UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Automating the multimodal analysis of musculoskeletal imaging in the presence of hip implants

Ranzini, Marta Bianca Maria; (2020) Automating the multimodal analysis of musculoskeletal imaging in the presence of hip implants. Doctoral thesis (Ph.D), UCL (University College London). Green open access

[thumbnail of RanziniMartaBiancaMaria_PhD_thesis_deposited.pdf]
Preview
Text
RanziniMartaBiancaMaria_PhD_thesis_deposited.pdf - Accepted Version

Download (57MB) | Preview

Abstract

In patients treated with hip arthroplasty, the muscular condition and presence of inflammatory reactions are assessed using magnetic resonance imaging (MRI). As MRI lacks contrast for bony structures, computed tomography (CT) is preferred for clinical evaluation of bone tissue and orthopaedic surgical planning. Combining the complementary information of MRI and CT could improve current clinical practice for diagnosis, monitoring and treatment planning. In particular, the different contrast of these modalities could help better quantify the presence of fatty infiltration to characterise muscular condition after hip replacement. In this thesis, I developed automated processing tools for the joint analysis of CT and MR images of patients with hip implants. In order to combine the multimodal information, a novel nonlinear registration algorithm was introduced, which imposes rigidity constraints on bony structures to ensure realistic deformation. I implemented and thoroughly validated a fully automated framework for the multimodal segmentation of healthy and pathological musculoskeletal structures, as well as implants. This framework combines the proposed registration algorithm with tailored image quality enhancement techniques and a multi-atlas-based segmentation approach, providing robustness against the large population anatomical variability and the presence of noise and artefacts in the images. The automation of muscle segmentation enabled the derivation of a measure of fatty infiltration, the Intramuscular Fat Fraction, useful to characterise the presence of muscle atrophy. The proposed imaging biomarker was shown to strongly correlate with the atrophy radiological score currently used in clinical practice. Finally, a preliminary work on multimodal metal artefact reduction, using an unsupervised deep learning strategy, showed promise for improving the postprocessing of CT and MR images heavily corrupted by metal artefact. This work represents a step forward towards the automation of image analysis in hip arthroplasty, supporting and quantitatively informing the decision-making process about patient’s management.

Type: Thesis (Doctoral)
Qualification: Ph.D
Title: Automating the multimodal analysis of musculoskeletal imaging in the presence of hip implants
Event: UCL (University College London)
Open access status: An open access version is available from UCL Discovery
Language: English
Additional information: Copyright © The Author 2020. 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 > 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 Chemical Engineering
URI: https://discovery.ucl.ac.uk/id/eprint/10115316
Downloads since deposit
107Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item