Machine Learning Algorithms for Classification of First-Trimester Fetal Brain Ultrasound Images
To evaluate the feasibility of machine learning (ML) tools for segmenting and classifying first-trimester fetal brain ultrasound images. Two image segmentation methods processed high-resolution fetal brain images obtained during the nuchal translucency scan: "Statistical Region Merging" (S...
Saved in:
| Published in: | Journal of ultrasound in medicine Vol. 41; no. 7; p. 1773 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
England
01.07.2022
|
| Subjects: | |
| ISSN: | 1550-9613, 1550-9613 |
| Online Access: | Get more information |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | To evaluate the feasibility of machine learning (ML) tools for segmenting and classifying first-trimester fetal brain ultrasound images.
Two image segmentation methods processed high-resolution fetal brain images obtained during the nuchal translucency scan: "Statistical Region Merging" (SRM) and "Trainable Weka Segmentation" (TWS), with training and testing sets in the latter. Measurement of the fetal cerebral cortex in original and processed images served to evaluate the performance of the algorithms. Mean absolute percentage error (MAPE) was used as an accuracy index of the segmentation processing.
The SRM plugin revealed a total MAPE of 1.71% ± 1.62 SD (standard deviation) and a MAPE of 1.4% ± 1.32 SD and 2.72% ± 2.21 SD for the normal and increased NT groups, respectively. The TWS plugin displayed a MAPE of 1.71% ± 0.59 SD (testing set). There were no significant differences between the training and testing sets after 5-fold cross-validation. The images obtained from normal NT fetuses and increased NT fetuses revealed a MAPE of 1.52% ± 1.02 SD and 2.63% ± 1.98 SD.
Our study demonstrates the feasibility of using ML algorithms to classify first-trimester fetal brain ultrasound images and lay the foundation for earlier diagnosis of fetal brain abnormalities. |
|---|---|
| AbstractList | To evaluate the feasibility of machine learning (ML) tools for segmenting and classifying first-trimester fetal brain ultrasound images.
Two image segmentation methods processed high-resolution fetal brain images obtained during the nuchal translucency scan: "Statistical Region Merging" (SRM) and "Trainable Weka Segmentation" (TWS), with training and testing sets in the latter. Measurement of the fetal cerebral cortex in original and processed images served to evaluate the performance of the algorithms. Mean absolute percentage error (MAPE) was used as an accuracy index of the segmentation processing.
The SRM plugin revealed a total MAPE of 1.71% ± 1.62 SD (standard deviation) and a MAPE of 1.4% ± 1.32 SD and 2.72% ± 2.21 SD for the normal and increased NT groups, respectively. The TWS plugin displayed a MAPE of 1.71% ± 0.59 SD (testing set). There were no significant differences between the training and testing sets after 5-fold cross-validation. The images obtained from normal NT fetuses and increased NT fetuses revealed a MAPE of 1.52% ± 1.02 SD and 2.63% ± 1.98 SD.
Our study demonstrates the feasibility of using ML algorithms to classify first-trimester fetal brain ultrasound images and lay the foundation for earlier diagnosis of fetal brain abnormalities. To evaluate the feasibility of machine learning (ML) tools for segmenting and classifying first-trimester fetal brain ultrasound images.OBJECTIVETo evaluate the feasibility of machine learning (ML) tools for segmenting and classifying first-trimester fetal brain ultrasound images.Two image segmentation methods processed high-resolution fetal brain images obtained during the nuchal translucency scan: "Statistical Region Merging" (SRM) and "Trainable Weka Segmentation" (TWS), with training and testing sets in the latter. Measurement of the fetal cerebral cortex in original and processed images served to evaluate the performance of the algorithms. Mean absolute percentage error (MAPE) was used as an accuracy index of the segmentation processing.METHODSTwo image segmentation methods processed high-resolution fetal brain images obtained during the nuchal translucency scan: "Statistical Region Merging" (SRM) and "Trainable Weka Segmentation" (TWS), with training and testing sets in the latter. Measurement of the fetal cerebral cortex in original and processed images served to evaluate the performance of the algorithms. Mean absolute percentage error (MAPE) was used as an accuracy index of the segmentation processing.The SRM plugin revealed a total MAPE of 1.71% ± 1.62 SD (standard deviation) and a MAPE of 1.4% ± 1.32 SD and 2.72% ± 2.21 SD for the normal and increased NT groups, respectively. The TWS plugin displayed a MAPE of 1.71% ± 0.59 SD (testing set). There were no significant differences between the training and testing sets after 5-fold cross-validation. The images obtained from normal NT fetuses and increased NT fetuses revealed a MAPE of 1.52% ± 1.02 SD and 2.63% ± 1.98 SD.RESULTSThe SRM plugin revealed a total MAPE of 1.71% ± 1.62 SD (standard deviation) and a MAPE of 1.4% ± 1.32 SD and 2.72% ± 2.21 SD for the normal and increased NT groups, respectively. The TWS plugin displayed a MAPE of 1.71% ± 0.59 SD (testing set). There were no significant differences between the training and testing sets after 5-fold cross-validation. The images obtained from normal NT fetuses and increased NT fetuses revealed a MAPE of 1.52% ± 1.02 SD and 2.63% ± 1.98 SD.Our study demonstrates the feasibility of using ML algorithms to classify first-trimester fetal brain ultrasound images and lay the foundation for earlier diagnosis of fetal brain abnormalities.CONCLUSIONSOur study demonstrates the feasibility of using ML algorithms to classify first-trimester fetal brain ultrasound images and lay the foundation for earlier diagnosis of fetal brain abnormalities. |
| Author | Gilboa, Yinon Perlman, Sharon Haik, Oren Gofer, Stav Bardin, Ron |
| Author_xml | – sequence: 1 givenname: Stav surname: Gofer fullname: Gofer, Stav organization: Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel – sequence: 2 givenname: Oren surname: Haik fullname: Haik, Oren organization: Independent Researcher – sequence: 3 givenname: Ron orcidid: 0000-0003-4545-7234 surname: Bardin fullname: Bardin, Ron organization: Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel – sequence: 4 givenname: Yinon surname: Gilboa fullname: Gilboa, Yinon organization: Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel – sequence: 5 givenname: Sharon orcidid: 0000-0002-8023-0679 surname: Perlman fullname: Perlman, Sharon organization: Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34710247$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkEtPwzAQhC1URB9w4A8gH7mk-JU0OZaqhUpFXNpz5Nib1pVjFzs58O-xRJG47M5In1YzO0Uj5x0g9EjJnBLCXs5DN6d5WZAbNKF5TrKqoHz0T4_RNMZzQgldiDs05mJBCROLCao_pDoZB3gHMjjjjnhpjz6Y_tRF3PqAV1bGaFqjZG-8w77FGxNin-2D6SD2EPAGemnxa5DG4YPtg4x-cBpvO3mEeI9uW2kjPFz3DB026_3qPdt9vm1Xy12mOEshFRRKC1lCRSvgbcHTaAqoSkWbvNGKUtEorcu2qLTkgiRHOG90rgsiWi7ZDD3_3r0E_zWkYHVnogJrpQM_xJrlFaGMC14m9OmKDk0Hur6kJjJ8139PYT_5eGXg |
| CitedBy_id | crossref_primary_10_1109_TUFFC_2023_3311879 crossref_primary_10_1016_j_ebiom_2023_104466 crossref_primary_10_1016_j_imavis_2023_104725 crossref_primary_10_1109_TIM_2024_3369155 crossref_primary_10_1002_ijgo_15762 crossref_primary_10_1007_s00247_025_06376_2 crossref_primary_10_1007_s00521_023_09148_x crossref_primary_10_3390_s25165034 crossref_primary_10_1016_j_bspc_2025_107499 crossref_primary_10_1002_pd_6411 crossref_primary_10_1038_s41598_024_77313_w crossref_primary_10_1109_TMI_2022_3226274 crossref_primary_10_3390_diagnostics14182089 crossref_primary_10_3390_jcm12165334 crossref_primary_10_3390_jcm12216833 crossref_primary_10_1002_jum_16418 |
| ContentType | Journal Article |
| Copyright | 2021 American Institute of Ultrasound in Medicine. |
| Copyright_xml | – notice: 2021 American Institute of Ultrasound in Medicine. |
| DBID | NPM 7X8 |
| DOI | 10.1002/jum.15860 |
| DatabaseName | PubMed MEDLINE - Academic |
| DatabaseTitle | PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| 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 | no_fulltext_linktorsrc |
| Discipline | Medicine Physics |
| EISSN | 1550-9613 |
| ExternalDocumentID | 34710247 |
| Genre | Journal Article |
| GroupedDBID | --- .55 .GJ 0R~ 18M 1KJ 1OB 1OC 33P 34G 39C 53G 5GY 5RE 5VS 6PF AAHHS AAHQN AAIPD AAMNL AANLZ AAWTL AAYCA AAZKR ABCUV ABDPE ABDQB ABJNI ABLJU ABOCM ABQWH ACCFJ ACCZN ACGFO ACGFS ACGOF ACPOU ACXQS ADBBV ADBTR ADKYN ADXAS ADZMN AEEZP AEIGN AENEX AEQDE AEUYR AFBPY AFFNX AFFPM AFWVQ AHBTC AITYG AIURR AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMYDB BFHJK C45 DCZOG DU5 EBS EJD F5P H13 HDBZQ HGLYW KQ8 LATKE LEEKS LOXES LUTES LYRES MEWTI N4W NPM O9- OK1 OVD P2P P2W RHF RHI ROL RS9 SAMSI SUPJJ TEORI TUL TWZ USG WIH WIJ WIK WOHZO WXSBR X7M ZGI ZVN ZXP ZZTAW 7X8 AAMMB AEFGJ AEYWJ AGHNM AGXDD AGYGG AIDQK AIDYY LH4 |
| ID | FETCH-LOGICAL-c3250-ce6cd4a8e919e3f63e3fb6e98c1b5bdc114bcdd8f69da3404bc033bd5d604f3a2 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 19 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000711905800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1550-9613 |
| IngestDate | Fri Sep 05 11:13:12 EDT 2025 Wed Feb 19 02:26:29 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Keywords | image processing first trimester nuchal translucency machine learning fetal cortex ultrasound |
| Language | English |
| License | 2021 American Institute of Ultrasound in Medicine. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3250-ce6cd4a8e919e3f63e3fb6e98c1b5bdc114bcdd8f69da3404bc033bd5d604f3a2 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-8023-0679 0000-0003-4545-7234 |
| PMID | 34710247 |
| PQID | 2590123438 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2590123438 pubmed_primary_34710247 |
| PublicationCentury | 2000 |
| PublicationDate | July 2022 |
| PublicationDateYYYYMMDD | 2022-07-01 |
| PublicationDate_xml | – month: 07 year: 2022 text: July 2022 |
| PublicationDecade | 2020 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England |
| PublicationTitle | Journal of ultrasound in medicine |
| PublicationTitleAlternate | J Ultrasound Med |
| PublicationYear | 2022 |
| SSID | ssj0020174 |
| Score | 2.4323895 |
| Snippet | To evaluate the feasibility of machine learning (ML) tools for segmenting and classifying first-trimester fetal brain ultrasound images.
Two image segmentation... To evaluate the feasibility of machine learning (ML) tools for segmenting and classifying first-trimester fetal brain ultrasound images.OBJECTIVETo evaluate... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 1773 |
| Title | Machine Learning Algorithms for Classification of First-Trimester Fetal Brain Ultrasound Images |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/34710247 https://www.proquest.com/docview/2590123438 |
| Volume | 41 |
| WOSCitedRecordID | wos000711905800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3JTsMwELWAAuLCUvZNRuJqSOIl8QkVRAUSrXpopd6ieCtFXYAUvp-xm8KFAxIXSzkkiuzJzIvn-T2ELou4iLRigmRMCsKYdERx54hJI8MB4HOtgmT-U9puZ_2-7FQbbmVFq1zkxJCozVT7PfLrxB-STCij2c3rG_GuUb67WlloLKMaBSjjKV1p_7uLALUtqDB7FE4k1K2FslCUXL98jK9inlXKlL8iy1Bhmlv_fbdttFlhS9yYB8MOWrKTOlpvVd3zOloLdE9d7qK8FTiUFlfyqgPcGA3gibPncYkBxuLglelZRGHh8NTh5hBwIul6NwCvrYCbFmA7vvUOE7g3mr0XpTdowo9jSFDlHuo177t3D6SyWiCaAggi2gptWJFZGUtLnaAwKGFlpmPFldHw16S0MZkT0hSURXAVUaoMNyJijhbJPlqZTCf2EGFuNCQFHhvhNHM6k8rTaFPBKXca4NYRulhMYg6h7PsTxcROP8r8ZxqP0MF8JfLXueZGTpmHQiw9_sPdJ2gj8YcUAqn2FNUcfMj2DK3qz9mwfD8PMQJju9P6AmGSx7c |
| 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=Machine+Learning+Algorithms+for+Classification+of+First-Trimester+Fetal+Brain+Ultrasound+Images&rft.jtitle=Journal+of+ultrasound+in+medicine&rft.au=Gofer%2C+Stav&rft.au=Haik%2C+Oren&rft.au=Bardin%2C+Ron&rft.au=Gilboa%2C+Yinon&rft.date=2022-07-01&rft.eissn=1550-9613&rft.volume=41&rft.issue=7&rft.spage=1773&rft_id=info:doi/10.1002%2Fjum.15860&rft_id=info%3Apmid%2F34710247&rft_id=info%3Apmid%2F34710247&rft.externalDocID=34710247 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1550-9613&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1550-9613&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1550-9613&client=summon |