Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/121980
DC FieldValue
dc.titleAUTOMATIC LOCALIZATION OF EPIDURAL NEEDLE ENTRY SITE WITH LUMBAR ULTRASOUND IMAGE PROCESSING
dc.contributor.authorYU SHUANG
dc.date.accessioned2015-12-31T18:01:57Z
dc.date.available2015-12-31T18:01:57Z
dc.date.issued2015-08-11
dc.identifier.citationYU SHUANG (2015-08-11). AUTOMATIC LOCALIZATION OF EPIDURAL NEEDLE ENTRY SITE WITH LUMBAR ULTRASOUND IMAGE PROCESSING. ScholarBank@NUS Repository.
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/121980
dc.description.abstractEpidural anesthesia (EA) is rated as one of the most difficult procedures to perform in anesthesiology. A key technical challenge of EA is the identification of the needle entry site, which is clinically determined by palpating the surface landmarks of the spine. Previous researches have confirmed the effectiveness of ultrasound imaging compared with traditional palpation method. However, the low resolution and speckle noises influence the interpretation of ultrasound images, leading to the difficulties of anaesthetists in adopting ultrasonography in the clinical practice. In this thesis, an intelligent image processing algorithm and procedure based on machine learning is developed for lumbar ultrasound image processing. The algorithm is able to provide guidance to locate the precise needle entry site as the operator moving the ultrasound probe, thus facilitating the interpretation of ultrasound images and realizing automatic localization of needle entry site.
dc.language.isoen
dc.subjectImage Processing, Epidural Anesthesia, Lumbar Ultrasound, Machine Learning, Support Vector Machine
dc.typeThesis
dc.contributor.departmentNUS GRAD SCH FOR INTEGRATIVE SCI & ENGG
dc.contributor.supervisorTAN KOK KIONG
dc.description.degreePh.D
dc.description.degreeconferredDOCTOR OF PHILOSOPHY
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Ph.D Theses (Open)

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
YuS.pdf16.13 MBAdobe PDF

OPEN

NoneView/Download

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.