Cervical Cell/Clumps Detection in Cytology Images Using Transfer Learning
Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, there have been many studies conducted using deep learning met...
Saved in:
Published in | Diagnostics (Basel) Vol. 12; no. 10; p. 2477 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
Switzerland
MDPI AG
01.10.2022
MDPI |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, there have been many studies conducted using deep learning methods for automatic cervical cancer screening and diagnosis. Deep-learning-based Convolutional Neural Network (CNN) models require large amounts of data for training, but large cervical cell datasets with annotations are difficult to obtain. Some studies have used transfer learning approaches to handle this problem. However, such studies used the same transfer learning method that is the backbone network initialization by the ImageNet pre-trained model in two different types of tasks, the detection and classification of cervical cell/clumps. Considering the differences between detection and classification tasks, this study proposes the use of COCO pre-trained models when using deep learning methods for cervical cell/clumps detection tasks to better handle limited data set problem at training time. To further improve the model detection performance, based on transfer learning, we conducted multi-scale training according to the actual situation of the dataset. Considering the effect of bounding box loss on the precision of cervical cell/clumps detection, we analyzed the effects of different bounding box losses on the detection performance of the model and demonstrated that using a loss function consistent with the type of pre-trained model can help improve the model performance. We analyzed the effect of mean and std of different datasets on the performance of the model. It was demonstrated that the detection performance was optimal when using the mean and std of the cervical cell dataset used in the current study. Ultimately, based on backbone Resnet50, the mean Average Precision (mAP) of the network model is 61.6% and Average Recall (AR) is 87.7%. Compared to the current values of 48.8% and 64.0% in the used dataset, the model detection performance is significantly improved by 12.8% and 23.7%, respectively. |
---|---|
AbstractList | Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, there have been many studies conducted using deep learning methods for automatic cervical cancer screening and diagnosis. Deep-learning-based Convolutional Neural Network (CNN) models require large amounts of data for training, but large cervical cell datasets with annotations are difficult to obtain. Some studies have used transfer learning approaches to handle this problem. However, such studies used the same transfer learning method that is the backbone network initialization by the ImageNet pre-trained model in two different types of tasks, the detection and classification of cervical cell/clumps. Considering the differences between detection and classification tasks, this study proposes the use of COCO pre-trained models when using deep learning methods for cervical cell/clumps detection tasks to better handle limited data set problem at training time. To further improve the model detection performance, based on transfer learning, we conducted multi-scale training according to the actual situation of the dataset. Considering the effect of bounding box loss on the precision of cervical cell/clumps detection, we analyzed the effects of different bounding box losses on the detection performance of the model and demonstrated that using a loss function consistent with the type of pre-trained model can help improve the model performance. We analyzed the effect of mean and std of different datasets on the performance of the model. It was demonstrated that the detection performance was optimal when using the mean and std of the cervical cell dataset used in the current study. Ultimately, based on backbone Resnet50, the mean Average Precision (mAP) of the network model is 61.6% and Average Recall (AR) is 87.7%. Compared to the current values of 48.8% and 64.0% in the used dataset, the model detection performance is significantly improved by 12.8% and 23.7%, respectively. Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, there have been many studies conducted using deep learning methods for automatic cervical cancer screening and diagnosis. Deep-learning-based Convolutional Neural Network (CNN) models require large amounts of data for training, but large cervical cell datasets with annotations are difficult to obtain. Some studies have used transfer learning approaches to handle this problem. However, such studies used the same transfer learning method that is the backbone network initialization by the ImageNet pre-trained model in two different types of tasks, the detection and classification of cervical cell/clumps. Considering the differences between detection and classification tasks, this study proposes the use of COCO pre-trained models when using deep learning methods for cervical cell/clumps detection tasks to better handle limited data set problem at training time. To further improve the model detection performance, based on transfer learning, we conducted multi-scale training according to the actual situation of the dataset. Considering the effect of bounding box loss on the precision of cervical cell/clumps detection, we analyzed the effects of different bounding box losses on the detection performance of the model and demonstrated that using a loss function consistent with the type of pre-trained model can help improve the model performance. We analyzed the effect of mean and std of different datasets on the performance of the model. It was demonstrated that the detection performance was optimal when using the mean and std of the cervical cell dataset used in the current study. Ultimately, based on backbone Resnet50, the mean Average Precision (mAP) of the network model is 61.6% and Average Recall (AR) is 87.7%. Compared to the current values of 48.8% and 64.0% in the used dataset, the model detection performance is significantly improved by 12.8% and 23.7%, respectively.Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, there have been many studies conducted using deep learning methods for automatic cervical cancer screening and diagnosis. Deep-learning-based Convolutional Neural Network (CNN) models require large amounts of data for training, but large cervical cell datasets with annotations are difficult to obtain. Some studies have used transfer learning approaches to handle this problem. However, such studies used the same transfer learning method that is the backbone network initialization by the ImageNet pre-trained model in two different types of tasks, the detection and classification of cervical cell/clumps. Considering the differences between detection and classification tasks, this study proposes the use of COCO pre-trained models when using deep learning methods for cervical cell/clumps detection tasks to better handle limited data set problem at training time. To further improve the model detection performance, based on transfer learning, we conducted multi-scale training according to the actual situation of the dataset. Considering the effect of bounding box loss on the precision of cervical cell/clumps detection, we analyzed the effects of different bounding box losses on the detection performance of the model and demonstrated that using a loss function consistent with the type of pre-trained model can help improve the model performance. We analyzed the effect of mean and std of different datasets on the performance of the model. It was demonstrated that the detection performance was optimal when using the mean and std of the cervical cell dataset used in the current study. Ultimately, based on backbone Resnet50, the mean Average Precision (mAP) of the network model is 61.6% and Average Recall (AR) is 87.7%. Compared to the current values of 48.8% and 64.0% in the used dataset, the model detection performance is significantly improved by 12.8% and 23.7%, respectively. |
Audience | Academic |
Author | Zhang, Yang Sun, Chengjie Xu, Chuanyun Li, Mengwei Li, Gang Bai, Nanlan |
AuthorAffiliation | 2 College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China 1 School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China |
AuthorAffiliation_xml | – name: 2 College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China – name: 1 School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China |
Author_xml | – sequence: 1 givenname: Chuanyun surname: Xu fullname: Xu, Chuanyun organization: College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China – sequence: 2 givenname: Mengwei surname: Li fullname: Li, Mengwei organization: School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China – sequence: 3 givenname: Gang surname: Li fullname: Li, Gang organization: School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China – sequence: 4 givenname: Yang surname: Zhang fullname: Zhang, Yang organization: College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China – sequence: 5 givenname: Chengjie surname: Sun fullname: Sun, Chengjie organization: School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China – sequence: 6 givenname: Nanlan surname: Bai fullname: Bai, Nanlan organization: School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36292166$$D View this record in MEDLINE/PubMed |
BookMark | eNptUk1rGzEUFCWl-Wh-QaEs9NKLk7f63kshbJvWYOglOQutpN3K7EqutA7430eu0zQukQ4STzOj94Y5RychBofQhxquCGng2no9hJhnb3KNa8BUiDfoDINgC0prefLifoouc15DWU1NJGbv0CnhuME152do2br04I0eq9aN43U7bqdNrr662ZnZx1D5ULW7OY5x2FXLSQ8uV_fZh6G6Szrk3qVq5XQKpfIeve31mN3l03mB7m-_3bU_Fquf35ftzWphGOfzgmjNrQFmcG2tZdZYBqVVzoH21hIutDWGdNIxSaGTxhliMaOCWFm655RcoOVB10a9VpvkJ512Kmqv_hRiGpROxZfRKdZZED2RAnpOOwzadY5IS1ljBe86XLS-HLQ2225y1rgwJz0eiR6_BP9LDfFBNRxAABSBz08CKf7eujyryWdTnNTBxW1WWOCGYdxwVqCf_oOu4zaFYtUeJSkTNch_qEGXAXzoY_nX7EXVjaCMAVBCCurqFVTZ1k3elKT0vtSPCORAMCnmnFz_PGMNah8o9UqgCuvjS3ueOX_jQx4BNy7Jmg |
CitedBy_id | crossref_primary_10_3390_biomedicines11082225 crossref_primary_10_4132_jptm_2023_07_17 crossref_primary_10_1016_j_imu_2024_101503 crossref_primary_10_1002_ima_23043 crossref_primary_10_3390_bioengineering11070686 crossref_primary_10_1007_s10462_023_10588_z crossref_primary_10_1109_JBHI_2024_3375889 |
Cites_doi | 10.1038/s41467-021-25296-x 10.1016/j.neucom.2021.01.006 10.1109/JBHI.2017.2705583 10.1016/j.media.2017.07.003 10.1309/AJCPTGD94EVRSJCG 10.1049/cit2.12059 10.1016/j.media.2021.102197 10.1109/CVPR.2019.00075 10.1007/978-3-319-46448-0_2 10.1016/j.compbiomed.2022.106083 10.3892/ol.2020.11974 10.1109/ICIP.2018.8451588 10.7717/peerj-cs.457 10.1109/CVPR.2017.690 10.1007/s12105-012-0377-0 10.1109/JBHI.2016.2519686 10.1049/cit2.12061 10.1016/j.cmpb.2021.106061 10.1109/ISBI52829.2022.9761652 10.1109/ICCV.2015.169 10.1109/CVPRW50498.2020.00521 10.1109/ACCESS.2020.2983186 10.1038/s41598-021-93783-8 10.1016/j.patcog.2018.05.014 10.1016/j.tice.2021.101677 10.1007/978-3-030-32692-0_8 10.1016/j.bbe.2020.01.016 10.1109/CVPR.2017.106 10.1016/j.media.2021.102167 10.1016/j.cmpb.2020.105807 10.1111/cyt.12835 10.1042/BSR20181769 10.1016/j.tice.2020.101347 10.3390/curroncol28050307 10.1109/CVPR.2016.91 10.1109/ICCV.2017.324 10.1109/TMI.2022.3163171 10.1186/s42490-021-00056-6 10.1016/j.compbiomed.2021.104649 10.1609/aaai.v34i07.6999 10.3934/mbe.2021090 10.1109/CVPR.2009.5206848 10.1016/S1470-2045(01)00486-7 10.1109/CVPR.2016.90 10.1007/978-3-319-10602-1_48 10.1586/eog.11.13 10.1109/ACCESS.2019.2919390 10.1016/j.media.2022.102691 10.1145/2964284.2967274 10.1109/CVPR.2014.81 |
ContentType | Journal Article |
Copyright | COPYRIGHT 2022 MDPI AG 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2022 by the authors. 2022 |
Copyright_xml | – notice: COPYRIGHT 2022 MDPI AG – notice: 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2022 by the authors. 2022 |
DBID | NPM AAYXX CITATION 3V. 7XB 8FK 8G5 ABUWG AFKRA AZQEC BENPR CCPQU DWQXO GNUQQ GUQSH M2O MBDVC PIMPY PQEST PQQKQ PQUKI PRINS Q9U 7X8 5PM DOA |
DOI | 10.3390/diagnostics12102477 |
DatabaseName | PubMed CrossRef ProQuest Central (Corporate) ProQuest Central (purchase pre-March 2016) ProQuest Central (Alumni) (purchase pre-March 2016) Research Library (Alumni Edition) ProQuest Central (Alumni Edition) ProQuest Central UK/Ireland ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central ProQuest One Community College ProQuest Central ProQuest Central Student Research Library Prep Research Library Research Library (Corporate) ProQuest - Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
DatabaseTitle | PubMed CrossRef Publicly Available Content Database Research Library Prep ProQuest Central Student ProQuest Central Basic ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College Research Library (Alumni Edition) ProQuest Central China ProQuest Central ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Research Library ProQuest One Academic ProQuest Central (Alumni) MEDLINE - Academic |
DatabaseTitleList | PubMed MEDLINE - Academic CrossRef Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine |
EISSN | 2075-4418 |
ExternalDocumentID | oai_doaj_org_article_5bd07f3870f64b20aebe38d459d76bb2 A745500433 10_3390_diagnostics12102477 36292166 |
Genre | Journal Article |
GeographicLocations | China |
GeographicLocations_xml | – name: China |
GrantInformation_xml | – fundername: Chongqing Science and Technology Commission grantid: cstc2019jcyj-msxmX0442 – fundername: Chongqing Science and Technology Commission grantid: cstc2019jscx-zdztzx0043 – fundername: Chongqing Science and Technology Commission grantid: cstc2020jscx-msxmX0086 – fundername: China Chongqing Banan District Science and Technology Commission project grantid: 2020QC413 – fundername: China Chongqing Science and Technology Commission grantid: cstc2020jscx-msxmX0086; cstc2019jscx-zdztzx0043; cstc2019jcyj-msxmX0442 – fundername: China Chongqing Municipal Education Commission grantid: KJQN202001137 |
GroupedDBID | 3V. 53G 5VS 8G5 AADQD AAFWJ ABDBF ABUWG ADBBV AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS AOIJS AZQEC BCNDV BENPR BPHCQ CCPQU DWQXO EBD ESX GNUQQ GROUPED_DOAJ GUQSH HYE IAO IHR ITC KQ8 M2O M48 MODMG M~E NPM OK1 PGMZT PIMPY PQQKQ PROAC RIG RPM AAYXX CITATION 7XB 8FK MBDVC PQEST PQUKI PRINS Q9U 7X8 5PM |
ID | FETCH-LOGICAL-c566t-3aa6dc05c21ddd5dcd502076604fdd367adcc3b8e5840b8cec3d25473d8138643 |
IEDL.DBID | RPM |
ISSN | 2075-4418 |
IngestDate | Mon Sep 16 06:55:29 EDT 2024 Tue Sep 17 21:31:04 EDT 2024 Fri Sep 06 20:23:57 EDT 2024 Wed Sep 25 01:25:18 EDT 2024 Fri Feb 23 00:20:18 EST 2024 Fri Feb 02 04:38:21 EST 2024 Thu Sep 26 21:09:49 EDT 2024 Wed Oct 02 05:29:19 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 10 |
Keywords | faster R-CNN transfer learning bounding box loss multi-scale training cervical cancer |
Language | English |
License | Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c566t-3aa6dc05c21ddd5dcd502076604fdd367adcc3b8e5840b8cec3d25473d8138643 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9600700/ |
PMID | 36292166 |
PQID | 2728457108 |
PQPubID | 2032410 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_5bd07f3870f64b20aebe38d459d76bb2 pubmedcentral_primary_oai_pubmedcentral_nih_gov_9600700 proquest_miscellaneous_2729522965 proquest_journals_2728457108 gale_infotracmisc_A745500433 gale_infotracacademiconefile_A745500433 crossref_primary_10_3390_diagnostics12102477 pubmed_primary_36292166 |
PublicationCentury | 2000 |
PublicationDate | 2022-10-01 |
PublicationDateYYYYMMDD | 2022-10-01 |
PublicationDate_xml | – month: 10 year: 2022 text: 2022-10-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Switzerland |
PublicationPlace_xml | – name: Switzerland – name: Basel |
PublicationTitle | Diagnostics (Basel) |
PublicationTitleAlternate | Diagnostics (Basel) |
PublicationYear | 2022 |
Publisher | MDPI AG MDPI |
Publisher_xml | – name: MDPI AG – name: MDPI |
References | ref_50 Manna (ref_20) 2021; 11 Saslow (ref_6) 2012; 137 Xiang (ref_28) 2020; 40 ref_58 ref_13 ref_57 Shiraz (ref_5) 2020; 31 ref_56 ref_55 ref_54 ref_53 Mohammed (ref_18) 2021; 3 ref_52 ref_51 Yu (ref_22) 2021; 18 Lu (ref_62) 2016; 21 ref_59 Pal (ref_11) 2022; 150 ref_61 ref_60 Hu (ref_10) 2018; 83 Chen (ref_40) 2022; 41 ref_64 ref_63 Li (ref_38) 2021; 28 Pirovano (ref_31) 2021; 73 ref_26 Richardson (ref_8) 2011; 6 Xie (ref_33) 2018; 44 Rahaman (ref_1) 2020; 8 Albuquerque (ref_19) 2021; 7 Yosinski (ref_27) 2014; 27 Cheng (ref_36) 2021; 12 Shi (ref_23) 2021; 198 ref_34 ref_32 Jafarbigloo (ref_12) 2021; 6 Wu (ref_24) 2018; 38 ref_30 ref_39 Rahaman (ref_21) 2021; 136 Cao (ref_37) 2021; 73 Hussain (ref_17) 2020; 65 Li (ref_25) 2022; 74 Zhang (ref_14) 2017; 21 Liang (ref_29) 2021; 204 ref_47 ref_46 ref_45 ref_44 Lin (ref_16) 2019; 7 ref_43 ref_42 ref_41 ref_3 Chaturvedi (ref_4) 2012; 6 Liang (ref_35) 2021; 437 ref_2 Liu (ref_15) 2020; 20 ref_49 ref_48 ref_9 Parkin (ref_7) 2001; 2 |
References_xml | – volume: 12 start-page: 5639 year: 2021 ident: ref_36 article-title: Robust whole slide image analysis for cervical cancer screening using deep learning publication-title: Nat. Commun. doi: 10.1038/s41467-021-25296-x contributor: fullname: Cheng – ident: ref_9 – volume: 437 start-page: 195 year: 2021 ident: ref_35 article-title: Comparison detector for cervical cell/clumps detection in the limited data scenario publication-title: Neurocomputing doi: 10.1016/j.neucom.2021.01.006 contributor: fullname: Liang – volume: 21 start-page: 1633 year: 2017 ident: ref_14 article-title: DeepPap: Deep convolutional networks for cervical cell classification publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2017.2705583 contributor: fullname: Zhang – ident: ref_55 – ident: ref_26 – volume: 44 start-page: 245 year: 2018 ident: ref_33 article-title: Efficient and robust cell detection: A structured regression approach publication-title: Med. Image Anal. doi: 10.1016/j.media.2017.07.003 contributor: fullname: Xie – volume: 137 start-page: 516 year: 2012 ident: ref_6 article-title: American Cancer Society, American Society for Colposcopy and Cervical Pathology, and American Society for Clinical Pathology screening guidelines for the prevention and early detection of cervical cancer publication-title: Am. J. Clin. Pathol. doi: 10.1309/AJCPTGD94EVRSJCG contributor: fullname: Saslow – ident: ref_13 doi: 10.1049/cit2.12059 – ident: ref_39 – volume: 73 start-page: 102197 year: 2021 ident: ref_37 article-title: A novel attention-guided convolutional network for the detection of abnormal cervical cells in cervical cancer screening publication-title: Med. Image Anal. doi: 10.1016/j.media.2021.102197 contributor: fullname: Cao – ident: ref_45 doi: 10.1109/CVPR.2019.00075 – ident: ref_52 doi: 10.1007/978-3-319-46448-0_2 – volume: 150 start-page: 106083 year: 2022 ident: ref_11 article-title: Attention UW-Net: A fully connected model for automatic segmentation and annotation of chest X-ray publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2022.106083 contributor: fullname: Pal – volume: 20 start-page: 113 year: 2020 ident: ref_15 article-title: Artificial classification of cervical squamous lesions in ThinPrep cytologic tests using a deep convolutional neural network publication-title: Oncol. Lett. doi: 10.3892/ol.2020.11974 contributor: fullname: Liu – ident: ref_61 doi: 10.1109/ICIP.2018.8451588 – volume: 7 start-page: e457 year: 2021 ident: ref_19 article-title: Ordinal losses for classification of cervical cancer risk publication-title: PeerJ Comput. Sci. doi: 10.7717/peerj-cs.457 contributor: fullname: Albuquerque – ident: ref_54 doi: 10.1109/CVPR.2017.690 – volume: 6 start-page: 16 year: 2012 ident: ref_4 article-title: Epidemiology and clinical aspects of HPV in head and neck cancers publication-title: Head Neck Pathol. doi: 10.1007/s12105-012-0377-0 contributor: fullname: Chaturvedi – volume: 21 start-page: 441 year: 2016 ident: ref_62 article-title: Evaluation of three algorithms for the segmentation of overlapping cervical cells publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2016.2519686 contributor: fullname: Lu – volume: 6 start-page: 426 year: 2021 ident: ref_12 article-title: Nuclear atypia grading in breast cancer histopathological images based on CNN feature extraction and LSTM classification publication-title: CAAI Trans. Intell. Technol. doi: 10.1049/cit2.12061 contributor: fullname: Jafarbigloo – volume: 204 start-page: 106061 year: 2021 ident: ref_29 article-title: Global context-aware cervical cell detection with soft scale anchor matching publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2021.106061 contributor: fullname: Liang – ident: ref_32 doi: 10.1109/ISBI52829.2022.9761652 – ident: ref_48 – ident: ref_41 – ident: ref_51 doi: 10.1109/ICCV.2015.169 – ident: ref_60 doi: 10.1109/CVPRW50498.2020.00521 – volume: 8 start-page: 61687 year: 2020 ident: ref_1 article-title: A survey for cervical cytopathology image analysis using deep learning publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2983186 contributor: fullname: Rahaman – volume: 11 start-page: 14538 year: 2021 ident: ref_20 article-title: A fuzzy rank-based ensemble of CNN models for classification of cervical cytology publication-title: Sci. Rep. doi: 10.1038/s41598-021-93783-8 contributor: fullname: Manna – volume: 83 start-page: 134 year: 2018 ident: ref_10 article-title: Deep learning for image-based cancer detection and diagnosis-A survey publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.05.014 contributor: fullname: Hu – volume: 74 start-page: 101677 year: 2022 ident: ref_25 article-title: Cervical cell multi-classification algorithm using global context information and attention mechanism publication-title: Tissue Cell doi: 10.1016/j.tice.2021.101677 contributor: fullname: Li – ident: ref_59 – ident: ref_34 doi: 10.1007/978-3-030-32692-0_8 – volume: 40 start-page: 611 year: 2020 ident: ref_28 article-title: A novel automation-assisted cervical cancer reading method based on convolutional neural network publication-title: Biocybern. Biomed. Eng. doi: 10.1016/j.bbe.2020.01.016 contributor: fullname: Xiang – ident: ref_30 – ident: ref_3 – ident: ref_49 doi: 10.1109/CVPR.2017.106 – volume: 73 start-page: 102167 year: 2021 ident: ref_31 article-title: Computer-aided diagnosis tool for cervical cancer screening with weakly supervised localization and detection of abnormalities using adaptable and explainable classifier publication-title: Med. Image Anal. doi: 10.1016/j.media.2021.102167 contributor: fullname: Pirovano – volume: 198 start-page: 105807 year: 2021 ident: ref_23 article-title: Cervical cell classification with graph convolutional network publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2020.105807 contributor: fullname: Shi – volume: 31 start-page: 258 year: 2020 ident: ref_5 article-title: The early detection of cervical cancer. The current and changing landscape of cervical disease detection publication-title: Cytopathology doi: 10.1111/cyt.12835 contributor: fullname: Shiraz – volume: 38 start-page: BSR20181769 year: 2018 ident: ref_24 article-title: Automatic classification of cervical cancer from cytological images by using convolutional neural network publication-title: Biosci. Rep. doi: 10.1042/BSR20181769 contributor: fullname: Wu – volume: 27 start-page: 3320 year: 2014 ident: ref_27 article-title: How transferable are features in deep neural networks? publication-title: Adv. Neural Inf. Process. Syst. NIPS contributor: fullname: Yosinski – volume: 65 start-page: 101347 year: 2020 ident: ref_17 article-title: A comprehensive study on the multi-class cervical cancer diagnostic prediction on pap smear images using a fusion-based decision from ensemble deep convolutional neural network publication-title: Tissue Cell doi: 10.1016/j.tice.2020.101347 contributor: fullname: Hussain – volume: 28 start-page: 3585 year: 2021 ident: ref_38 article-title: Detection of cervical cancer cells in whole slide images using deformable and global context aware faster RCNN-FPN publication-title: Curr. Oncol. doi: 10.3390/curroncol28050307 contributor: fullname: Li – ident: ref_63 – ident: ref_53 doi: 10.1109/CVPR.2016.91 – ident: ref_56 doi: 10.1109/ICCV.2017.324 – volume: 41 start-page: 2432 year: 2022 ident: ref_40 article-title: A Task Decomposing and Cell Comparing Method for Cervical Lesion Cell Detection publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2022.3163171 contributor: fullname: Chen – volume: 3 start-page: 11 year: 2021 ident: ref_18 article-title: Single-cell conventional pap smear image classification using pre-trained deep neural network architectures publication-title: BMC Biomed. Eng. doi: 10.1186/s42490-021-00056-6 contributor: fullname: Mohammed – volume: 136 start-page: 104649 year: 2021 ident: ref_21 article-title: DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2021.104649 contributor: fullname: Rahaman – ident: ref_46 doi: 10.1609/aaai.v34i07.6999 – ident: ref_2 – volume: 18 start-page: 1740 year: 2021 ident: ref_22 article-title: Generative adversarial network based data augmentation to improve cervical cell classification model publication-title: Math. Biosci. Eng. doi: 10.3934/mbe.2021090 contributor: fullname: Yu – ident: ref_42 doi: 10.1109/CVPR.2009.5206848 – volume: 2 start-page: 533 year: 2001 ident: ref_7 article-title: Global cancer statistics in the year 2000 publication-title: Lancet Oncol. doi: 10.1016/S1470-2045(01)00486-7 contributor: fullname: Parkin – ident: ref_47 doi: 10.1109/CVPR.2016.90 – ident: ref_43 doi: 10.1007/978-3-319-10602-1_48 – ident: ref_64 – volume: 6 start-page: 343 year: 2011 ident: ref_8 article-title: Optimizing technology for cervical cancer screening in high-resource settings publication-title: Expert Rev. Obstet. Gynecol. doi: 10.1586/eog.11.13 contributor: fullname: Richardson – volume: 7 start-page: 71541 year: 2019 ident: ref_16 article-title: Fine-grained classification of cervical cells using morphological and appearance based convolutional neural networks publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2919390 contributor: fullname: Lin – ident: ref_58 doi: 10.1016/j.media.2022.102691 – ident: ref_57 – ident: ref_44 doi: 10.1145/2964284.2967274 – ident: ref_50 doi: 10.1109/CVPR.2014.81 |
SSID | ssj0000913825 |
Score | 2.2874506 |
Snippet | Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical... |
SourceID | doaj pubmedcentral proquest gale crossref pubmed |
SourceType | Open Website Open Access Repository Aggregation Database Index Database |
StartPage | 2477 |
SubjectTerms | Algorithms bounding box loss Cellular biology Cervical cancer Classification Datasets Deep learning Developing countries Diagnosis faster R-CNN Health aspects Human papillomavirus LDCs Localization Machine learning Medical research Medical screening multi-scale training Neural networks transfer learning Womens health |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwELUQh4oL6gelaWnlSpV6abRJ_H2kKQgqwalI3KzY47RINCB2OfDvO-OE1Uat1AvXtaON33hmnpXxG8Y-YQ4yOtq-lM6KUtYduVTsShl7kSDUqZJ0wfnsXJ9cyO-X6nKj1RfVhI3ywCNwCxWgMr3AbdVrGZqqw38VFqRyYHQIY_St1cZhKsdgR9p6apQZEniuX8BYuUbax1kzSxozS0VZsf_vuLyRmOZFkxtZ6Pg5253oIz8cX_sF20rDS_bsbPpA_oqdttn3cUqbrq8XLYae2yX_lla54mrgVwNvH3LL2gd--htjyZLnogGec1af7vgkuPpzj10cH_1oT8qpW0IZkZKtStF1GmKlYlMDgIIICqmg0RrRBhDadBCjCDYh5aiCjSkKaKjzMFjEConJa7Y93AzpDeNOWbANps9I3z2hcTH2yDSQvQSne2kL9uUROH87imJ4PEwQzv4fOBfsK4G7nkqK1vkHtLOf7Oz_Z-eCfSbTePI7xD920_UBfGNSsPKHhu5nkxxbwQ5mM9Ff4nz40bh-8telbwymaYVsC9f2cT1MT1IN2pBu7vMch2zVaVWw_XEvrJeENMA1tdYFM7NdMlvzfGS4-pXVvB11CKiqt08B0ju209D1jFxseMC2V3f36T2SplX4kP3jD-TRFjI priority: 102 providerName: Directory of Open Access Journals – databaseName: AUTh Library subscriptions: ProQuest Central dbid: BENPR link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3da9RAEB9qC-KL-G20SgTBF8Mlu8nu5kna2HIVWkQs9C1kdza1UHPnXfrQ_96ZTe5sUHzNbkgymY_f7s78BuA9xSCtnGmTvDQyybOGTco1Se5a6dFmPs25wPn0TM3P8y8XxcUOzDe1MJxWufGJwVHjwvEe-UxocqSF5q41jeVdANfPPi1_Jdw_is9Zx2Ya92BPZDkf2O4dHp19_bbdb2H-S1oNDcRDklb6Mxxy2ZgNObBo5VpPglPg8P_bU98JVdM0yjtx6fgRPBwBZXwwaMBj2PHdE7h_Oh6ZP4WTKngDmlL56-tZRc5ouY4_-z7kYHXxVRdXt6GJ7W188pO8yzoOaQRxiGKtX8UjBevlMzg_PvpezZOxf0LiCKT1iWwahS4tnMgQsUCHBYFDrRTJH1Eq3aBz0hpPICS1xnknUXAvYjQkK4Iqz2G3W3T-JcRlYdAICqiOT0JRlM61hD0Iz9hStbmJ4ONGcPVyoMmoaXnBcq7_IecIDlm426nMcR0uLFaX9WgydWEx1a0kh9LSY0TakL5Jg3lRolbWigg-8K-p2RJZH5qxoIDemDmt6gPNFdtM0BbB_mQmWZCbDm9-bj1a8Lr-o28RvNsO852cldb5xU2YUxJ-LVURwYtBF7afRMCgFJlSEeiJlky-eTrSXf0I_N4l9wxI01f_f63X8EBwKUZILNyH3X51498QQOrt21H3fwP01xJa priority: 102 providerName: ProQuest – databaseName: Scholars Portal Open Access Journals dbid: M48 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEB6VIiEuiDeBgoyExIXQrJ_xAaESqFqk5cRKvVmJ7ZRKS7bsbiX23zPjZFeNKBeusa3E43l8Vma-AXiDMchoX7a5tKXI5aQmk_J1Ln0rYmgmsZBU4Dz9pk9m8uuZOtuDbVfUQYCrG6921E9qtpy___1r8xEN_gPdOPHKfhj6pDSiNU50WNKYW3CbSyFJ5acD3k-u2RLlnurZh_61dhShEpH_3-76Wrwa51JeC07H9-HegCrZUa8GD2Avdg_hznT4b_4ITqvkEnBKFefzwwo90uWKfY7rlIjVsYuOVZvUyXbDTn-ii1mxlEvAUihr45INPKznj2F2_OV7dZIPTRRyj0htnYu61sEXyvNJCEEFHxQiRKM1HkIIQps6eC-aMiISKZrSRy8Cp4bEoURZIV55AvvdoovPgFlVhpJjVPX0OzRw632LAARBTWN1K8sM3m0F5y57rgyHdwySs7tBzhl8IuHuphLRdXqwWJ67wW6cakJhWoFepcXX8KJGpRNlkMoGo5uGZ_CWjsaRgqD8fT1UFeAXE7GVOzJUtk0sbRkcjGaiGfnx8PZw3VYLHTcYvRWCMNzb690wraTUtC4urtIciyDWapXB014XdltCdGD5ROsMzEhLRnsej3QXPxLJt6XGAUXx_L9XvoC7nEo1UuLhAeyvl1fxJQKodfMqGcUfLFoeaA priority: 102 providerName: Scholars Portal |
Title | Cervical Cell/Clumps Detection in Cytology Images Using Transfer Learning |
URI | https://www.ncbi.nlm.nih.gov/pubmed/36292166 https://www.proquest.com/docview/2728457108/abstract/ https://www.proquest.com/docview/2729522965/abstract/ https://pubmed.ncbi.nlm.nih.gov/PMC9600700 https://doaj.org/article/5bd07f3870f64b20aebe38d459d76bb2 |
Volume | 12 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Na9swFH-0HYxdxr7nrQsaDHaZa8eyvo6t19IOUspYoTdhfbgLJE5I0kP_-z3JTojZTrv4YMnYenofP1nv_QTwBWOQ4FY2aakkTctxHUzK1mlpG-qdGfu8DAXOk2t-eVv-uGN3B8C2tTAxad-a6Uk7m5-0098xt3I5t9k2Tyy7mVQqkKrneXYIh4LSvSV6dL8q0OqxjmGI4pI-c13SWqA9jnRZpRCDKBTJ-v92yXsxaZgvuReALl7A8x45ktPuC1_CgW9fwdNJvzf-Gq6qaPbYpfKzWVah11muyXe_iclWLZm2pHqMp9U-kqs5upE1ifkCJIarxq9Iz7V6_wZuL85_VZdpf1BCahGNbVJa19zZnNli7JxjzjqGKFBwjoJ2jnJRO2upkR7RRm6k9Za6Ihw67CTKCjHJWzhqF61_D0Qx6WSBkdOGLU9XKGsbBBkIXIziTSkT-LYVnF52fBga1xFBzvofck7gLAh31zWQWccbi9W97qdUM-Ny0VD0HA2-pshrVCwqXcmUE9yYIoGvYWp0MDmUv637ygH84kBepU9FKM0OTGwJHA96oqnYYfN2cnVvqmtdCIzQDIEWju3zrjk8GdLPWr94iH0UAlXFWQLvOl3YDQkRgCrGnCcgBloyGPOwBfU6Enn3evzhv5_8CM-KUI4RkwuP4WizevCfECRtzAienJ1f3_wcxZ8MeJ2UchQN5Q-2axfS |
link.rule.ids | 230,315,733,786,790,870,891,2115,2236,21416,24346,27957,27958,33779,33780,43840,53827,53829,74659 |
linkProvider | National Library of Medicine |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3fb9MwED5BJwEviJ8jY0CQkHghamontvOEtrCphbVCaJP2ZiW2MyaNtGu7h_333DluWQTiNXYU5-y7-2zffQfwAX2QFEY1SVYonmSjilTKVElmGu5sPXJpRgnO05kYn2Vfz_PzcOC2CmGVG5voDbWdGzojHzKJhjRHf6g-L64TqhpFt6uhhMZ92Mk4blUGsHN4NPv-Y3vKQqyXuAfq6IY47u-HtotgIw5kz52VSdlzSZ65_2_7fMdB9YMn73ij4yfwOMDI-KCb96dwz7XP4ME0XJQ_h0npbQB2Kd3V1bBEE7RYxV_c2kdetfFlG5e3vnTtbTz5hTZlFfvggdj7rsYt40C8evECzo6PTstxEqomJAah2TrhVSWsSXPDRtba3BqbIySUQqDUreVCVtYYXiuH0COtlXGGW0YViK1CWSFAeQmDdt66VxAXubKKoRs1dP9pWWFMg4gDUUxdiCZTEXzaCE4vOnIMjZsKkrP-h5wjOCThbrsSs7V_MF9e6KAoOq9tKhuOZqTBz7C0wlXGlc3ywkpR1yyCjzQ1mvQP5W-qkEaAIyYmK30gKU-baNki2O_1RL0x_ebN5Oqgtyv9Z5VF8H7bTG9SLFrr5je-T4GotRB5BLvdWtj-EsKBgo2EiED2Vknvn_st7eVPz-pdUKWANN37_7DewcPx6fREn0xm317DI0bJGD60cB8G6-WNe4MQaV2_DXrwGwKOEY0 |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT9swED9tIKG9IPZJNtgyadJeFjVNYjt5QhCo6DYqNA2JNyvxOQyJpaUtD_z33DluR7Rpr7GjOOf7-Nk-_w7gE8UgJU3eRFmRp1E2rNikTBVlpkkt1kMbZ3zB-WwiTy-yr5fi0uc_LXxa5conOkeNU8N75INEkSMViqvWND4t4vx4dDC7jbiCFJ-0-nIaT2FTZVKQhm8enUzOf6x3XJgBk9ZDHfVQSmv9AXbZbMyH7Hi0MqV64cmx-P_tqx8Fq34i5aPINNqBbQ8pw8NOB57DE9u-gK0zf2j-Esal8wfUpbQ3N4OS3NFsER7bpcvCasPrNizvXRnb-3D8m_zLInSJBKGLY42dh56E9eoVXIxOfpanka-gEBmCacsorSqJJhYmGSKiQIOC4KGSkmYAMZWqQmPSOrcEQ-I6N9akmHA1YsxJVgRWXsNGO23tLoSFyDFPKKQaPgvFpDCmIfRBiKYuZJPlAXxZCU7POqIMTQsMlrP-h5wDOGLhrrsyy7V7MJ1faW80WtQYqyYll9LQZ5K4Io1Lc8xEgUrWdRLAZ54azbZI8jeVv1JAI2ZWK32o-M42U7QFsNfrSTZk-s2rydXehhf6j8YF8HHdzG9yXlprp3euT0EItpAigDedLqx_iaBBkQylDED1tKT3z_2W9vqXY_guuGpAHL_9_7A-wBaZgP4-nnx7B88Svpfhsgz3YGM5v7P7hJaW9XtvBg_gghXK |
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=Cervical+Cell%2FClumps+Detection+in+Cytology+Images+Using+Transfer+Learning&rft.jtitle=Diagnostics+%28Basel%29&rft.au=Xu%2C+Chuanyun&rft.au=Li%2C+Mengwei&rft.au=Li%2C+Gang&rft.au=Zhang%2C+Yang&rft.date=2022-10-01&rft.pub=MDPI&rft.eissn=2075-4418&rft.volume=12&rft.issue=10&rft_id=info:doi/10.3390%2Fdiagnostics12102477&rft.externalDBID=PMC9600700 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2075-4418&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2075-4418&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2075-4418&client=summon |