Matt Moores

Matt Moores

Qualifications

  • B.Inf.Tech. (Computing Science) with distinction, QUT
  • M.Math.Sci. (Statistical Modelling), QUT

Position

PhD candidate and sessional academic

Supervisors:

  • Prof. Kerrie Mengersen
  • Dr. Fiona Harden, Medical Radiation Sciences, Faculty of Health
  • Prof. Ian Turner

Areas of interest

  • Biostatistics
  • Bayesian inference
  • Spatial models
  • Computation

Current project

My PhD project is in medical image analysis of cone-beam computed tomography (CT). These 3D images have a low contrast-to-noise ratio, so prior information needs to be considered in order to accurately interpret the voxel intensity values and identify the regions of interest. I have used a hidden Markov random field (Potts model) to represent the spatial homogeneity between the labels of neighbouring voxels. Informative priors are derived from a previous image of the same subject, as well as from published studies. By highlighting changes in these images, I aim to assist radiotherapists in their decision making, thereby improving the accuracy of image-guided radiotherapy and reducing the incidence and severity of side-effects experienced by cancer patients receiving the treatment. This project is a collaboration between QUT and the Radiation Oncology Mater Centre, QHealth.

Abstracts:

QUT ePrints

Informative Priors for Segmentation of Medical Images,” presented at Bayes on the Beach 2011

“Analysis of Cone-Beam CT using prior information,” academic poster presented at the SSAI Young Statisticians’ Conference, 2011

“A Bayesian spatial model with informative priors, with application to cone-beam computed tomography,” presented at the Australian Statistical Conference 2012

“Segmentation of cone-beam CT using a hidden Markov random field with informative priors,” academic poster presented at the International Conference on the Use of Computers in Radiation Therapy (ICCR 2013)

Pre-computation for ABC in image analysis,” contributed talk presented at the 5th IMS-ISBA joint meeting (MCMSki IV)

Precomputation for SMC-ABC with undirected graphical models,” invited talk at ABC in Sydney

About

Prior to commencing my PhD, I was involved in the Visible Cell project at the Institute for Molecular Bioscience. I’ve also worked in R&D for various international companies: writing software for editing a 3D wireframe mesh of a human face; a multimedia search engine and a cable TV programme guide using speech recognition; and an electronic medical records database based on the ANSI HL7 standard. My masters project investigated Gaussian mixture distributions of exhaled particles.

In my spare time I enjoy roleplaying games and playing capoeira.

https://mattstats.wordpress.com/

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s