016/j.irbm.2013.01.010 10.1016/j.bspc.2017.02.012 10.1016/j.ins.2019.06.011 10.1007/BF00920219
ContentType	Journal Article
Copyright	2023 Wiley Periodicals LLC.
Copyright_xml	– notice: 2023 Wiley Periodicals LLC.
DBID	AAYXX CITATION NPM 7QF 7QO 7QP 7QQ 7SC 7SE 7SP 7SR 7SS 7TA 7TB 7U5 7U7 8BQ 8FD C1K F28 FR3 H8D H8G JG9 JQ2 K9. KR7 L7M L~C L~D P64 RC3 7X8
DOI	10.1002/jemt.24345
DatabaseName	CrossRef PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Entomology Abstracts (Full archive) Materials Business File Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts Toxicology Abstracts METADEX Technology Research Database Environmental Sciences and Pollution Management ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Copper Technical Reference Library Materials Research Database ProQuest Computer Science Collection ProQuest Health & Medical Complete (Alumni) Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts Genetics Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Health & Medical Complete (Alumni) Materials Business File Environmental Sciences and Pollution Management Aerospace Database Copper Technical Reference Library Engineered Materials Abstracts Genetics Abstracts Biotechnology Research Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Toxicology Abstracts Electronics & Communications Abstracts Ceramic Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Entomology Abstracts Solid State and Superconductivity Abstracts Engineering Research Database Calcium & Calcified Tissue Abstracts Corrosion Abstracts MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic PubMed Materials Research Database
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	1097-0029
EndPage	1460
ExternalDocumentID	37194727 10_1002_jemt_24345
Genre	Journal Article
GrantInformation_xml	– fundername: National Science Foundation of China grantid: 82171992 – fundername: Beijing Laboratory of Advanced Information Networks
GroupedDBID	--- -~X .3N .55 .GA .GJ .Y3 05W 0R~ 10A 123 1L6 1OB 1OC 1ZS 31~ 33P 3SF 3WU 4.4 4ZD 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 53G 5VS 66C 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A03 AAESR AAEVG AAHQN AAMMB AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAYXX AAZKR ABCQN ABCUV ABEFU ABEML ABIJN ABJNI ABPVW ACAHQ ACBWZ ACCZN ACGFS ACIWK ACNCT ACPOU ACPRK ACRPL ACSCC ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN AEFGJ AEIGN AEIMD AENEX AETEA AEUYR AEYWJ AFBPY AFFPM AFGKR AFRAH AFWVQ AFZJQ AGHNM AGQPQ AGXDD AGYGG AHBTC AHMBA AIDQK AIDYY AIQQE AITYG AIURR AJXKR ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ATUGU AUFTA AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMNLL BMXJE BNHUX BQCPF BROTX BRXPI BY8 CITATION CS3 D-E D-F DCZOG DPXWK DR1 DR2 DRFUL DRSTM EBD EBS EJD EMOBN F00 F01 F04 F5P FEDTE G-S G.N GNP GODZA H.T H.X HBH HF~ HGLYW HHY HHZ HVGLF HZ~ IX1 J0M JPC KQQ LATKE LAW LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES M56 MEWTI MK4 MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 N9A NF~ NNB O66 O8X O9- OIG P2P P2W P2X P4D PALCI PQQKQ Q.N Q11 QB0 QRW R.K RIWAO ROL RX1 RYL SAMSI SUPJJ SV3 TWZ UB1 V2E W8V W99 WBKPD WHWMO WIB WIH WIK WJL WOHZO WQJ WVDHM WXSBR X7M XG1 XPP XV2 ZZTAW ~02 ~IA ~WT AAHHS ACCFJ AEEZP AEQDE AEUQT AFPWT AIWBW AJBDE NPM RWI RWR WRC 7QF 7QO 7QP 7QQ 7SC 7SE 7SP 7SR 7SS 7TA 7TB 7U5 7U7 8BQ 8FD C1K F28 FR3 H8D H8G JG9 JQ2 K9. KR7 L7M L~C L~D P64 RC3 7X8
ID	FETCH-LOGICAL-c315t-8e1b66f5b2aebe8e14dd211ea0c6824654a13d5a86c5cf5d5fb25a9741939a5a3
ISICitedReferencesCount	8
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000990979900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1059-910X 1097-0029
IngestDate	Thu Oct 02 05:19:05 EDT 2025 Sat Nov 29 14:43:58 EST 2025 Wed Feb 19 02:25:10 EST 2025 Sat Nov 29 07:02:30 EST 2025 Tue Nov 18 22:03:34 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	11
Keywords	retinal image data augmentation exudates residual network semantic segmentation diabetic retinopathy convolution neural network
Language	English
License	2023 Wiley Periodicals LLC.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c315t-8e1b66f5b2aebe8e14dd211ea0c6824654a13d5a86c5cf5d5fb25a9741939a5a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-5603-8874
PMID	37194727
PQID	2873090321
PQPubID	1016375
PageCount	18
ParticipantIDs	proquest_miscellaneous_2814814783 proquest_journals_2873090321 pubmed_primary_37194727 crossref_citationtrail_10_1002_jemt_24345 crossref_primary_10_1002_jemt_24345
PublicationCentury	2000
PublicationDate	2023-11-01
PublicationDateYYYYMMDD	2023-11-01
PublicationDate_xml	– month: 11 year: 2023 text: 2023-11-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	Microscopy research and technique
PublicationTitleAlternate	Microsc Res Tech
PublicationYear	2023
Publisher	Wiley Subscription Services, Inc
Publisher_xml	– name: Wiley Subscription Services, Inc
References	e_1_2_11_32_1 e_1_2_11_55_1 e_1_2_11_57_1 e_1_2_11_36_1 e_1_2_11_51_1 e_1_2_11_13_1 e_1_2_11_34_1 e_1_2_11_53_1 e_1_2_11_11_1 e_1_2_11_29_1 e_1_2_11_6_1 e_1_2_11_27_1 e_1_2_11_48_1 e_1_2_11_2_1 e_1_2_11_60_1 e_1_2_11_20_1 e_1_2_11_45_1 Khan T. M. (e_1_2_11_30_1) 2022 e_1_2_11_47_1 e_1_2_11_24_1 e_1_2_11_41_1 e_1_2_11_62_1 e_1_2_11_8_1 e_1_2_11_22_1 e_1_2_11_43_1 e_1_2_11_17_1 e_1_2_11_15_1 e_1_2_11_38_1 e_1_2_11_19_1 e_1_2_11_50_1 Bhawarkar Y. (e_1_2_11_4_1) 2022 e_1_2_11_10_1 Weeks J. E. (e_1_2_11_59_1) 1897; 8 e_1_2_11_31_1 e_1_2_11_56_1 e_1_2_11_58_1 e_1_2_11_14_1 e_1_2_11_35_1 e_1_2_11_52_1 e_1_2_11_12_1 e_1_2_11_54_1 e_1_2_11_7_1 e_1_2_11_28_1 e_1_2_11_5_1 e_1_2_11_26_1 e_1_2_11_3_1 e_1_2_11_49_1 Khan T. M. (e_1_2_11_33_1) 2021 e_1_2_11_61_1 e_1_2_11_21_1 e_1_2_11_44_1 e_1_2_11_46_1 e_1_2_11_25_1 e_1_2_11_40_1 e_1_2_11_9_1 e_1_2_11_23_1 e_1_2_11_42_1 e_1_2_11_18_1 e_1_2_11_16_1 e_1_2_11_37_1 e_1_2_11_39_1
References_xml	– ident: e_1_2_11_24_1 doi: 10.1007/s10044-017-0661-4 – ident: e_1_2_11_40_1 doi: 10.1167/iovs.06-0996 – ident: e_1_2_11_16_1 doi: 10.1016/j.neucom.2018.10.103 – ident: e_1_2_11_34_1 doi: 10.1109/ACCESS.2019.2953259 – ident: e_1_2_11_49_1 doi: 10.1049/ipr2.12007 – volume-title: Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) year: 2021 ident: e_1_2_11_33_1 – ident: e_1_2_11_3_1 doi: 10.1109/JTEHM.2018.2835315 – ident: e_1_2_11_21_1 doi: 10.3390/photonics9120923 – ident: e_1_2_11_9_1 doi: 10.1109/ICCKE.2012.6395375 – ident: e_1_2_11_15_1 doi: 10.1016/j.media.2011.07.004 – ident: e_1_2_11_58_1 doi: 10.1109/IRI.2018.00074 – ident: e_1_2_11_48_1 doi: 10.1109/CVPR.2008.4587503 – ident: e_1_2_11_6_1 doi: 10.1109/EMBC.2018.8512354 – ident: e_1_2_11_52_1 doi: 10.1109/ACCESS.2018.2794463 – ident: e_1_2_11_60_1 doi: 10.1134/S0006350915020220 – volume: 8 start-page: 158 year: 1897 ident: e_1_2_11_59_1 article-title: Retinitis proliferans publication-title: Transactions of the American Ophthalmological Society – ident: e_1_2_11_56_1 doi: 10.1046/j.1464-5491.2003.01085.x – ident: e_1_2_11_22_1 doi: 10.5244/C.21.15 – ident: e_1_2_11_54_1 doi: 10.1016/j.ins.2017.08.050 – ident: e_1_2_11_19_1 doi: 10.1016/j.compeleceng.2021.107036 – ident: e_1_2_11_14_1 doi: 10.1007/s10439-009-9707-0 – ident: e_1_2_11_31_1 doi: 10.1109/IJCNN48605.2020.9207668 – ident: e_1_2_11_57_1 doi: 10.1109/TMI.2002.806290 – ident: e_1_2_11_13_1 doi: 10.1038/eye.1994.66 – ident: e_1_2_11_17_1 doi: 10.1109/EMBC.2012.6347349 – volume-title: Fifth International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT) ident: e_1_2_11_46_1 – ident: e_1_2_11_50_1 doi: 10.1007/s10044-017-0630-y – ident: e_1_2_11_42_1 doi: 10.1016/j.ins.2014.10.059 – ident: e_1_2_11_47_1 doi: 10.1016/j.medengphy.2007.04.010 – ident: e_1_2_11_35_1 doi: 10.1007/978-3-642-15561-1_31 – ident: e_1_2_11_11_1 doi: 10.1088/0031-9155/52/24/012 – ident: e_1_2_11_61_1 doi: 10.1016/j.media.2014.05.004 – ident: e_1_2_11_62_1 doi: 10.1364/BOE.9.004863 – ident: e_1_2_11_20_1 doi: 10.1016/j.compbiomed.2022.106277 – ident: e_1_2_11_7_1 doi: 10.1117/12.2293549 – ident: e_1_2_11_18_1 doi: 10.1109/CVPR.2016.90 – volume-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision year: 2022 ident: e_1_2_11_30_1 – ident: e_1_2_11_55_1 doi: 10.1167/iovs.11-7275 – ident: e_1_2_11_10_1 doi: 10.1007/978-3-319-70093-9_76 – ident: e_1_2_11_25_1 doi: 10.1007/s10044-018-0696-1 – ident: e_1_2_11_44_1 doi: 10.1016/j.cmpb.2016.09.018 – ident: e_1_2_11_45_1 doi: 10.1016/j.eswa.2018.12.008 – ident: e_1_2_11_2_1 doi: 10.1016/j.cmpb.2014.01.010 – volume-title: ITM Web of Conferences year: 2022 ident: e_1_2_11_4_1 – ident: e_1_2_11_5_1 doi: 10.1613/jair.953 – ident: e_1_2_11_28_1 doi: 10.1007/978-3-030-63820-7_18 – ident: e_1_2_11_41_1 doi: 10.1038/s41598-021-81539-3 – ident: e_1_2_11_27_1 doi: 10.1038/s41598-022-26482-7 – ident: e_1_2_11_39_1 doi: 10.3390/diagnostics11010114 – ident: e_1_2_11_23_1 doi: 10.1109/IVCNZ.2016.7804441 – ident: e_1_2_11_29_1 doi: 10.1109/DICTA52665.2021.9647320 – ident: e_1_2_11_51_1 doi: 10.1007/s11760-017-1114-7 – ident: e_1_2_11_53_1 doi: 10.1109/ACCESS.2020.2998635 – ident: e_1_2_11_36_1 doi: 10.1109/TBME.2003.820400 – ident: e_1_2_11_38_1 doi: 10.1109/CVPR.2015.7298965 – ident: e_1_2_11_26_1 doi: 10.1016/j.bspc.2021.103169 – ident: e_1_2_11_32_1 doi: 10.1109/IJCNN48605.2020.9207411 – ident: e_1_2_11_8_1 doi: 10.1016/j.irbm.2013.01.010 – ident: e_1_2_11_12_1 doi: 10.1016/j.bspc.2017.02.012 – ident: e_1_2_11_37_1 doi: 10.1016/j.ins.2019.06.011 – ident: e_1_2_11_43_1 doi: 10.1007/BF00920219
SSID	ssj0011514
Score	2.4578001
Snippet	Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to...
SourceID	proquest pubmed crossref
SourceType	Aggregation Database Index Database Enrichment Source
StartPage	1443
SubjectTerms	Accuracy Artificial neural networks Benchmarks Blood vessels Coders Computer architecture Deep learning Diabetes Diabetes mellitus Diabetic retinopathy Diagnosis Edema Exudates Exudation Health services Image contrast Image processing Image segmentation Lesions Machine learning Medical imaging Neural networks Ophthalmology Parameters Performance enhancement Retina Retinal images Retinopathy Screening Semantic segmentation Semantics Vision
Title	Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy
URI	https://www.ncbi.nlm.nih.gov/pubmed/37194727 https://www.proquest.com/docview/2873090321 https://www.proquest.com/docview/2814814783
Volume	86
WOSCitedRecordID	wos000990979900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVWIB databaseName: Wiley Online Library - Journals customDbUrl: eissn: 1097-0029 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011514 issn: 1059-910X databaseCode: DRFUL dateStart: 19960101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1fb9MwELe6DSReEP8pjMkIhISiQGznj_M4wSaEuoGgk8pT5DjOWmjTdm2m7o3vwLfjkU_C2XHSVBpoPCBVUZNYjuL75c7n8_0OoedB5IeMyNRNAwUOCsm5m5LMd7kKw4wKRoU0ku5Fx8d8MIg_djo_61yY83FUFHy1imf_VdRwDYStU2f_QdxNp3AB_oPQ4Qhih-OVBP9ZTWC0RtJZqNOJzSwyc0Kdr6jnnmpVajd_4ZRmnUDAjUWVkqVJLTWhiN0AwTJlzp2NaIPePmsWbA35M3Q51VWNN6LDR3qXn853uXAsmVCVP9cQxq7Xwcejb85-mpVjsxGnQSqM6KnzflTIoZg2NmFoSymDez9fr-J-EfPSBJWOyqGYTETWXsigzGb0XV1dttQ0TApBTXuDyorZa5pX1rPrJ1a3W5pti2HS0tTgSLKW1QeD4V1qUSqG2q9qsnxFfVZRX27Sdh9_SA5Per2kfzDov5jNXV3RTEf-bXmXLbRDoyAGo7Hz9hM0bGJcpGKeb96lIc-lr9eP25wu_cEHMnOh_i100zoxeL8C323UUcUddL0qa3pxF81rCOI2BPE0xxaCuIYgNhDEAtcQxBaCv77_sODDbfDhUYFr8OEW-O6hk8OD_pt3ri3t4UpGgiWoApKGYR6kVIAWgTM_yyghSngy5FRz_AnCskDwUAYyD7IgT2kgwPcFfyMWgWD30XYxLdRDhD0_J7GOXsPk2k8554qTiEjB0tTPw5h00ct6BBNpee91-ZVxUjF200SPdmJGu4ueNW1nFdvLpa12a0Ek9sNfJJSDrYw9RuGBT5vboKt1AE4UalrqNsSHX8RZFz2oBNg8hkUk9sGZePT3zh-jG-tvZxdtL89K9QRdk-fL0eJsD21FA75ngfYbozjG4A
linkProvider	Wiley-Blackwell
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Semantic+segmentation+of+retinal+exudates+using+a+residual+encoder%E2%80%93decoder+architecture+in+diabetic+retinopathy&rft.jtitle=Microscopy+research+and+technique&rft.au=Malik+Abdul+Manan&rft.au=Feng+Jinchao&rft.au=Khan%2C+Tariq+M&rft.au=Yaqub%2C+Muhammad&rft.date=2023-11-01&rft.pub=Wiley+Subscription+Services%2C+Inc&rft.issn=1059-910X&rft.eissn=1097-0029&rft.volume=86&rft.issue=11&rft.spage=1443&rft.epage=1460&rft_id=info:doi/10.1002%2Fjemt.24345&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1059-910X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1059-910X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1059-910X&client=summon