eprintid: 10173752
rev_number: 15
eprint_status: archive
userid: 699
dir: disk0/10/17/37/52
datestamp: 2023-09-04 20:34:15
lastmod: 2023-09-04 20:34:15
status_changed: 2023-09-04 20:34:15
type: thesis
metadata_visibility: show
sword_depositor: 699
creators_name: Xu, Mou Cheng
title: Deep Learning with Limited Labels for Medical Imaging
ispublished: unpub
divisions: UCL
divisions: B04
divisions: C05
divisions: F42
note: Copyright © The Author 2023.  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.
abstract: Recent advancements in deep learning-based AI technologies provide an automatic tool to revolutionise medical image computing. Training a deep learning model requires a large amount of labelled data. Acquiring labels for medical images is extremely challenging due to the high cost in terms of both money and time, especially for the pixel-wise segmentation task of volumetric medical scans. However, obtaining unlabelled medical scans is relatively easier compared to acquiring labels for those images.

This work addresses the pervasive issue of limited labels in training deep learning models for medical imaging. It begins by exploring different strategies of entropy regularisation in the joint training of labelled and unlabelled data to reduce the time and cost associated with manual labelling for medical image segmentation. Of particular interest are consistency regularisation and pseudo labelling. Specifically, this work proposes a well-calibrated semi-supervised segmentation framework that utilises consistency regularisation on different morphological feature perturbations, representing a significant step towards safer AI in medical imaging. Furthermore, it reformulates pseudo labelling in semi-supervised learning as an Expectation-Maximisation framework. Building upon this new formulation, the work explains the empirical successes of pseudo labelling and introduces a generalisation of the technique, accompanied by variational inference to learn its true posterior distribution. The applications of pseudo labelling in segmentation tasks are also presented. Lastly, this work explores unsupervised deep learning for parameter estimation of diffusion MRI signals, employing a hierarchical variational clustering framework and representation learning.
date: 2023-07-28
date_type: published
oa_status: green
full_text_type: other
thesis_class: doctoral_open
thesis_award: Ph.D
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 2038780
lyricists_name: Xu, Moucheng
lyricists_id: MXUAX99
actors_name: Xu, Moucheng
actors_id: MXUAX99
actors_role: owner
full_text_status: public
pagerange: 1-1
pages: 165
institution: UCL (University College London)
department: Medical Physics and Biomedical Engineering
thesis_type: Doctoral
citation:        Xu, Mou Cheng;      (2023)    Deep Learning with Limited Labels for Medical Imaging.                   Doctoral thesis  (Ph.D), UCL (University College London).     Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/10173752/1/Xu_10173752_Thesis_sig-removed.pdf