Deep learning based digital cell profiles for risk stratification of urine cytology images

Urine cytology is a test for the detection of high‐grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of a...

Full description

Saved in:

Bibliographic Details
Published in:	Cytometry. Part A Vol. 99; no. 7; pp. 732 - 742
Main Authors:	Awan, Ruqayya, Benes, Ksenija, Azam, Ayesha, Song, Tzu‐Hsi, Shaban, Muhammad, Verrill, Clare, Tsang, Yee Wah, Snead, David, Minhas, Fayyaz, Rajpoot, Nasir
Format:	Journal Article
Language:	English
Published:	Hoboken, USA John Wiley & Sons, Inc 01.07.2021 Wiley Subscription Services, Inc
Subjects:	Annotations Bladder cell classification cell detection cell segmentation Cellular biology Cytodiagnosis Cytology Deep Learning Depth profiling Diagnosis Digital imaging digital risk Histopathology Machine learning Malignancy Medical imaging Morphology oversampling Risk Risk Assessment ROC Curve The Paris System Urine urine cytology The Paris System deep learning urine cytology cell classification cell segmentation cell detection digital risk oversampling
ISSN:	1552-4922, 1552-4930, 1552-4930
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Urine cytology is a test for the detection of high‐grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low‐risk and high‐risk malignancy. Computer‐assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning‐based approaches. Based on the best performing network predictions at the cell level, we identified low‐risk and high‐risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology‐based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability.
AbstractList	Urine cytology is a test for the detection of high-grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low-risk and high-risk malignancy. Computer-assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning-based approaches. Based on the best performing network predictions at the cell level, we identified low-risk and high-risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology-based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability. Urine cytology is a test for the detection of high-grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low-risk and high-risk malignancy. Computer-assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning-based approaches. Based on the best performing network predictions at the cell level, we identified low-risk and high-risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology-based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability.Urine cytology is a test for the detection of high-grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low-risk and high-risk malignancy. Computer-assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning-based approaches. Based on the best performing network predictions at the cell level, we identified low-risk and high-risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology-based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability.
Author	Minhas, Fayyaz Awan, Ruqayya Azam, Ayesha Tsang, Yee Wah Snead, David Rajpoot, Nasir Benes, Ksenija Shaban, Muhammad Verrill, Clare Song, Tzu‐Hsi
Author_xml	– sequence: 1 givenname: Ruqayya orcidid: 0000-0002-2223-329X surname: Awan fullname: Awan, Ruqayya email: awanruqayya2@gmail.com organization: University of Warwick – sequence: 2 givenname: Ksenija surname: Benes fullname: Benes, Ksenija organization: The Royal Wolverhampton NHS Trust – sequence: 3 givenname: Ayesha surname: Azam fullname: Azam, Ayesha organization: University Hospitals Coventry and Warwickshire – sequence: 4 givenname: Tzu‐Hsi surname: Song fullname: Song, Tzu‐Hsi organization: Laboratory of Quantitative Cellular Imaging, Worcester Polytechnic Institute – sequence: 5 givenname: Muhammad surname: Shaban fullname: Shaban, Muhammad organization: University of Warwick – sequence: 6 givenname: Clare surname: Verrill fullname: Verrill, Clare organization: University of Oxford – sequence: 7 givenname: Yee Wah surname: Tsang fullname: Tsang, Yee Wah organization: University Hospitals Coventry and Warwickshire – sequence: 8 givenname: David surname: Snead fullname: Snead, David organization: University Hospitals Coventry and Warwickshire – sequence: 9 givenname: Fayyaz surname: Minhas fullname: Minhas, Fayyaz organization: University of Warwick – sequence: 10 givenname: Nasir surname: Rajpoot fullname: Rajpoot, Nasir organization: The Alan Turing Institute
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33486882$$D View this record in MEDLINE/PubMed
BookMark	eNp9kTtPwzAURi0EAgpszMgSCwMtfuU1ovKUKnXpAovlONeVSxoXOxHqv8ehpUMlWGwP57M_nztAh41rAKFLSkaUEHan160bqRETnPIDdEqThA1Fwcnh7szYCRqEsCCEJ4SzY3TCucjTPGen6P0BYIVrUL6xzRyXKkCFKzu3raqxhrrGK--MrSFg4zz2Nnzg0HrVWmN1XF2DncGdtw3gvknt5mtsl2oO4RwdGVUHuNjuZ2j29Dgbvwwn0-fX8f1kqEWa8yFNM1XykhktDKQmKYsKMkp0JgqVKAJEaYBSaU7zKk1FomlJjCZ5lXNV8YqfoZvNtbHoZwehlUsb-uaqAdcFyUROMl7QjET0eg9duM43sZxkiUgLmhCaRepqS3XlEiq58vE_fi1_pUXgdgNo70LwYHYIJbKfiexNSCV_ZhJxtofraLdXFz3a-q-Q2IS-ovv1vw_I8dtser-JfQOfZ6Hl
CitedBy_id	crossref_primary_10_1111_bju_15518 crossref_primary_10_1016_j_critrevonc_2022_103601 crossref_primary_10_1016_j_media_2024_103109 crossref_primary_10_1111_cyt_13412 crossref_primary_10_1016_j_jasc_2023_11_005 crossref_primary_10_1002_cncy_22725 crossref_primary_10_1016_j_jasc_2025_07_004 crossref_primary_10_1016_j_compbiomed_2024_108942 crossref_primary_10_3390_app13031763 crossref_primary_10_1007_s00345_025_05583_8 crossref_primary_10_1016_j_jpi_2023_100346 crossref_primary_10_1002_cyto_a_24832 crossref_primary_10_1002_cncy_22633 crossref_primary_10_3390_diagnostics13132308 crossref_primary_10_1016_j_compbiolchem_2025_108616 crossref_primary_10_1016_j_media_2022_102691 crossref_primary_10_3390_jcm13237110 crossref_primary_10_1007_s00761_024_01482_6 crossref_primary_10_3390_s24247873 crossref_primary_10_1002_INMD_20230013 crossref_primary_10_3390_cancers16051064 crossref_primary_10_1002_cncy_22615 crossref_primary_10_2196_56946 crossref_primary_10_1016_j_euf_2025_07_011 crossref_primary_10_1007_s11654_024_00572_6 crossref_primary_10_1109_ACCESS_2024_3385864 crossref_primary_10_1016_j_jasc_2024_09_001 crossref_primary_10_3390_cancers14143529 crossref_primary_10_1016_j_euo_2023_11_009
Cites_doi	10.1002/dc.24476 10.1109/JBHI.2016.2519686 10.1109/CVPR.2017.195 10.1016/j.eururo.2016.06.010 10.1016/j.jasc.2018.02.005 10.1613/jair.953 10.3390/app8091608 10.1002/cncy.22176 10.4103/cytojournal.cytojournal_12_17 10.4103/cytojournal.cytojournal_30_19 10.1042/BSR20180289 10.1109/CVPRW.2016.172 10.1159/000446270 10.4103/2153-3539.124015 10.1109/CVPR.2016.91 10.1007/978-3-319-22864-8 10.1002/cncy.22099 10.1109/CVPR.2014.81 10.1109/JBHI.2017.2705583 10.1109/ICCV.2017.324 10.1016/j.neucom.2019.06.086 10.1109/TSMC.1979.4310076 10.1007/978-3-319-46448-0_2 10.1109/ISBI.2016.7493244 10.1109/ICCV.2015.169 10.1016/j.ijmedinf.2018.11.010
ContentType	Journal Article
Copyright	2021 The Authors. published by Wiley Periodicals LLC. on behalf of International Society for Advancement of Cytometry. 2021 The Authors. Cytometry Part A published by Wiley Periodicals LLC. on behalf of International Society for Advancement of Cytometry. 2021. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: 2021 The Authors. published by Wiley Periodicals LLC. on behalf of International Society for Advancement of Cytometry. – notice: 2021 The Authors. Cytometry Part A published by Wiley Periodicals LLC. on behalf of International Society for Advancement of Cytometry. – notice: 2021. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	24P AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QO 7TK 8FD FR3 P64 7X8
DOI	10.1002/cyto.a.24313
DatabaseName	Wiley-Blackwell Open Access Titles CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Biotechnology Research Abstracts Neurosciences Abstracts Technology Research Database Engineering Research Database Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Engineering Research Database Biotechnology Research Abstracts Technology Research Database Neurosciences Abstracts Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitleList	MEDLINE CrossRef Engineering Research Database MEDLINE - Academic
Database_xml	– sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	1552-4930
EndPage	742
ExternalDocumentID	33486882 10_1002_cyto_a_24313 CYTOA24313
Genre	article Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: Warwick Impact Fund – fundername: UK Research and Innovation – fundername: Engineering and Physical Sciences Research Council funderid: EP/N510129/1 – fundername: Engineering and Physical Sciences Research Council grantid: EP/N510129/1 – fundername: Medical Research Council grantid: MR/P015476/1
GroupedDBID	--- -~X .3N .GA .Y3 05W 0R~ 10A 1L6 1OC 24P 2WC 31~ 33P 3SF 4.4 4ZD 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 53G 5GY 5VS 66C 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A03 AAESR AAEVG AAHHS AAHQN AAMNL AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABEML ABIJN ABLJU ABPVW ACAHQ ACCFJ ACCZN ACFBH ACGFS ACIWK ACPOU ACPRK ACSCC ACXBN ACXQS ADBBV ADEOM ADIZJ ADKYN ADMGS ADOZA ADXAS ADZMN ADZOD AEEZP AEGXH AEIGN AEIMD AENEX AEQDE AEUQT AEUYR AFBPY AFFPM AFGKR AFPWT AFRAH AFWVQ AFZJQ AHBTC AITYG AIURR AIWBW AJBDE AJXKR ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ATUGU AUFTA AZBYB AZVAB BAFTC BAWUL BFHJK BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BY8 CO8 CS3 D-E D-F DCZOG DIK DPXWK DR2 DRFUL DRSTM DU5 E3Z EBD EBS EJD EMOBN F00 F01 F04 F5P G-S G.N GNP GODZA H.T H.X HBH HF~ HGLYW HHY HHZ HZ~ IX1 J0M JPC KQQ LATKE LAW LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 N9A NF~ O66 O9- OIG OK1 P2P P2W P2X P4D Q.N QB0 QRW R.K RNS ROL RWI SUPJJ SV3 UB1 V2E W8V W99 WBKPD WIH WIK WIN WJL WNSPC WOHZO WQJ WRC WXSBR WYISQ XG1 XV2 ZZTAW ~IA ~KM ~WT AAMMB AAYXX AEFGJ AEYWJ AGHNM AGXDD AGYGG AIDQK AIDYY CITATION CGR CUY CVF ECM EIF NPM 7QO 7TK 8FD FR3 P64 7X8
ID	FETCH-LOGICAL-c4683-167ab3b2fc4fe6f5b9de710c749a5a0e0aceebac318d6645c1b0fc08d83ad3d3
IEDL.DBID	24P
ISICitedReferencesCount	23
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000619856200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1552-4922 1552-4930
IngestDate	Thu Oct 02 07:09:21 EDT 2025 Fri Jul 25 21:17:18 EDT 2025 Mon Jul 21 05:35:28 EDT 2025 Sat Nov 29 01:52:12 EST 2025 Tue Nov 18 22:29:04 EST 2025 Wed Jan 22 16:28:57 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	7
Keywords	The Paris System deep learning urine cytology cell classification cell segmentation cell detection digital risk oversampling
Language	English
License	Attribution 2021 The Authors. Cytometry Part A published by Wiley Periodicals LLC. on behalf of International Society for Advancement of Cytometry.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c4683-167ab3b2fc4fe6f5b9de710c749a5a0e0aceebac318d6645c1b0fc08d83ad3d3
Notes	Funding information Warwick Impact Fund; Engineering and Physical Sciences Research Council, Grant/Award Number: EP/N510129/1; UK Research and Innovation ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-2223-329X
OpenAccessLink	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fcyto.a.24313
PMID	33486882
PQID	2546915017
PQPubID	2045167
PageCount	11
ParticipantIDs	proquest_miscellaneous_2480739170 proquest_journals_2546915017 pubmed_primary_33486882 crossref_primary_10_1002_cyto_a_24313 crossref_citationtrail_10_1002_cyto_a_24313 wiley_primary_10_1002_cyto_a_24313_CYTOA24313
PublicationCentury	2000
PublicationDate	July 2021
PublicationDateYYYYMMDD	2021-07-01
PublicationDate_xml	– month: 07 year: 2021 text: July 2021
PublicationDecade	2020
PublicationPlace	Hoboken, USA
PublicationPlace_xml	– name: Hoboken, USA – name: United States – name: Hoboken
PublicationTitle	Cytometry. Part A
PublicationTitleAlternate	Cytometry A
PublicationYear	2021
Publisher	John Wiley & Sons, Inc Wiley Subscription Services, Inc
Publisher_xml	– name: John Wiley & Sons, Inc – name: Wiley Subscription Services, Inc
References	2002; 16 2013; 4 2017; 21 2019; 16 2019; 127 2019; 122 2019; 365 2018; 7 2018; 8 2017; 71 2017; 14 2020 2016; 21 2020; 48 2009; 344 2017 2016 2016; 60 2015 2014 2013 2017; 783 2012; 5 2018; 38 1979; 9 e_1_2_9_30_1 e_1_2_9_31_1 e_1_2_9_10_1 e_1_2_9_13_1 e_1_2_9_32_1 e_1_2_9_12_1 e_1_2_9_33_1 Reid MD (e_1_2_9_34_1) 2012; 5 e_1_2_9_15_1 e_1_2_9_14_1 e_1_2_9_17_1 e_1_2_9_16_1 e_1_2_9_19_1 e_1_2_9_18_1 e_1_2_9_20_1 e_1_2_9_22_1 e_1_2_9_21_1 e_1_2_9_23_1 e_1_2_9_8_1 e_1_2_9_7_1 e_1_2_9_6_1 e_1_2_9_5_1 e_1_2_9_4_1 e_1_2_9_3_1 e_1_2_9_2_1 e_1_2_9_9_1 e_1_2_9_26_1 Żejmo M (e_1_2_9_11_1) 2017 e_1_2_9_25_1 Kaufman L (e_1_2_9_24_1) 2009 e_1_2_9_28_1 e_1_2_9_27_1 e_1_2_9_29_1
References_xml	– volume: 7 start-page: 174 issue: 4 year: 2018 end-page: 84 article-title: Paris interobserver reproducibility study (PIRST) publication-title: J Am Soc Cytopathol – volume: 127 start-page: 658 issue: 10 year: 2019 end-page: 66 article-title: Performance of an artificial intelligence algorithm for reporting urine cytopathology publication-title: Cancer Cytopathol – start-page: 779 year: 2016 end-page: 788 – start-page: 21 year: 2016 end-page: 37 – volume: 365 start-page: 157 year: 2019 end-page: 70 article-title: Accurate segmentation of overlapping cells in cervical cytology with deep convolutional neural networks publication-title: Neurocomputing – volume: 14 start-page: 17 year: 2017 article-title: Interobserver reproducibility of the Paris system for reporting urinary cytology publication-title: Cytojournal – start-page: 63 year: 2016 end-page: 69 – start-page: 1251 year: 2017 end-page: 1258 – volume: 60 start-page: 185 issue: 3 year: 2016 end-page: 97 article-title: The Paris system for reporting urinary cytology: the quest to develop a standardized terminology publication-title: Acta Cytol – year: 2016 – volume: 5 start-page: 882 issue: 9 year: 2012 end-page: 91 article-title: Accuracy of grading of urothelial carcinoma on urine cytology: an analysis of interobserver and intraobserver agreement publication-title: Int J Clin Exp Pathol – volume: 9 start-page: 62 issue: 1 year: 1979 end-page: 6 article-title: A threshold selection method from gray‐level histograms publication-title: IEEE Trans Syst Man Cybern – volume: 122 start-page: 13 year: 2019 end-page: 9 article-title: Nasal cytology with deep learning techniques publication-title: Int J Med Inform – volume: 783 start-page: 12060 year: 2017 – volume: 21 start-page: 1633 issue: 6 year: 2017 end-page: 43 article-title: DeepPap: deep convolutional networks for cervical cell classification publication-title: IEEE J Biomed Health Inform – start-page: 2980 year: 2017 end-page: 2988 – volume: 16 start-page: 21 year: 2019 article-title: Impact of the Paris system for reporting urine cytopathology on predictive values of the equivocal diagnostic categories and interobserver agreement publication-title: CytoJournal – volume: 344 year: 2009 – start-page: 1440 year: 2015 end-page: 1448 – volume: 48 start-page: 979 issue: 11 year: 2020 end-page: 85 article-title: Interobserver reproducibility of the Paris system of reporting urine cytology on cytocentrifuged samples publication-title: Diagn Cytopathol – volume: 16 start-page: 321 year: 2002 end-page: 57 article-title: SMOTE: synthetic minority over‐sampling technique publication-title: J Artif Intell Res – start-page: 91 year: 2015 end-page: 99 – year: 2020 – volume: 38 issue: 3 year: 2018 article-title: Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks publication-title: Biosci Rep – start-page: 379 year: 2016 end-page: 387 – volume: 71 start-page: 96 issue: 1 year: 2017 end-page: 108 article-title: Bladder cancer incidence and mortality: a global overview and recent trends publication-title: Eur Urol – volume: 4 start-page: 38 year: 2013 article-title: Optimal z‐axis scanning parameters for gynecologic cytology specimens publication-title: J Pathol Inform – start-page: 201 year: 2016 end-page: 204 – volume: 21 start-page: 441 issue: 2 year: 2016 end-page: 50 article-title: Evaluation of three algorithms for the segmentation of overlapping cervical cells publication-title: IEEE J Biomed Health Inform – volume: 127 start-page: 98 issue: 2 year: 2019 end-page: 115 article-title: Automating the Paris system for urine cytopathology—a hybrid deep‐learning and morphometric approach publication-title: Cancer Cytopathol – start-page: 580 year: 2014 end-page: 587 – volume: 8 start-page: 1608 issue: 9 year: 2018 article-title: Detection and classification of overlapping cell nuclei in cytology effusion images using a double‐strategy random forest publication-title: App Sci – year: 2013 – ident: e_1_2_9_10_1 doi: 10.1002/dc.24476 – volume-title: Finding groups in data: an introduction to cluster analysis year: 2009 ident: e_1_2_9_24_1 – ident: e_1_2_9_20_1 doi: 10.1109/JBHI.2016.2519686 – ident: e_1_2_9_25_1 doi: 10.1109/CVPR.2017.195 – ident: e_1_2_9_2_1 doi: 10.1016/j.eururo.2016.06.010 – ident: e_1_2_9_8_1 doi: 10.1016/j.jasc.2018.02.005 – volume: 5 start-page: 882 issue: 9 year: 2012 ident: e_1_2_9_34_1 article-title: Accuracy of grading of urothelial carcinoma on urine cytology: an analysis of interobserver and intraobserver agreement publication-title: Int J Clin Exp Pathol – ident: e_1_2_9_22_1 doi: 10.1613/jair.953 – ident: e_1_2_9_18_1 doi: 10.3390/app8091608 – ident: e_1_2_9_16_1 doi: 10.1002/cncy.22176 – ident: e_1_2_9_7_1 doi: 10.4103/cytojournal.cytojournal_12_17 – ident: e_1_2_9_4_1 – ident: e_1_2_9_32_1 – ident: e_1_2_9_9_1 doi: 10.4103/cytojournal.cytojournal_30_19 – ident: e_1_2_9_14_1 doi: 10.1042/BSR20180289 – ident: e_1_2_9_21_1 doi: 10.1109/CVPRW.2016.172 – ident: e_1_2_9_5_1 doi: 10.1159/000446270 – ident: e_1_2_9_3_1 doi: 10.4103/2153-3539.124015 – ident: e_1_2_9_31_1 doi: 10.1109/CVPR.2016.91 – start-page: 12060 volume-title: Journal of physics: conference series year: 2017 ident: e_1_2_9_11_1 – ident: e_1_2_9_6_1 doi: 10.1007/978-3-319-22864-8 – ident: e_1_2_9_15_1 doi: 10.1002/cncy.22099 – ident: e_1_2_9_27_1 doi: 10.1109/CVPR.2014.81 – ident: e_1_2_9_12_1 doi: 10.1109/JBHI.2017.2705583 – ident: e_1_2_9_30_1 – ident: e_1_2_9_33_1 doi: 10.1109/ICCV.2017.324 – ident: e_1_2_9_19_1 doi: 10.1016/j.neucom.2019.06.086 – ident: e_1_2_9_26_1 – ident: e_1_2_9_23_1 doi: 10.1109/TSMC.1979.4310076 – ident: e_1_2_9_29_1 doi: 10.1007/978-3-319-46448-0_2 – ident: e_1_2_9_17_1 doi: 10.1109/ISBI.2016.7493244 – ident: e_1_2_9_28_1 doi: 10.1109/ICCV.2015.169 – ident: e_1_2_9_13_1 doi: 10.1016/j.ijmedinf.2018.11.010
SSID	ssj0035032
Score	2.4450836
Snippet	Urine cytology is a test for the detection of high‐grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the... Urine cytology is a test for the detection of high-grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the...
SourceID	proquest pubmed crossref wiley
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	732
SubjectTerms	Annotations Bladder cell classification cell detection cell segmentation Cellular biology Cytodiagnosis Cytology Deep Learning Depth profiling Diagnosis Digital imaging digital risk Histopathology Machine learning Malignancy Medical imaging Morphology oversampling Risk Risk Assessment ROC Curve The Paris System Urine urine cytology
Title	Deep learning based digital cell profiles for risk stratification of urine cytology images
URI	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fcyto.a.24313 https://www.ncbi.nlm.nih.gov/pubmed/33486882 https://www.proquest.com/docview/2546915017 https://www.proquest.com/docview/2480739170
Volume	99
WOSCitedRecordID	wos000619856200001&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 Free Content customDbUrl: eissn: 1552-4930 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035032 issn: 1552-4922 databaseCode: WIN dateStart: 20030101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1552-4930 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035032 issn: 1552-4922 databaseCode: DRFUL dateStart: 20030101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3da9RAEB-0VeiL9as1WssK-iRpN7t7yeaxtD0U5Cxy4ulL2K-Ug_auNFeh_70zm71riyiILyEhk-yys_Oxw8z8AN4KizbOlnjIkdznyimd67IKuefe8yAoBdBEsIlqNNKTSX2SAm5UC9P3h1gF3Egyor4mATe2279pGuquF_M9syfQAsr7sF4UUhN0g1AnS00sBzwClFGXsVzVQqTEd_x-__bXd03Sb37mXbc12p3h5v_O-DE8Sh4nO-i3yBO4F2ZP4WGPQXn9DH4chXDBEnjEKSOr5pmfnhKYCKOwPkuw3h1D_5ZRKjrre-22KdzH5i2jmH1gNDT9lU3PUU11z2E8PB4ffsgT4ELuVKllXpSVsdKK1qk2lO3A1j6gB-IqVZuB4YEbNKnWONQDvizVwBWWt45rr6Xx0sstWJvNZ-EFsMIExb1F_ycYFapK-8KqUCP_qfReigzeL5e8cakZOWFinDV9G2XR0Iwb08TFyuDdivqib8LxB7qdJfeaJIpdQw3_a3R7iyqDN6vXKES0hGYW5ldIQ4X1Ek-uPIPtnuurgahUucRzSAZ5ZO5fZ9Acfh9_Poi3L_-R_hVsCMqXianAO7C2uLwKr-GB-7mYdpe7cWPjtZroXVg_-jL8-gmfvn0c_QLhXQBK
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dSxwxEB-sWtoXW-3XWrUp2Keymk1y-_EoVlFqTx8OavsS8rVy0N6Jdxb87zuTzV2VYqH4trCT3ZBkPjLM_H4A28Kij7MlXnIk97lyqs7rsgq5597zIKgE0ESyiarfr8_Pm7PEc0q9MB0-xDzhRpoR7TUpOCWkd_-ghrqb6XjH7Ah0gfIRLCmMNYi74etxf2aKZY9HhjKCGctVI0SqfMfxu7dH3_VJfwWad-PW6HgOnz14ys9hJcWcbK87JKuwEEZr8Lhjobx5Ad8_hXDJEn3EBSO_5pkfXhCdCKPEPkvE3hOGES6jYnTWoe22KeHHxi2jrH1g9Gv6Khv-REM1eQmDw4PB_lGeKBdyp8pa5kVZGSutaJ1qQ9n2bOMDxiCuUo3pGR64QadqjUNL4MtS9Vxheet47WtpvPTyFSyOxqPwBlhhguLeYgQUjApVVfvCqtDgCaDmeyky-Dhbc-0SHDmxYvzQHZCy0DRjbXRcrAw-zKUvOxiOe-Q2ZtunkzJONEH-Nxj4FlUG7-evUY1oCc0ojK9RhlrrJd5deQavu22f_4ialUu8iWSQx9395wz0_rfB6V58XP9P-Xfw5Gjw5USfHPc_v4WngqpnYmHwBixOr67DJiy7X9Ph5GornvLfq_ABCw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dSxwxEB_s2RZfaj-srto2hfaprGaT3H48iufRUrlKuYLtS8jHrBzo3eGdgv-9md3cVSktFN8WdjYbksxHhpnfD-CDsMHH2TxcciT3qXKqTMu8wNRz7zkKKgE0DdlEMRiUp6fVSeQ5pV6YFh9imXAjzWjsNSk4Tn29_xs11N3MJ3tmTwQXKB_BqiIemQ6s9r73fxwvjLHs8oajjIDGUlUJEWvfwwj7d7-_75X-CDXvR66N6-mvP3jSz-FZjDrZQXtMXsAKjl_Ck5aH8uYV_OohTlkkkDhj5Nk886MzIhRhlNpnkdp7xkKMy6gcnbV4u3VM-bFJzShvj4x-TaOy0UUwVbMNGPaPhoef00i6kDqVlzLN8sJYaUXtVI153bWVxxCFuEJVpms4chPcqjUu2AKf56rrMstrx0tfSuOll6-hM56McQtYZlBxb0MMhEZhUZQ-swqrcAao_V6KBD4t1ly7CEhOvBjnuoVSFppmrI1uFiuBj0vpaQvE8Re53cX26aiOM02g_1UIfbMigffL10GRaAnNGCdXQYaa62W4vfIENtttX_6I2pXzcBdJIG12958z0Ic_h98Omsft_5R_B09Pen19_GXwdQfWBJXPNJXBu9CZX17hG3jsruej2eXbeMxvAUgKAbQ
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=Deep+learning+based+digital+cell+profiles+for+risk+stratification+of+urine+cytology+images&rft.jtitle=Cytometry.+Part+A&rft.au=Awan%2C+Ruqayya&rft.au=Benes%2C+Ksenija&rft.au=Azam%2C+Ayesha&rft.au=Song%2C+Tzu-Hsi&rft.date=2021-07-01&rft.eissn=1552-4930&rft.volume=99&rft.issue=7&rft.spage=732&rft_id=info:doi/10.1002%2Fcyto.a.24313&rft_id=info%3Apmid%2F33486882&rft.externalDocID=33486882
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1552-4922&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1552-4922&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1552-4922&client=summon