PKA2-Net: Prior Knowledge-Based Active Attention Network for Accurate Pneumonia Diagnosis on Chest X-Ray Images

To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA 2 -Net 1 ) was constructed. The PKA 2 -Net uses improved ResNet as the backbone network and consists of residual blocks, novel subject enhancement and bac...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics Vol. 27; no. 7; pp. 3513 - 3524
Main Authors: Fu, Yu, Xue, Peng, Zhang, Zhili, Dong, Enqing
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.07.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:2168-2194, 2168-2208, 2168-2208
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA 2 -Net 1 ) was constructed. The PKA 2 -Net uses improved ResNet as the backbone network and consists of residual blocks, novel subject enhancement and background suppression (SEBS) blocks and candidate template generators, where template generators are designed to generate candidate templates for characterizing the importance of different spatial locations in feature maps. The core of PKA 2 -Net is SEBS block, which is proposed based on the prior knowledge that highlighting distinctive features and suppressing irrelevant features can improve the recognition effect. The purpose of SEBS block is to generate active attention features without any high-level features and enhance the ability of the model to localize lung lesions. In SEBS block, first, a series of candidate templates T with different spatial energy distributions are generated and the controllability of the energy distribution in T enables active attention features to maintain the continuity and integrity of the feature space distributions. Second, Top- n templates are selected from T according to certain learning rules, which are then operated by a convolution layer for generating supervision information that can guide the inputs of SEBS block to form active attention features. We evaluated the PKA 2 -Net on the binary classification problem of identifying pneumonia and healthy controls on a dataset containing 5856 chest X-ray images (ChestXRay2017), the results showed that our method can achieve 97.63% accuracy and 0.9872 sensitivity.
AbstractList To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA2-Net1) was constructed. The PKA2-Net uses improved ResNet as the backbone network and consists of residual blocks, novel subject enhancement and background suppression (SEBS) blocks and candidate template generators, where template generators are designed to generate candidate templates for characterizing the importance of different spatial locations in feature maps. The core of PKA2-Net is SEBS block, which is proposed based on the prior knowledge that highlighting distinctive features and suppressing irrelevant features can improve the recognition effect. The purpose of SEBS block is to generate active attention features without any high-level features and enhance the ability of the model to localize lung lesions. In SEBS block, first, a series of candidate templates T with different spatial energy distributions are generated and the controllability of the energy distribution in T enables active attention features to maintain the continuity and integrity of the feature space distributions. Second, Top- n templates are selected from T according to certain learning rules, which are then operated by a convolution layer for generating supervision information that can guide the inputs of SEBS block to form active attention features. We evaluated the PKA2-Net on the binary classification problem of identifying pneumonia and healthy controls on a dataset containing 5856 chest X-ray images (ChestXRay2017), the results showed that our method can achieve 97.63% accuracy and 0.9872 sensitivity.
To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA2-Net1) was constructed. The PKA2-Net uses improved ResNet as the backbone network and consists of residual blocks, novel subject enhancement and background suppression (SEBS) blocks and candidate template generators, where template generators are designed to generate candidate templates for characterizing the importance of different spatial locations in feature maps. The core of PKA2-Net is SEBS block, which is proposed based on the prior knowledge that highlighting distinctive features and suppressing irrelevant features can improve the recognition effect. The purpose of SEBS block is to generate active attention features without any high-level features and enhance the ability of the model to localize lung lesions. In SEBS block, first, a series of candidate templates T with different spatial energy distributions are generated and the controllability of the energy distribution in T enables active attention features to maintain the continuity and integrity of the feature space distributions. Second, Top-n templates are selected from T according to certain learning rules, which are then operated by a convolution layer for generating supervision information that can guide the inputs of SEBS block to form active attention features. We evaluated the PKA2-Net on the binary classification problem of identifying pneumonia and healthy controls on a dataset containing 5856 chest X-ray images (ChestXRay2017), the results showed that our method can achieve 97.63% accuracy and 0.9872 sensitivity.To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA2-Net1) was constructed. The PKA2-Net uses improved ResNet as the backbone network and consists of residual blocks, novel subject enhancement and background suppression (SEBS) blocks and candidate template generators, where template generators are designed to generate candidate templates for characterizing the importance of different spatial locations in feature maps. The core of PKA2-Net is SEBS block, which is proposed based on the prior knowledge that highlighting distinctive features and suppressing irrelevant features can improve the recognition effect. The purpose of SEBS block is to generate active attention features without any high-level features and enhance the ability of the model to localize lung lesions. In SEBS block, first, a series of candidate templates T with different spatial energy distributions are generated and the controllability of the energy distribution in T enables active attention features to maintain the continuity and integrity of the feature space distributions. Second, Top-n templates are selected from T according to certain learning rules, which are then operated by a convolution layer for generating supervision information that can guide the inputs of SEBS block to form active attention features. We evaluated the PKA2-Net on the binary classification problem of identifying pneumonia and healthy controls on a dataset containing 5856 chest X-ray images (ChestXRay2017), the results showed that our method can achieve 97.63% accuracy and 0.9872 sensitivity.
To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA 2 -Net 1 ) was constructed. The PKA 2 -Net uses improved ResNet as the backbone network and consists of residual blocks, novel subject enhancement and background suppression (SEBS) blocks and candidate template generators, where template generators are designed to generate candidate templates for characterizing the importance of different spatial locations in feature maps. The core of PKA 2 -Net is SEBS block, which is proposed based on the prior knowledge that highlighting distinctive features and suppressing irrelevant features can improve the recognition effect. The purpose of SEBS block is to generate active attention features without any high-level features and enhance the ability of the model to localize lung lesions. In SEBS block, first, a series of candidate templates T with different spatial energy distributions are generated and the controllability of the energy distribution in T enables active attention features to maintain the continuity and integrity of the feature space distributions. Second, Top- n templates are selected from T according to certain learning rules, which are then operated by a convolution layer for generating supervision information that can guide the inputs of SEBS block to form active attention features. We evaluated the PKA 2 -Net on the binary classification problem of identifying pneumonia and healthy controls on a dataset containing 5856 chest X-ray images (ChestXRay2017), the results showed that our method can achieve 97.63% accuracy and 0.9872 sensitivity.
Author Xue, Peng
Zhang, Zhili
Fu, Yu
Dong, Enqing
Author_xml – sequence: 1
  givenname: Yu
  orcidid: 0000-0002-2413-3858
  surname: Fu
  fullname: Fu, Yu
  email: yufu_2020@yeah.net
  organization: School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai, China
– sequence: 2
  givenname: Peng
  surname: Xue
  fullname: Xue, Peng
  email: xue.peng@sdu.edu.cn
  organization: School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai, China
– sequence: 3
  givenname: Zhili
  orcidid: 0000-0002-7105-1126
  surname: Zhang
  fullname: Zhang, Zhili
  email: zzl_cherish@163.com
  organization: School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai, China
– sequence: 4
  givenname: Enqing
  orcidid: 0000-0002-1013-7639
  surname: Dong
  fullname: Dong, Enqing
  email: enqdong@sdu.edu.cn
  organization: School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai, China
BookMark eNpdz01PAjEQBuDGYASRH2DioYkXL4v9YNuutwU_QIgSo4k3UroDFqHF7a6Ef28T9OJcZjJ5MnnnFDWcd4DQOSVdSkl2_dgfjrqMMN7lTEiSyiPUYlSohDGiGn8zzXpN1AlhRWKpuMrECWry6BWXrIX8dJyz5AmqGzwtrS_x2PndGoolJH0doMC5qew34LyqwFXWOxztzpefeBFxbkxd6grw1EG98c5qfGv10vlgA4528AGhwu_Ji97j0UYvIZyh44VeB-j89jZ6u797HQyTyfPDaJBPEkuFrBLg1BRapVxLxgBomjJegJFiTrOFLKjRmUk5lyBUOi96C6OlEFrFr2SPZrTgbXR1uLst_VcdU8w2NhhYr7UDX4cZU4RmMiOER3r5j658XbqYLipOU6KY6EV1cVAWAGbb0m50uZ9RQglLueI_NcV14w
CODEN IJBHA9
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
K9.
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
DOI 10.1109/JBHI.2023.3267057
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Ceramic Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
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
Nursing & Allied Health Premium
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle Materials Research Database
Civil Engineering Abstracts
Aluminium Industry Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Health & Medical Complete (Alumni)
Ceramic Abstracts
Materials Business File
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Aerospace Database
Nursing & Allied Health Premium
Engineered Materials Abstracts
Biotechnology Research Abstracts
Solid State and Superconductivity Abstracts
Engineering Research Database
Corrosion Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
MEDLINE - Academic
DatabaseTitleList Materials Research Database
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2168-2208
EndPage 3524
ExternalDocumentID 10102538
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62171261; 81671848; 81371635
  funderid: 10.13039/501100001809
– fundername: Innovation Ability Improvement Project of Science and Technology Small and Medium-sized Enterprises of Shandong Province
  grantid: 2021TSGC1028
– fundername: Fundamental Research Funds for the Central Universities
  funderid: 10.13039/501100012226
GroupedDBID 0R~
4.4
6IF
6IH
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
K9.
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
ID FETCH-LOGICAL-i167t-e31cda853a722ee15523dec76b19f7d1ca9c5337e685bd4fca766a805874191d3
IEDL.DBID RIE
ISICitedReferencesCount 8
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001022230000036&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2168-2194
2168-2208
IngestDate Sun Sep 28 12:02:54 EDT 2025
Sun Nov 09 07:26:38 EST 2025
Wed Aug 27 02:25:49 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i167t-e31cda853a722ee15523dec76b19f7d1ca9c5337e685bd4fca766a805874191d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-2413-3858
0000-0002-1013-7639
0000-0002-7105-1126
PMID 37058372
PQID 2831508264
PQPubID 85417
PageCount 12
ParticipantIDs proquest_journals_2831508264
ieee_primary_10102538
proquest_miscellaneous_2801979003
PublicationCentury 2000
PublicationDate 2023-07-01
PublicationDateYYYYMMDD 2023-07-01
PublicationDate_xml – month: 07
  year: 2023
  text: 2023-07-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE journal of biomedical and health informatics
PublicationTitleAbbrev JBHI
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
SSID ssj0000816896
Score 2.4250052
Snippet To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA 2 -Net 1 )...
To accurately diagnose pneumonia patients on a limited annotated chest X-ray image dataset, a prior knowledge-based active attention network (PKA2-Net1) was...
SourceID proquest
ieee
SourceType Aggregation Database
Publisher
StartPage 3513
SubjectTerms active attention features
Adaptation models
candidate templates
Chest
Computer networks
Data models
Datasets
Deep learning
Energy distribution
Feature extraction
Feature maps
Generators
Medical diagnosis
Medical imaging
Pneumonia
Pneumonia diagnosis
prior knowledge
Pulmonary diseases
subject enhancement and background suppression block
Task analysis
X-ray imaging
Title PKA2-Net: Prior Knowledge-Based Active Attention Network for Accurate Pneumonia Diagnosis on Chest X-Ray Images
URI https://ieeexplore.ieee.org/document/10102538
https://www.proquest.com/docview/2831508264
https://www.proquest.com/docview/2801979003
Volume 27
WOSCitedRecordID wos001022230000036&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2168-2208
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816896
  issn: 2168-2194
  databaseCode: RIE
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED90iPji58TpHBF8zezXmsa3OR1-4BiisLeRJjfog61sreB_7yXtfBEffGogoZTLXe7Xu8v9AC6l8kwQSOQmwgUnF5DwVCSSi1TKSIt0EArlyCbEZJLMZnLaXFZ3d2EQ0RWfYd8OXS7fFLqyoTKycHKHZKGbsClEXF_W-gmoOAYJx8cV0ICTJUZNFtP35NXjzf1D31KF9wmvCAIpO7Ad0pP-z4KGWOXXaexczHjvnx-3D7sNlmTDevMPYAPzQ9h-brLlR1BMn4YBn2B5zabLrFiyp3UAjd-Q8zJs6A47NizLuuiRTeqicEZIliZ1ZftIsGmOFSlrpthtXZeXrRitHVmmLTbjL-qLPbzTsbRqw9v47nV0zxuCBZ75sSg5hr42ihy2EkGAaLuxhQa1iFNfLoTxtZKa4KDAOBmkJlpoJeJYJSQ1wiHSN-ExtPIixxNgcuCZWBmNkUqiRZqoCFWUhkg_TJ6vvbQDbSuy-UfdQ2O-llYHumuhzxvrWc0J8tg29YTVOnDxM016b5MZKseismsInAobhz3949VnsGM3vK6t7UKrXFZ4Dlv6s8xWyx6p0CzpORX6BsXJwXs
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9swDCa2ruh62bPD0nWbBvSqzA_FsnpL0wbJ0hpB0QK5GbLEAD7UHhJ7wP59KdnppeihJwuQIBiUKH4iKX4Ap0oHNooUcitwzckEpLyQqeKyUEoYWYxiqT3ZhMyydLVSy_6xun8Lg4g--QyHrulj-bY2rXOVkYaTOSQNfQ1vRkJEQfdc69Gl4jkkPCNXRA1Ouij6OGYYqN9_zmfzoSMLHxJikQRTDuEgpi_d0KKeWuXJeeyNzPT9C3_vA7zr0SQbd8v_EV5h9QkOrvt4-Weol4txxDNszthyU9Ybtti50Pg5mS_Lxv64Y-Om6dIeWdalhTPCstRpWldJgi0rbGm7lppddJl55ZbR2Inj2mIrfqP_s_k9HUzbI7ibXt5OZrynWOBlmMiGYxwaq8lkaxlFiK4eW2zRyKQI1Vra0GhlCBBKTNJRYcXaaJkkOiWpERJRoY2_wF5VV_gVmBoFNtHWoNCpWBepFqhFESNdmYLQBMUAjpzI8r9dFY18J60BnOyEnvf6s80J9LhC9YTWBvDrsZt2vgtn6Arr1o0heCqdJ_b4mal_wtvZ7fVVfjXPFt_g0C1-l2l7AnvNpsXvsG_-NeV288NvpAdyT8Pa
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=PKA2-Net%3A+Prior+Knowledge-Based+Active+Attention+Network+for+Accurate+Pneumonia+Diagnosis+on+Chest+X-Ray+Images&rft.jtitle=IEEE+journal+of+biomedical+and+health+informatics&rft.au=Fu%2C+Yu&rft.au=Xue%2C+Peng&rft.au=Zhang%2C+Zhili&rft.au=Dong%2C+Enqing&rft.date=2023-07-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=2168-2194&rft.eissn=2168-2208&rft.volume=27&rft.issue=7&rft.spage=3513&rft_id=info:doi/10.1109%2FJBHI.2023.3267057&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2194&client=summon