Varsavsky, Thomas;
(2024)
Overcoming Challenges in Automated Neuroimaging Analysis: Learning from Heterogeneous Data with Limited Supervision.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Varsavsky_thesis.pdf - Other Download (10MB) | Preview |
Abstract
Clinical neuroimaging using magnetic resonance imaging (MRI) is crucial for diagnosis and prognosis of most neurological pathologies including but not limited to brain cancers, stroke, Alzheimer’s disease and multiple sclerosis. The interpretation of these brain scans is an expert manual task performed by highly skilled neuroradiologists. Through the advent of modern computer vision techniques, a series of tools have been developed to aid in the analysis of these images by human assessors, however many challenges remain to provide timely and accurate segmentations, bounding boxes, classifications or automated reports from these scans. This thesis addresses three major challenges in automating such processes: 1) Learning from scans of unknown modality 2) Learning from scans which have large variability in acquisition parameters 3) Learning from limited supervision (e.g radiological reports or image-wide labels).
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Overcoming Challenges in Automated Neuroimaging Analysis: Learning from Heterogeneous Data with Limited Supervision |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2024. Original content in this thesis is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/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 Med Phys and Biomedical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10190170 |
Archive Staff Only
 |
View Item |
