Automatic photoacoustic monitoring of perinatal brain hypoxia with superior sagittal sinus detection
Despite advances in perinatal medicine over decades, perinatal hypoxic-ischemic encephalopathy (HIE) remains a significant cause of fetal cerebral palsy and can lead to other severe medical sequelae or death. Therefore, it is highly desirable to effectively detect brain hypoxia during labor and post...
Gespeichert in:
| Veröffentlicht in: | Journal of biomedical optics Jg. 30; H. 7; S. 076004 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
Society of Photo-Optical Instrumentation Engineers
01.07.2025
|
| Schlagworte: | |
| ISSN: | 1083-3668, 1560-2281, 1560-2281 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Despite advances in perinatal medicine over decades, perinatal hypoxic-ischemic encephalopathy (HIE) remains a significant cause of fetal cerebral palsy and can lead to other severe medical sequelae or death. Therefore, it is highly desirable to effectively detect brain hypoxia during labor and postnatally for HIE management.
We recently validated the feasibility of transcranial photoacoustic (PA) imaging for oxyhemoglobin saturation measurement at the superior sagittal sinus (
) in the neonatal piglet brain, at which overall oxygen supply status can be reflected as a primary collective vein. We aim to automate the PA-based workflow of at-risk subject detection and enable fully autonomous and continuous perinatal monitoring.
We proposed a two-step algorithm that focuses on the most informative region of the brain for oxygenation status, the superior sagittal sinus (SSS). First, a convolutional neural network (U-Net) is trained to detect the location of SSS in the coronal cross-section PA images. Then, an optimized region of interest patch around the predicted SSS location is cropped from the spectral unmixed image and averaged as the
measurement. A confidence score can be computed for the measurement via Monte Carlo dropout (MCD), which infers the prediction uncertainty for better clinical decision-making.
The algorithm was evaluated on an
piglet brain imaging dataset containing 84 independent experimental settings from 10 piglet subjects. A 10-fold leave-one-subject-out cross-validation experiment reports 85.2% sensitivity and 93.3% specificity for healthy/hypoxia classification with an
-squared value of 0.708 and a confidence score of 94.06% based on MCD computation, well agreed with our ground-truth given by blood gas measurements.
The proposed automatic
monitoring solution demonstrated a hypoxia detection capability comparable to the human expert manual annotation on the same task. We concluded with high feasibility for a noninvasive PA-based continuous monitoring of the perinatal brain. |
|---|---|
| AbstractList | Despite advances in perinatal medicine over decades, perinatal hypoxic-ischemic encephalopathy (HIE) remains a significant cause of fetal cerebral palsy and can lead to other severe medical sequelae or death. Therefore, it is highly desirable to effectively detect brain hypoxia during labor and postnatally for HIE management.SignificanceDespite advances in perinatal medicine over decades, perinatal hypoxic-ischemic encephalopathy (HIE) remains a significant cause of fetal cerebral palsy and can lead to other severe medical sequelae or death. Therefore, it is highly desirable to effectively detect brain hypoxia during labor and postnatally for HIE management.We recently validated the feasibility of transcranial photoacoustic (PA) imaging for oxyhemoglobin saturation measurement at the superior sagittal sinus ( O 2 Sat ss ) in the neonatal piglet brain, at which overall oxygen supply status can be reflected as a primary collective vein. We aim to automate the PA-based workflow of at-risk subject detection and enable fully autonomous and continuous perinatal monitoring.AimWe recently validated the feasibility of transcranial photoacoustic (PA) imaging for oxyhemoglobin saturation measurement at the superior sagittal sinus ( O 2 Sat ss ) in the neonatal piglet brain, at which overall oxygen supply status can be reflected as a primary collective vein. We aim to automate the PA-based workflow of at-risk subject detection and enable fully autonomous and continuous perinatal monitoring.We proposed a two-step algorithm that focuses on the most informative region of the brain for oxygenation status, the superior sagittal sinus (SSS). First, a convolutional neural network (U-Net) is trained to detect the location of SSS in the coronal cross-section PA images. Then, an optimized region of interest patch around the predicted SSS location is cropped from the spectral unmixed image and averaged as the O 2 Sat ss measurement. A confidence score can be computed for the measurement via Monte Carlo dropout (MCD), which infers the prediction uncertainty for better clinical decision-making.ApproachWe proposed a two-step algorithm that focuses on the most informative region of the brain for oxygenation status, the superior sagittal sinus (SSS). First, a convolutional neural network (U-Net) is trained to detect the location of SSS in the coronal cross-section PA images. Then, an optimized region of interest patch around the predicted SSS location is cropped from the spectral unmixed image and averaged as the O 2 Sat ss measurement. A confidence score can be computed for the measurement via Monte Carlo dropout (MCD), which infers the prediction uncertainty for better clinical decision-making.The algorithm was evaluated on an in vivo piglet brain imaging dataset containing 84 independent experimental settings from 10 piglet subjects. A 10-fold leave-one-subject-out cross-validation experiment reports 85.2% sensitivity and 93.3% specificity for healthy/hypoxia classification with an R -squared value of 0.708 and a confidence score of 94.06% based on MCD computation, well agreed with our ground-truth given by blood gas measurements.ResultsThe algorithm was evaluated on an in vivo piglet brain imaging dataset containing 84 independent experimental settings from 10 piglet subjects. A 10-fold leave-one-subject-out cross-validation experiment reports 85.2% sensitivity and 93.3% specificity for healthy/hypoxia classification with an R -squared value of 0.708 and a confidence score of 94.06% based on MCD computation, well agreed with our ground-truth given by blood gas measurements.The proposed automatic O 2 Sat ss monitoring solution demonstrated a hypoxia detection capability comparable to the human expert manual annotation on the same task. We concluded with high feasibility for a noninvasive PA-based continuous monitoring of the perinatal brain.ConclusionsThe proposed automatic O 2 Sat ss monitoring solution demonstrated a hypoxia detection capability comparable to the human expert manual annotation on the same task. We concluded with high feasibility for a noninvasive PA-based continuous monitoring of the perinatal brain. Despite advances in perinatal medicine over decades, perinatal hypoxic-ischemic encephalopathy (HIE) remains a significant cause of fetal cerebral palsy and can lead to other severe medical sequelae or death. Therefore, it is highly desirable to effectively detect brain hypoxia during labor and postnatally for HIE management. We recently validated the feasibility of transcranial photoacoustic (PA) imaging for oxyhemoglobin saturation measurement at the superior sagittal sinus ( ) in the neonatal piglet brain, at which overall oxygen supply status can be reflected as a primary collective vein. We aim to automate the PA-based workflow of at-risk subject detection and enable fully autonomous and continuous perinatal monitoring. We proposed a two-step algorithm that focuses on the most informative region of the brain for oxygenation status, the superior sagittal sinus (SSS). First, a convolutional neural network (U-Net) is trained to detect the location of SSS in the coronal cross-section PA images. Then, an optimized region of interest patch around the predicted SSS location is cropped from the spectral unmixed image and averaged as the measurement. A confidence score can be computed for the measurement via Monte Carlo dropout (MCD), which infers the prediction uncertainty for better clinical decision-making. The algorithm was evaluated on an piglet brain imaging dataset containing 84 independent experimental settings from 10 piglet subjects. A 10-fold leave-one-subject-out cross-validation experiment reports 85.2% sensitivity and 93.3% specificity for healthy/hypoxia classification with an -squared value of 0.708 and a confidence score of 94.06% based on MCD computation, well agreed with our ground-truth given by blood gas measurements. The proposed automatic monitoring solution demonstrated a hypoxia detection capability comparable to the human expert manual annotation on the same task. We concluded with high feasibility for a noninvasive PA-based continuous monitoring of the perinatal brain. |
| Author | Unberath, Mathias Koehler, Raymond C. Kang, Jeeun Taylor, Russell H. Jiang, Baichuan Graham, Ernest Boctor, Emad M. |
| Author_xml | – sequence: 1 givenname: Baichuan orcidid: 0000-0001-5223-7104 surname: Jiang fullname: Jiang, Baichuan email: bcjiang@jhu.edu organization: Johns Hopkins University, Department of Computer Science, Baltimore, Maryland, United States – sequence: 2 givenname: Ernest surname: Graham fullname: Graham, Ernest email: egraham5@jhmi.edu organization: Johns Hopkins Medical Institute, Department of Gynecology and Obstetrics, Baltimore, Maryland, United States – sequence: 3 givenname: Mathias orcidid: 0000-0002-0055-9950 surname: Unberath fullname: Unberath, Mathias email: unberath@jhu.edu organization: Johns Hopkins University, Department of Computer Science, Baltimore, Maryland, United States – sequence: 4 givenname: Russell H. orcidid: 0000-0001-6272-1100 surname: Taylor fullname: Taylor, Russell H. email: rht@jhu.edu organization: Johns Hopkins University, Department of Computer Science, Baltimore, Maryland, United States – sequence: 5 givenname: Raymond C. surname: Koehler fullname: Koehler, Raymond C. email: rkoehle1@jh.edu organization: Johns Hopkins Medical Institute, Department of Anesthesiology and Critical Care Medicine, Baltimore, Maryland, United States – sequence: 6 givenname: Jeeun surname: Kang fullname: Kang, Jeeun email: kangj@jhmi.edu organization: Johns Hopkins University, Department of Electrical and Computer Engineering, Baltimore, Maryland, United States – sequence: 7 givenname: Emad M. surname: Boctor fullname: Boctor, Emad M. email: kangj@jhmi.edu organization: Johns Hopkins University, Department of Computer Science, Baltimore, Maryland, United States |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40655941$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kM1OwzAQhC0Eoi3wAFyQj1wS1nbiOMeC-BVSL71bjuNQo8YOtiPo25OqwJHTzmq_WWlmgY6ddwahSwI5IaS6IfnL7SpnkFc5VBygOEJzUnLIKBXkeNIgWMY4FzO0iPEdAASv-SmaFcDLsi7IHLXLMfleJavxsPHJK-3HuN9672zywbo37Ds8mEmppLa4Cco6vNkN_ssq_GnTBsdxf_YBR_Vm0x6K1o0RtyYZnax35-ikU9toLn7mGVo_3K_vnrLX1ePz3fI104xVKVOiNBp0K4RuOiiELhgRLdCyaLquFCWngglGiSig7USj25qWVVNDo6q6Y4ydoevD2yH4j9HEJHsbtdlulTNTKskorWsoaM0n9OoHHZvetHIItldhJ3-LmQByAHTwMQbT_SEE5L58SeRUvmQgK3kof_LkB08crJHvfgxuSvuP4RtHlobD |
| ContentType | Journal Article |
| Copyright | The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. 2025 The Authors. |
| Copyright_xml | – notice: The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. – notice: 2025 The Authors. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1117/1.JBO.30.7.076004 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef 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: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Biology Physics |
| EISSN | 1560-2281 |
| EndPage | 076004 |
| ExternalDocumentID | 40655941 10_1117_1_JBO_30_7_076004 |
| Genre | Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural |
| GrantInformation_xml | – fundername: National Institutes of Health grantid: R01HL139543 – fundername: National Science Foundation Career Award grantid: 1653322 – fundername: Maryland Innovation Initiative, TEDCO – fundername: Analog Devices Inc. fellowship – fundername: NIH Blueprint for Neuroscience Research grantid: U54EB015408; U54EB033650 – fundername: NB NIH HHS grantid: U54EB015408 – fundername: NB NIH HHS grantid: U54EB033650 – fundername: NIH HHS grantid: R01HL139543 |
| GroupedDBID | --- 0R~ 29J 4.4 53G 5GY AAFWJ ACBEA ACGFO ACGFS ADBBV AENEX AEUYN AFKRA AFPKN AKROS ALMA_UNASSIGNED_HOLDINGS BBNVY BCNDV BENPR BHPHI CCPQU CS3 DU5 EBS EMOBN F5P FQ0 GROUPED_DOAJ HCIFZ HZ~ M7P O9- OK1 P2P PBYJJ PHGZM PHGZT PIMPY PQGLB RNS RPM SPBNH UPT W2D YQT AAYXX AFFHD CITATION IAO IGS INH M4X CGR CUY CVF ECM EIF EJD HYE M4W NPM NU. 7X8 PUEGO |
| ID | FETCH-LOGICAL-c337t-a85ec0cd88cbf048c4318d0254bff58562838321840df8bcd9257b90ba79f333 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001542364900012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1083-3668 1560-2281 |
| IngestDate | Thu Oct 02 22:24:04 EDT 2025 Wed Aug 13 02:12:49 EDT 2025 Sat Nov 29 07:46:20 EST 2025 Fri Aug 01 20:50:19 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Keywords | brain monitoring deep learning perinatal health photoacoustic imaging oxygen saturation measurement |
| Language | English |
| License | 2025 The Authors. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c337t-a85ec0cd88cbf048c4318d0254bff58562838321840df8bcd9257b90ba79f333 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-0055-9950 0000-0001-5223-7104 0000-0001-6272-1100 |
| OpenAccessLink | http://dx.doi.org/10.1117/1.JBO.30.7.076004 |
| PMID | 40655941 |
| PQID | 3229904296 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | spie_journals_10_1117_1_JBO_30_7_076004 proquest_miscellaneous_3229904296 pubmed_primary_40655941 crossref_primary_10_1117_1_JBO_30_7_076004 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-07-01 |
| PublicationDateYYYYMMDD | 2025-07-01 |
| PublicationDate_xml | – month: 07 year: 2025 text: 2025-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Journal of biomedical optics |
| PublicationTitleAlternate | J. Biomed. Opt |
| PublicationYear | 2025 |
| Publisher | Society of Photo-Optical Instrumentation Engineers |
| Publisher_xml | – name: Society of Photo-Optical Instrumentation Engineers |
| SSID | ssj0008696 |
| Score | 2.456968 |
| Snippet | Despite advances in perinatal medicine over decades, perinatal hypoxic-ischemic encephalopathy (HIE) remains a significant cause of fetal cerebral palsy and... |
| SourceID | proquest pubmed crossref spie |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 076004 |
| SubjectTerms | Algorithms Animals Animals, Newborn Brain - diagnostic imaging Female Hypoxia, Brain - diagnostic imaging Hypoxia-Ischemia, Brain - diagnostic imaging Image Processing, Computer-Assisted - methods Neural Networks, Computer Photoacoustic Techniques - methods Superior Sagittal Sinus - diagnostic imaging Swine |
| Title | Automatic photoacoustic monitoring of perinatal brain hypoxia with superior sagittal sinus detection |
| URI | http://www.dx.doi.org/10.1117/1.JBO.30.7.076004 https://www.ncbi.nlm.nih.gov/pubmed/40655941 https://www.proquest.com/docview/3229904296 |
| Volume | 30 |
| WOSCitedRecordID | wos001542364900012&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1560-2281 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008696 issn: 1083-3668 databaseCode: DOA dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1560-2281 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008696 issn: 1083-3668 databaseCode: M7P dateStart: 20190101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1560-2281 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008696 issn: 1083-3668 databaseCode: BENPR dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content customDbUrl: eissn: 1560-2281 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008696 issn: 1083-3668 databaseCode: PIMPY dateStart: 20190101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdpu5XuYWzdV_YRNBgMFpy58Zf82IyMrqxZKNnInoxkyYuhtU3slPSv2L-8k2TZKSGwPSwPJshGAv1-ujud7nQIvUs8nzNBXYuGiYANCuEWSxJiMfh5HmNCZ_H_-BpMJmQ-D6edzm-TC3NzFWQZWa_D4r9CDW0Atkyd_Qe4m06hAf4D6PAE2OH5V8Cfrqpc38NaLPIqB4mnCnb1r9XqXZooZ5n2pyqHMFkkor-4LfJ1Sk3IunydL_sl_ZVW8qMyzVZln4tKRW5lO0xancuvYM-LaiOO_jyt3dIjmsaLVcvINlF7vMzMSRe0f5dxZ1T7fC5kgCRt-mp9DJerspSux7NN18XQa8JcQfPU4ta3reFQF20x8rg-p9G8CzaEqzpEdHfIfXVzwOB89G3g2INgsP0toFRcK8zBhoF9lHvSqsAmMNG82kMHw8ALQUwejMaT6WWj3Ikf-vXhOIz5cWvEI3Ro-rhr6WxtX2ToYJGKDWtm9gg9rDHDp5o-j1FHZMfovi5MenuMHmxcUwntKkw4Lp8g3pAL3yEXbsmF8wQ35MKKXLgmF5bkwoZc2JALK3LhhlxP0ezzePbpzKrrdFix4wSVRYknYjvmhMQsAY0Qg1FKuLxmAZY9bEd9MGFlQSzi2jwhLOYh6AkW2owGYeI4zjO0n-WZeIGw4MR1fOExj1CXS-vVCymNWchZ4NrM66IPZkqjQt_GEuldbBCdRABF5NhREGkouuitmfQIZKY8CKOZgGmJQImBEQaWmN9FzzUaTXcGvS56L-GJ6pVd7h7n5c4-XqGjlvav0X61XIk36F58U6Xlsof2gjnp1QTrKWdQT4YeT6Ft-uVi-vMPdFSmnw |
| linkProvider | ProQuest |
| 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=Automatic+photoacoustic+monitoring+of+perinatal+brain+hypoxia+with+superior+sagittal+sinus+detection&rft.jtitle=Journal+of+biomedical+optics&rft.au=Jiang%2C+Baichuan&rft.au=Graham%2C+Ernest&rft.au=Unberath%2C+Mathias&rft.au=Taylor%2C+Russell+H&rft.date=2025-07-01&rft.eissn=1560-2281&rft.volume=30&rft.issue=7&rft.spage=076004&rft_id=info:doi/10.1117%2F1.JBO.30.7.076004&rft_id=info%3Apmid%2F40655941&rft.externalDocID=40655941 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1083-3668&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1083-3668&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1083-3668&client=summon |