Efficient Ultrasound Image Enhancement Using Lightweight CNNs

Simple item page
dc.contributor.authorAnjidani, Farid
dc.contributor.supervisorRakhmatov, Daler N.
dc.date.accessioned2023-05-18T17:16:43Z
dc.date.available2023-05-18T17:16:43Z
dc.date.copyright2023en_US
dc.date.issued2023-05-18
dc.degree.departmentDepartment of Electrical and Computer Engineering
dc.degree.levelMaster of Applied Science M.A.Sc.en_US
dc.description.abstractPlane-wave ultrasound imaging allows for very high frame rates. During image reconstruction, conventional delay-and-sum beamforming can be replaced by the quicker Fourier-domain remapping method. Typically, after Fourier-domain reconstruction, postbeamforming interpolation is needed to increase the image grid resolution in the lateral dimension. To achieve this, we propose to use a fast lightweight superresolution convolutional neural network (CNN) operating on the Fourier-beamformed envelope data. Specifically, we train different configurations of well-known Efficient Sub-Pixel Convolutional Neural Network (ESPCN) to perform both 1D and 2D upscaling. First, we pretrain a network using the diverse (non-ultrasound) dataset DIV2K. Then, we apply transfer learning on a small augmented dataset of public-domain experimental ultrasound images. Our results demonstrate that our approach is capable of producing enhanced ultrasound images having higher quality compared to non-CNN interpolation options and conventional delay-and-sum beamforming.en_US
dc.description.scholarlevelGraduateen_US
dc.identifier.urihttp://hdl.handle.net/1828/15120
dc.languageEnglisheng
dc.language.isoenen_US
dc.rightsAvailable to the World Wide Weben_US
dc.subjectBicubic Interpolationen_US
dc.subjectCoherent Plane-Wave Compoundingen_US
dc.subjectConvolutional Neural Networken_US
dc.subjectDelay-and-Sum (Beamforming)en_US
dc.subjectFast Fourier Transformen_US
dc.subjectFourier Interpolationen_US
dc.subjectFull Width at Half Maximumen_US
dc.subjectMean Squared Logarithmic Erroren_US
dc.subjectPlane Wave Imagingen_US
dc.subjectTemme-Mueller (Migration)en_US
dc.subjectUltraSounden_US
dc.subjectSingle-Image Super-Resolutionen_US
dc.subjectbeamformingen_US
dc.subjectDASen_US
dc.subjectsuperresolutionen_US
dc.titleEfficient Ultrasound Image Enhancement Using Lightweight CNNsen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Anjidani_Farid_MASc_2023.pdf
Size:
8.8 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Electronic Theses and Dissertations (ETD)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.