Lumbar Ultrasound Image Feature Extraction and Classification with Support Vector Machine

Needle entry site localization remains a challenge for procedures that involve lumbar puncture, for example, epidural anesthesia. To solve the problem, we have developed an image classification algorithm that can automatically identify the bone/interspinous region for ultrasound images obtained from...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Ultrasound in medicine & biology Ročník 41; číslo 10; s. 2677 - 2689
Hlavní autori: Yu, Shuang, Tan, Kok Kiong, Sng, Ban Leong, Li, Shengjin, Sia, Alex Tiong Heng
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: England 01.10.2015
Predmet:
Algorithms
Anesthesia, Epidural - methods
Female
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Lumbar Vertebrae - diagnostic imaging
Pattern Recognition, Automated - methods
Pregnancy
Punctures
Reproducibility of Results
Sensitivity and Specificity
Support Vector Machine
Ultrasonography, Interventional - methods
Medical image processing
Feature selection
Video processing
Machine learning
Feature extraction
Support vector machine
Epidural anesthesia
ISSN:1879-291X
On-line prístup:Zistit podrobnosti o prístupe
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Needle entry site localization remains a challenge for procedures that involve lumbar puncture, for example, epidural anesthesia. To solve the problem, we have developed an image classification algorithm that can automatically identify the bone/interspinous region for ultrasound images obtained from lumbar spine of pregnant patients in the transverse plane. The proposed algorithm consists of feature extraction, feature selection and machine learning procedures. A set of features, including matching values, positions and the appearance of black pixels within pre-defined windows along the midline, were extracted from the ultrasound images using template matching and midline detection methods. A support vector machine was then used to classify the bone images and interspinous images. The support vector machine model was trained with 1,040 images from 26 pregnant subjects and tested on 800 images from a separate set of 20 pregnant patients. A success rate of 95.0% on training set and 93.2% on test set was achieved with the proposed method. The trained support vector machine model was further tested on 46 off-line collected videos, and successfully identified the proper needle insertion site (interspinous region) in 45 of the cases. Therefore, the proposed method is able to process the ultrasound images of lumbar spine in an automatic manner, so as to facilitate the anesthetists' work of identifying the needle entry site.
AbstractList Needle entry site localization remains a challenge for procedures that involve lumbar puncture, for example, epidural anesthesia. To solve the problem, we have developed an image classification algorithm that can automatically identify the bone/interspinous region for ultrasound images obtained from lumbar spine of pregnant patients in the transverse plane. The proposed algorithm consists of feature extraction, feature selection and machine learning procedures. A set of features, including matching values, positions and the appearance of black pixels within pre-defined windows along the midline, were extracted from the ultrasound images using template matching and midline detection methods. A support vector machine was then used to classify the bone images and interspinous images. The support vector machine model was trained with 1,040 images from 26 pregnant subjects and tested on 800 images from a separate set of 20 pregnant patients. A success rate of 95.0% on training set and 93.2% on test set was achieved with the proposed method. The trained support vector machine model was further tested on 46 off-line collected videos, and successfully identified the proper needle insertion site (interspinous region) in 45 of the cases. Therefore, the proposed method is able to process the ultrasound images of lumbar spine in an automatic manner, so as to facilitate the anesthetists' work of identifying the needle entry site.
Author Sia, Alex Tiong Heng
Tan, Kok Kiong
Yu, Shuang
Li, Shengjin
Sng, Ban Leong
Author_xml – sequence: 1
  givenname: Shuang
  surname: Yu
  fullname: Yu, Shuang
  email: yushuang@nus.edu.sg
  organization: NUS Graduate School for Sciences and Engineering, Department of Electrical and Computer Engineering, National University of Singapore, Singapore. Electronic address: yushuang@nus.edu.sg
– sequence: 2
  givenname: Kok Kiong
  surname: Tan
  fullname: Tan, Kok Kiong
  organization: NUS Graduate School for Sciences and Engineering, Department of Electrical and Computer Engineering, National University of Singapore, Singapore
– sequence: 3
  givenname: Ban Leong
  surname: Sng
  fullname: Sng, Ban Leong
  organization: Department of Women's Anesthesia, KK Womens and Childrens Hospital, Singapore; Duke-National University of Singapore Graduate Medical School, Singapore
– sequence: 4
  givenname: Shengjin
  surname: Li
  fullname: Li, Shengjin
  organization: Duke-National University of Singapore Graduate Medical School, Singapore
– sequence: 5
  givenname: Alex Tiong Heng
  surname: Sia
  fullname: Sia, Alex Tiong Heng
  organization: Department of Women's Anesthesia, KK Womens and Childrens Hospital, Singapore; Duke-National University of Singapore Graduate Medical School, Singapore
BackLink https://www.ncbi.nlm.nih.gov/pubmed/26119460$$D View this record in MEDLINE/PubMed
BookMark eNo1kE1LxDAYhIMo7of-BQmevLQmaZs0R1l2dWHFg67oqbxNUzdL29QmQf33lnWFgYF5hjnMDJ12ttMIXVMSU0L57T4OjR_AtboqjY0ZoVlMRtHsBE1pLmTEJH2boJlze0KI4Ik4RxPGKZUpJ1P0vgltCQPeHlZs6Cq8buFD45UGHwaNl98jUN7YDsMIFw04Z2qj4BB9Gb_Dz6Hv7eDxq1beDvgR1M50-gKd1dA4fXn0Odquli-Lh2jzdL9e3G0ilfHUR1LkjKlS1yLlea2IqAEUVFJlldZZrVSSMSZZyZIkVWkKNIWKc1FTVgnIFGVzdPO32w_2M2jni9Y4pZsGOm2DK6ggeS45lXKsXh2roRwPK_rBtDD8FP93sF90L2ee
CitedBy_id crossref_primary_10_1016_j_compbiomed_2016_03_018
crossref_primary_10_1016_j_arth_2023_08_045
crossref_primary_10_1093_comjnl_bxab088
crossref_primary_10_1109_MCOMSTD_2025_3582997
crossref_primary_10_1007_s12046_021_01574_8
crossref_primary_10_1108_K_08_2020_0512
crossref_primary_10_1016_j_bspc_2021_102886
crossref_primary_10_1080_21681163_2022_2124545
crossref_primary_10_1016_j_cosrev_2020_100320
crossref_primary_10_1007_s00261_018_1517_0
crossref_primary_10_3389_fbioe_2018_00075
crossref_primary_10_7759_cureus_48078
crossref_primary_10_1016_j_ijoa_2024_104288
crossref_primary_10_1007_s40031_022_00745_3
crossref_primary_10_1108_IJWIS_01_2021_0007
crossref_primary_10_1186_s12871_019_0726_6
crossref_primary_10_1002_ima_22482
crossref_primary_10_1007_s10878_021_00770_w
crossref_primary_10_1007_s12065_020_00400_0
crossref_primary_10_14366_usg_20080
crossref_primary_10_3390_diagnostics13152606
crossref_primary_10_1177_01617346231220000
crossref_primary_10_1007_s12065_020_00403_x
crossref_primary_10_1177_21925682211049164
crossref_primary_10_1007_s10928_020_09685_1
crossref_primary_10_1108_IJICC_10_2019_0116
crossref_primary_10_1109_ACCESS_2020_2997663
crossref_primary_10_1093_comjnl_bxab171
crossref_primary_10_1007_s10877_023_01088_0
crossref_primary_10_1007_s12046_021_01631_2
crossref_primary_10_1108_SR_02_2020_0039
crossref_primary_10_1007_s11042_023_14606_8
crossref_primary_10_1007_s11042_024_18659_1
crossref_primary_10_1002_ima_22475
crossref_primary_10_1002_ase_2266
crossref_primary_10_1007_s13755_024_00301_x
crossref_primary_10_1515_bams_2020_0053
crossref_primary_10_1038_s41598_023_39508_5
crossref_primary_10_3390_math8112008
crossref_primary_10_1093_comjnl_bxab068
crossref_primary_10_1016_j_bja_2024_01_036
crossref_primary_10_1002_ima_22519
crossref_primary_10_1109_TUFFC_2019_2956730
crossref_primary_10_1016_j_jksuci_2020_12_022
crossref_primary_10_1016_j_csi_2021_103518
crossref_primary_10_1007_s40009_025_01800_5
crossref_primary_10_1007_s11548_017_1575_8
crossref_primary_10_1002_ima_22665
crossref_primary_10_1109_TMI_2017_2739110
crossref_primary_10_4018_IJDST_300356
crossref_primary_10_1007_s10586_022_03960_1
ContentType Journal Article
Copyright Copyright © 2015 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.
Copyright_xml – notice: Copyright © 2015 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1016/j.ultrasmedbio.2015.05.015
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
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: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
Biology
Physics
EISSN 1879-291X
EndPage 2689
ExternalDocumentID 26119460
Genre Journal Article
GroupedDBID ---
--K
-DZ
.1-
.55
.FO
.GJ
0R~
123
1B1
1P~
1RT
1~5
29Q
3O-
4.4
457
4G.
53G
5RE
5VS
7-5
AAEDT
AAEDW
AALRI
AAQFI
AAQXK
AAWTL
AAXUO
AAYWO
ABDPE
ABJNI
ABLJU
ABMAC
ABNEU
ABOCM
ABWVN
ACGFS
ACIUM
ACRPL
ACVFH
ADBBV
ADCNI
ADMUD
ADNMO
AENEX
AEUPX
AEVXI
AFCTW
AFJKZ
AFPUW
AFRHN
AFTJW
AGCQF
AGQPQ
AHHHB
AIGII
AITUG
AJUYK
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
APXCP
ASPBG
AVWKF
AZFZN
BELOY
C5W
CGR
CS3
CUY
CVF
DU5
EBS
ECM
EFJIC
EFKBS
EIF
EJD
F5P
FDB
FEDTE
FGOYB
FIRID
G-2
GBLVA
HEI
HMK
HMO
HVGLF
HZ~
IHE
J1W
K-O
KOM
L7B
M29
M41
MO0
NPM
NQ-
O9-
OI~
OU0
P2P
R2-
RIG
ROL
RPZ
SAE
SDG
SEL
SES
SEW
SSZ
WUQ
X7M
XH2
Z5R
ZGI
ZXP
ZY4
~S-
7X8
ID FETCH-LOGICAL-c564t-97822cbef7468fc07faacad9c5dee5fcc352292b2334c44a14ad667f12d7a5c12
IEDL.DBID 7X8
ISICitedReferencesCount 53
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000366470400014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Sun Nov 09 12:04:46 EST 2025
Mon Jul 21 06:08:32 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Keywords Medical image processing
Feature selection
Video processing
Machine learning
Feature extraction
Support vector machine
Epidural anesthesia
Language English
License Copyright © 2015 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c564t-97822cbef7468fc07faacad9c5dee5fcc352292b2334c44a14ad667f12d7a5c12
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 26119460
PQID 1708896199
PQPubID 23479
PageCount 13
ParticipantIDs proquest_miscellaneous_1708896199
pubmed_primary_26119460
PublicationCentury 2000
PublicationDate 2015-10-01
PublicationDateYYYYMMDD 2015-10-01
PublicationDate_xml – month: 10
  year: 2015
  text: 2015-10-01
  day: 01
PublicationDecade 2010
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Ultrasound in medicine & biology
PublicationTitleAlternate Ultrasound Med Biol
PublicationYear 2015
SSID ssj0007637
Score 2.4101322
Snippet Needle entry site localization remains a challenge for procedures that involve lumbar puncture, for example, epidural anesthesia. To solve the problem, we have...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 2677
SubjectTerms Algorithms
Anesthesia, Epidural - methods
Female
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Lumbar Vertebrae - diagnostic imaging
Pattern Recognition, Automated - methods
Pregnancy
Punctures
Reproducibility of Results
Sensitivity and Specificity
Support Vector Machine
Ultrasonography, Interventional - methods
Title Lumbar Ultrasound Image Feature Extraction and Classification with Support Vector Machine
URI https://www.ncbi.nlm.nih.gov/pubmed/26119460
https://www.proquest.com/docview/1708896199
Volume 41
WOSCitedRecordID wos000366470400014&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/eLvHCXMwpV1JSwMxFA5qVby41K1uRPA6OEtmMjmJSIuCLT1YqaeSFQp2WmcR_ffmZab0JAhe5jDDQEje8iXvy_sQujFUg-AA9ahhxiPE7lNSwyPP90VCfaVsllFObIIOBul4zIbNgVvR0CqXMdEFajWXcEZ-G1Ag5Fi4z-4WHx6oRkF1tZHQWEetyEIZcEw6XnULt75Dl41GHaerei9zXtg0I6Zw8S-I666d8e_w0qWZ3t5_B7iPdhuAie9rizhAazpro61acvK7jbb7TTHdvnTsT1kcorfnaiZ4jkdu4CC0hJ9mNtBgAIhVrnH3q8zrGxCY249OSRM4Rm5ZMZzlYpAHtVAev7oyAO47kqY-QqNe9-Xh0Ws0FzwZJ6T0GCAGKbShJEmN9KnhXHLFZKy0jo2UANhYKMIoIpIQHhCukoSaIFSUxzIIj9FGNs_0KcKG8UQyIbnghghooqOgrTlXxBAeybSDrpcTObE2DYUKnul5VUxWU9lBJ_VqTBZ1842J3fEFjCT-2R_-Pkc7sMg19-4CtYz1aH2JNuVnOS3yK2cs9jkY9n8ADbvNYg
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=Lumbar+Ultrasound+Image+Feature+Extraction+and+Classification+with+Support+Vector+Machine&rft.jtitle=Ultrasound+in+medicine+%26+biology&rft.au=Yu%2C+Shuang&rft.au=Tan%2C+Kok+Kiong&rft.au=Sng%2C+Ban+Leong&rft.au=Li%2C+Shengjin&rft.date=2015-10-01&rft.eissn=1879-291X&rft.volume=41&rft.issue=10&rft.spage=2677&rft_id=info:doi/10.1016%2Fj.ultrasmedbio.2015.05.015&rft_id=info%3Apmid%2F26119460&rft_id=info%3Apmid%2F26119460&rft.externalDocID=26119460