Towards Bridging the Navigation Gap in Ultrasound-Guided Prostate Biopsy
Loading...
Authors
Barr, Colton
Date
Type
thesis
Language
eng
Keyword
Prostate Biopsy , Deep Learning , Low-cost , Ultrasound , Surgical Navigation , Open-source
Alternative Title
Abstract
Global disparities in access to advanced imaging modalities and navigational systems have exacerbated existing differences in prostate cancer diagnosis and prognosis worldwide. As a result, a clear navigational gap has emerged between clinicians that have access to MRI data during prostate biopsy and those that do not. Enabling technologies, such as spatially-tracked ultrasound and deep learning, have the potential to help bridge this gap and improve prostate biopsy yield in low resource settings. The objective of this thesis is to develop a technique for extending the diagnostic utility of trans-rectal ultrasound guidance during prostate biopsy. The principle contributions presented here are the design, implementation and testing of a system capable of generating a 3D model of the prostate from spatially-tracked 2D ultrasound images.
A trained deep learning network was used to identify the prostate within 2D trans-rectal ultrasound images, while a spatially tracked probe enabled the 3D localization of prostate segmentations and subsequent generation of a 3D prostate model. The system was developed using open-source software and low-cost materials, and a user study was conducted to evaluate the accuracy of the prostate reconstruction. The results indicated comparable performance between this low-cost system and more expensive mechanically-tracked methodologies.
The capacity to generate a 3D prostate model using readily available technologies has the potential to improve access to navigated biopsy in low resource settings. Future work will focus on using the 3D prostate reconstruction to overlay zonal information on 2D ultrasound images, helping clinicians visualize the zones of the prostate and more evenly place biopsy cores within the gland. Low-cost navigational tools have an important role to play in democratizing access to reliable prostate cancer diagnosis and reducing the burden of disease among those most affected by prostate cancer.
Description
Citation
Publisher
License
Queen's University's Thesis/Dissertation Non-Exclusive License for Deposit to QSpace and Library and Archives Canada
ProQuest PhD and Master's Theses International Dissemination Agreement
Intellectual Property Guidelines at Queen's University
Copying and Preserving Your Thesis
This publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.
ProQuest PhD and Master's Theses International Dissemination Agreement
Intellectual Property Guidelines at Queen's University
Copying and Preserving Your Thesis
This publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.