Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Health Technology and Informatics | en_US |
| dc.contributor.advisor | Yoo, Jung Sun (HTI) | en_US |
| dc.contributor.advisor | Baciu, George (COMP) | en_US |
| dc.creator | Wong, Ngai Nick Alex | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/12757 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Development of an intraoperative imaging technique to specifically visualise peripheral nerves using spectral reflectance and deep neural networks | en_US |
| dcterms.abstract | Nerve preservation is vital for surgery in reducing postoperative adverse effects, i.e., reduction of the action potential of nerves, which might result in significant complications, such as chronic pain, sensory loss, or even ability loss including erectile dysfunction, urinary incontinence, and abnormal vocal cord function. Real-time visualisation of nerves with high accuracy in the operating room is important to guide surgeons to avoid nerve transection. Here, we developed a label-free imaging strategy to provide accurate and safe intraoperative guidance for detecting peripheral nerves. Specific visualisation of peripheral nerves during surgery was successfully demonstrated utilizing strong wavelength-specific reflectance from myelin structure surrounding nerve fibres and real-time segmentation by deep neural networks. | en_US |
| dcterms.abstract | Based on ex vivo and in vivo experiments, we showed the reflectance signal’s changes of nerve and non-nerve tissues at different wavelengths and different imaging depths. These patterns highlighted nerves with a diameter > 1 µm with strong reflectance of myelin at around 900 nm under homogenous ex vivo environment. The developed intraoperative imaging technique has been tested in multiple murine cancer models including breast cancer and glioblastoma to distinguish peripheral nerves mimicking real surgery situation. Notably, the nerves exhibited stronger reflectance under heterogeneous cancer environment compared to relatively homogeneous normal models, which further enhances its translational values in the development of a clinically applicable nerve identification technique in cancer surgery. Based on the optimal optical setting for nerve reflectance, our work employed a deep learning system to highlight the nerve in real-time with high sensitivity and specificity during cancer surgery. This novel technique clearly demonstrated its excellent performance in visualising peripheral nerves particularly in a label-free manner, which will definitely benefit surgery operations to prevent accidental nerve injury, thereby avoiding the risk of having severe side effects that may compromise patient’s life quality after surgery. | en_US |
| dcterms.extent | 173 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2021 | en_US |
| dcterms.educationalLevel | Ph.D. | en_US |
| dcterms.educationalLevel | All Doctorate | en_US |
| dcterms.LCSH | Nervous system -- Imaging | en_US |
| dcterms.LCSH | Nerves, Peripheral | en_US |
| dcterms.LCSH | Computer-assisted surgery | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | open access | en_US |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/12757