Skip to content

Latest commit

 

History

History
35 lines (21 loc) · 2.98 KB

index.md

File metadata and controls

35 lines (21 loc) · 2.98 KB
Raw

My photo{: style="width:180px; float: right;"}

Overview

I am a final year PhD student in the Centre for Medical Imaging ([CMI](https://www.ucl.ac.uk/medical-imaging/ 'CMI')) at UCL. My supervisors are [Dr Anna Barnes](https://kclpure.kcl.ac.uk/portal/anna.barnes.html 'Anna's KCL Profile'), director of King's Technology Evaluation Centre ([KiTEC](https://www.kcl.ac.uk/lsm/research/divisions/hscr/research/groups/biostatistics/current-projects/kitec/kitec 'KiTEC')) at KCL, and [Prof Gary Zhang](https://iris.ucl.ac.uk/iris/browse/profile?upi=HZHAN50 'Gary's Iris page'), head of the Computational Imaging Group ([CIG](https://cig-ucl.github.io/ 'CIG')) at UCL. My work is focussed around applying statistics and deep learning to quantitative whole-body magnetic resonance imaging (WB-MRI) in the context of metastatic cancer.

Variability of ADC estimates between scanners from whole-body imaging is dominated by within-scanner variance

[ISMRM 2022 abstract](https://index.mirasmart.com/ISMRM2022/PDFfiles/1685.html 'ISMRM 2022 abstract')

We investigate the reliability of whole-body imaging apparent diffusion coefficient (ADC) estimates from subjects tested and retested within- and between-scanners from different vendors with minimal differences in acquisition protocol and post-acquisition analysis. We show substantial within-subject variation in extracranial ADC estimates within- and between-scanners as measured by Limits of Agreement. We additionally show between-scan variability between scanners is dominated by between-scan variability within a scanner. We therefore conclude a post-acquisition method for reducing within-scanner variation is required to improve the reliability of ADC estimates.

See the abstract presentation I gave at ISMRM 2022 on youtube:

My photo

Automatic detection of Nyquist ghosts in whole-body diffusion weighted MRI using deep learning

[ISMRM 2021 abstract](https://index.mirasmart.com/ISMRM2021/PDFfiles/2445.html 'ISMRM 2021 abstract')

Despite its potential as an imaging biomarker in assessing tumor response to therapy, use of ADC as a quantitative endpoint is not routine in clinical practice. One factor that limits the usefulness of ADC is the presence of artifacts in the constituent diffusion-weighted imaging (DWI) data. In this study, we propose a supervised deep-learning approach to detect the presence of Nyquist ghosts in axial DWI slices of the abdomen, achieving a test accuracy of 81.5%. The detection and removal of these artifacts could help improve the reproducibility of quantitative ADC measurements.

See the abstract presentation I gave at ISMRM 2021 on youtube:

My photo

Education

2019-present: PhD in Medical Imaging, University College London

2018-2019: MRes in Medical Imaging, University College London

2013-2017: MSci in Physics, University of Birmingham