Automatic tissue characterization of air trapping in chest radiographs using deep neural networks
Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar initiatives in chest radiographs (CXR), the common modality for pulmonary diagnosis, are much less developed. CXR are fast, cost effective and...
Saved in:
| Published in: | 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Vol. 2016; pp. 97 - 100 |
|---|---|
| Main Authors: | , , , |
| Format: | Conference Proceeding Journal Article |
| Language: | English |
| Published: |
United States
IEEE
01.08.2016
|
| Subjects: | |
| ISSN: | 1557-170X, 2694-0604, 2694-0604 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar initiatives in chest radiographs (CXR), the common modality for pulmonary diagnosis, are much less developed. CXR are fast, cost effective and low-radiation solution to diagnosis over CT. However, the subtlety of textures in CXR makes them hard to discern even by trained eye. We explore the performance of deep learning abnormal tissue characterization from CXR. Prior studies have used CT imaging to characterize air trapping in subjects with pulmonary disease; however, the use of CT in children is not recommended mainly due to concerns pertaining to radiation dosage. In this work, we present a stacked autoencoder (SAE) deep learning architecture for automated tissue characterization of air-trapping from CXR. To our best knowledge this is the first study applying deep learning framework for the specific problem on 51 CXRs, an F-score of ≈ 76.5% and a strong correlation with the expert visual scoring (R=0.93, p =<; 0.01) demonstrate the potential of the proposed method to characterization of air trapping. |
|---|---|
| AbstractList | Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar initiatives in chest radiographs (CXR), the common modality for pulmonary diagnosis, are much less developed. CXR are fast, cost effective and low-radiation solution to diagnosis over CT. However, the subtlety of textures in CXR makes them hard to discern even by trained eye. We explore the performance of deep learning abnormal tissue characterization from CXR. Prior studies have used CT imaging to characterize air trapping in subjects with pulmonary disease; however, the use of CT in children is not recommended mainly due to concerns pertaining to radiation dosage. In this work, we present a stacked autoencoder (SAE) deep learning architecture for automated tissue characterization of air-trapping from CXR. To our best knowledge this is the first study applying deep learning framework for the specific problem on 51 CXRs, an F-score of ≈ 76.5% and a strong correlation with the expert visual scoring (R=0.93, p =<; 0.01) demonstrate the potential of the proposed method to characterization of air trapping. Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar initiatives in chest radiographs (CXR), the common modality for pulmonary diagnosis, are much less developed. CXR are fast, cost effective and low-radiation solution to diagnosis over CT. However, the subtlety of textures in CXR makes them hard to discern even by trained eye. We explore the performance of deep learning abnormal tissue characterization from CXR. Prior studies have used CT imaging to characterize air trapping in subjects with pulmonary disease; however, the use of CT in children is not recommended mainly due to concerns pertaining to radiation dosage. In this work, we present a stacked autoencoder (SAE) deep learning architecture for automated tissue characterization of air-trapping from CXR. To our best knowledge this is the first study applying deep learning framework for the specific problem on 51 CXRs, an F-score of ≈ 76.5% and a strong correlation with the expert visual scoring (R=0.93, p =<; 0.01) demonstrate the potential of the proposed method to characterization of air trapping.Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar initiatives in chest radiographs (CXR), the common modality for pulmonary diagnosis, are much less developed. CXR are fast, cost effective and low-radiation solution to diagnosis over CT. However, the subtlety of textures in CXR makes them hard to discern even by trained eye. We explore the performance of deep learning abnormal tissue characterization from CXR. Prior studies have used CT imaging to characterize air trapping in subjects with pulmonary disease; however, the use of CT in children is not recommended mainly due to concerns pertaining to radiation dosage. In this work, we present a stacked autoencoder (SAE) deep learning architecture for automated tissue characterization of air-trapping from CXR. To our best knowledge this is the first study applying deep learning framework for the specific problem on 51 CXRs, an F-score of ≈ 76.5% and a strong correlation with the expert visual scoring (R=0.93, p =<; 0.01) demonstrate the potential of the proposed method to characterization of air trapping. Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar initiatives in chest radiographs (CXR), the common modality for pulmonary diagnosis, are much less developed. CXR are fast, cost effective and low-radiation solution to diagnosis over CT. However, the subtlety of textures in CXR makes them hard to discern even by trained eye. We explore the performance of deep learning abnormal tissue characterization from CXR. Prior studies have used CT imaging to characterize air trapping in subjects with pulmonary disease; however, the use of CT in children is not recommended mainly due to concerns pertaining to radiation dosage. In this work, we present a stacked autoencoder (SAE) deep learning architecture for automated tissue characterization of air-trapping from CXR. To our best knowledge this is the first study applying deep learning framework for the specific problem on 51 CXRs (≈ 76.5%, F-score) and a strong correlation with the expert visual scoring (R=0.93, p =< 0.01) demonstrate the potential of the proposed method to characterization of air trapping. |
| Author | Nino, Gustavo Perez, Geovanny Linguraru, Marius George Mansoor, Awais |
| AuthorAffiliation | b Division of Pulmonary and Sleep Medicine, Childrens National Health System, Washington, DC c School of Medicine and Health Sciences, George Washington University, DC a Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Health System, Washington DC |
| AuthorAffiliation_xml | – name: a Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Health System, Washington DC – name: c School of Medicine and Health Sciences, George Washington University, DC – name: b Division of Pulmonary and Sleep Medicine, Childrens National Health System, Washington, DC |
| Author_xml | – sequence: 1 givenname: Awais surname: Mansoor fullname: Mansoor, Awais organization: Children's Nat. Health Syst., Sheikh Zayed Inst. for Pediatric Surg. Innovation, Washington, DC, USA – sequence: 2 givenname: Geovanny surname: Perez fullname: Perez, Geovanny organization: Div. of Pulmonary & Sleep Med., ChildrenaAZs Nat. Health Syst., Washington, DC, USA – sequence: 3 givenname: Gustavo surname: Nino fullname: Nino, Gustavo organization: Div. of Pulmonary & Sleep Med., ChildrenaAZs Nat. Health Syst., Washington, DC, USA – sequence: 4 givenname: Marius George surname: Linguraru fullname: Linguraru, Marius George organization: Children's Nat. Health Syst., Sheikh Zayed Inst. for Pediatric Surg. Innovation, Washington, DC, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/28324924$$D View this record in MEDLINE/PubMed |
| BookMark | eNpVUcFu1DAQNaiIbks_ACEhH3vJYk9iO74glVULSEVcqNRbNEkmu4asHewE1H49rrpUcBrpvaf35s2csCMfPDH2Woq1lMK-u_zyYbMGIfXaKCt0ZZ-xE1kpYwSAMM_ZCrStCqFFdcRWUilTSCNuj9lZSt-FENJoXYJ6yY6hLqGyUK0YXixz2OPsOj67lBbi3Q4jdjNFd5_h4HkYOLrI54jT5PyWO581lGYesXdhm-Fd4kt6oHqiiXtaIo55zL9D_JFesRcDjonODvOU3Vxdftt8Kq6_fvy8ubguXAl2LpTpBdaVRmr7Ftq6zlWGQdsWyeAgAZWxYEF3PfVtmUFjW7AtoYGuVxLKU_b-0Xda2j31Hfm88dhM0e0x3jUBXfM_492u2YZfjaqUrWqbDc4PBjH8XHLBZu9SR-OInsKSGlnXQtQA8kH69t-sp5C_d82CN48CR0RP9OFr5R8dQYwG |
| ContentType | Conference Proceeding Journal Article |
| DBID | 6IE 6IH CBEJK RIE RIO CGR CUY CVF ECM EIF NPM 7X8 5PM |
| DOI | 10.1109/EMBC.2016.7590649 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library IEEE Proceedings Order Plans (POP) 1998-present Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| 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: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 1457702207 9781457702204 |
| EISSN | 2694-0604 |
| EndPage | 100 |
| ExternalDocumentID | PMC5459489 28324924 7590649 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: NICHD NIH HHS grantid: K12 HD001399 – fundername: NCATS NIH HHS grantid: UL1 TR000075 – fundername: NCATS NIH HHS grantid: UL1 TR001876 – fundername: NCATS NIH HHS grantid: KL2 TR000076 |
| GroupedDBID | 29F 29G 6IE 6IH 6IK 6IM ACGFS ALMA_UNASSIGNED_HOLDINGS CBEJK IPLJI M43 RIE RIO RNS CGR CUY CVF ECM EIF NPM 7X8 5PM |
| ID | FETCH-LOGICAL-i329t-57d0a846aebdb2b88694ff69bae7af12a5792926cdedb3ae779b29bea72cd5123 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 10 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000399823500025&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1557-170X 2694-0604 |
| IngestDate | Tue Sep 30 16:41:51 EDT 2025 Thu Oct 02 16:13:26 EDT 2025 Thu Jan 02 22:59:28 EST 2025 Wed Jun 26 19:26:30 EDT 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i329t-57d0a846aebdb2b88694ff69bae7af12a5792926cdedb3ae779b29bea72cd5123 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | http://doi.org/10.1109/EMBC.2016.7590649 |
| PMID | 28324924 |
| PQID | 1880082219 |
| PQPubID | 23479 |
| PageCount | 4 |
| ParticipantIDs | ieee_primary_7590649 pubmed_primary_28324924 pubmedcentral_primary_oai_pubmedcentral_nih_gov_5459489 proquest_miscellaneous_1880082219 |
| PublicationCentury | 2000 |
| PublicationDate | 20160801 |
| PublicationDateYYYYMMDD | 2016-08-01 |
| PublicationDate_xml | – month: 8 year: 2016 text: 20160801 day: 1 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) |
| PublicationTitleAbbrev | EMBC |
| PublicationTitleAlternate | Conf Proc IEEE Eng Med Biol Soc |
| PublicationYear | 2016 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0001766325 ssj0061641 ssib061542107 ssib053545923 ssib042469959 |
| Score | 2.1474674 |
| Snippet | Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar... |
| SourceID | pubmedcentral proquest pubmed ieee |
| SourceType | Open Access Repository Aggregation Database Index Database Publisher |
| StartPage | 97 |
| SubjectTerms | Air Charge carrier processes Computed tomography Diagnosis, Computer-Assisted Humans Image Processing, Computer-Assisted - methods Lung - diagnostic imaging Lungs Machine learning Neural Networks, Computer Radiography, Thoracic - methods Shape Training Virus Diseases - diagnostic imaging Visualization |
| Title | Automatic tissue characterization of air trapping in chest radiographs using deep neural networks |
| URI | https://ieeexplore.ieee.org/document/7590649 https://www.ncbi.nlm.nih.gov/pubmed/28324924 https://www.proquest.com/docview/1880082219 https://pubmed.ncbi.nlm.nih.gov/PMC5459489 |
| Volume | 2016 |
| WOSCitedRecordID | wos000399823500025&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 | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1LT8MwDICtgTjAhTeMxxQkjhS2pmnqIyAQB5h2AGm3Ka9CJdROe_D7idPRAeLCqVWbVmls1U5ifwY4511lNGY64kIlEaVqRornGAn_P1Y8S3WWh6olj7Lfz4ZDHLTgosmFcc6F4DN3SadhL99WZk5LZVdSoLeguAIrUso6V2u5niK97Vxy9lI_DahZqYIgiN3hYkez18Wru6ebWwrqSi8XLyQisNfsBCnvPRRZ-cvf_B02-c0O3W_-7wu2YG-Z0McGjanahpYrd2DjG4twF9T1fFYFfiubBWEw07Cc61RNVuVMFRPme0VQh1dWlCyU22ITZYsafT1lFEj_yqxzY0asTPXuDyHSfLoHL_d3z7cP0aL-QlTwGGeRkLarvH-inLY61lmWYpLnKWrlpMp7sRLSO1dxaqyzmvuLEnWM2ikZG-sdCb4Pq2VVukNgudZJInLHNWVBG4lWaIupdgnynhGmDbs0WKNxjdgYLcapDWdfYhh5tae9DFW6aj4dEUaOYPU93-agFkvz8Jcs2yB_CKxpQEjtn3fK4i2gtb0_iUmGR3935xjWSW3q-L8TWJ1N5u4U1syHl8uk47VymHWCVn4CNdviHg |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1LT9wwEIBHFCq1vUALtFsedaUeG9jEdpw5FgQCdVlxoNLeIr8CkVCC9tHfX4-zZKHiwilR4kSOZ5QZ2zPfAPzgQ20NFibhUouEUjUTzStMZPgfa17kpqhi1ZKRGo-LyQSv1-BnnwvjvY_BZ_6ITuNevmvtgpbKjpXEYEHxDWxIIbK0y9ZaraioYD1XpL08TAQ6WqokDOJwstzTTId4fHZ1ckphXfnR8pXEBA66LZAy32OZlZc8zv8DJ59YovPN133DFuysUvrYdW-sPsKabz7Bhyc0wm3QvxbzNhJc2TyKg9me5twla7K2YrqestArwjrcsrphseAWm2pXd_DrGaNQ-lvmvH9gRMvU9-EQY81nO_Dn_Ozm9CJZVmBIap7hPJHKDXXwULQ3zmSmKHIUVZWj0V7pKs20VMG9ynLrvDM8XFRoMjReq8y64ErwXVhv2sZ_AVYZI4SsPDeUB20VOmkc5sYL5KmVdgDbNFjlQwfZKJfjNIDvj2Iog-LTboZufLuYlQSSI1x9Gtp87sTSP_woywGoZwLrGxBU-_mdpr6LcO3gUaIo8OvL3fkG7y5urkbl6HL8ew_ekwp10YD7sD6fLvwBvLV_g4ymh1E3_wHEjOR9 |
| 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%3Abook&rft.genre=proceeding&rft.title=2016+38th+Annual+International+Conference+of+the+IEEE+Engineering+in+Medicine+and+Biology+Society+%28EMBC%29&rft.atitle=Automatic+tissue+characterization+of+air+trapping+in+chest+radiographs+using+deep+neural+networks&rft.au=Mansoor%2C+Awais&rft.au=Perez%2C+Geovanny&rft.au=Nino%2C+Gustavo&rft.au=Linguraru%2C+Marius+George&rft.date=2016-08-01&rft.pub=IEEE&rft.issn=1557-170X&rft.spage=97&rft.epage=100&rft_id=info:doi/10.1109%2FEMBC.2016.7590649&rft_id=info%3Apmid%2F28324924&rft.externalDocID=7590649 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1557-170X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1557-170X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1557-170X&client=summon |