Brandao, Patrick;
(2021)
Enhancing endoscopic navigation and polyp detection using artificial intelligence.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Rosa Brandao_10133672_thesis_revised.pdf Download (25MB) | Preview |
Abstract
Colorectal cancer (CRC) is one most common and deadly forms of cancer. It has a very high mortality rate if the disease advances to late stages however early diagnosis and treatment can be curative is hence essential to enhancing disease management. Colonoscopy is considered the gold standard for CRC screening and early therapeutic treatment. The effectiveness of colonoscopy is highly dependent on the operator’s skill, as a high level of hand-eye coordination is required to control the endoscope and fully examine the colon wall. Because of this, detection rates can vary between different gastroenterologists and technology have been proposed as solutions to assist disease detection and standardise detection rates. This thesis focuses on developing artificial intelligence algorithms to assist gastroenterologists during colonoscopy with the potential to ensure a baseline standard of quality in CRC screening. To achieve such assistance, the technical contributions develop deep learning methods and architectures for automated endoscopic image analysis to address both the detection of lesions in the endoscopic image and the 3D mapping of the endoluminal environment. The proposed detection models can run in real-time and assist visualization of different polyp types. Meanwhile the 3D reconstruction and mapping models developed are the basis for ensuring that the entire colon has been examined appropriately and to support quantitative measurement of polyp sizes using the image during a procedure. Results and validation studies presented within the thesis demonstrate how the developed algorithms perform on both general scenes and on clinical data. The feasibility of clinical translation is demonstrated for all of the models on endoscopic data from human participants during CRC screening examinations.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Enhancing endoscopic navigation and polyp detection using artificial intelligence |
| Event: | UCL (University College London) |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2021. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10133672 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
