This year the ACRF Image X Institute is thrilled to offer three summer research scholarships.

The scholarships are offered on behalf of the Cancer Imaging and Targeted Radiotherapy Translational Program, which is a partnership between universities, local health districts and industry. The program aims to translate a pipeline of cancer imaging and targeted radiotherapy medical devices from the discovery phase to broad clinical practice. These scholarships provide an opportunity for students studying at the University of Sydney with a background in physics, mathematics, computer science, biomedical or electrical engineering to undertake a summer vacation research project with investigators in the program.

Three top applicants will be invited to choose from the projects below. Scholarships will be awarded based on the student’s academic transcript, relevant academic background or any research experience.

More information: email image-x.contact@sydney.edu.au

Application Deadline: Sunday, December 6
Click Here to Apply Now

 

 

Projects


 

Real-time tumour tracking with deep learning

Supervisors:
Dr Trang Nguyen, Prof Paul Keall, Dr Jeremy Booth.

Project description:
This project will explore the use of deep learning to track cancer during radiotherapy with the goal of making the treatment more accurate and precise.

From 2015-2020, we have developed and clinically translated a world-first technology to track the tumour during radiotherapy treatment for cancer patients in 4 clinical trials. The goal is to harness deep learning to personalise treatment and optimise treatment delivery, maximise cancer treatment success and minimise possible side effects.

The right candidate will have an enthusiasm for medical technology development and a can-do attitude. Familiarity and experience with at least one programming language e.g. Matlab, Python, C, etc. will be advantageous.

New imaging technologies in radiation therapy

Supervisors:
A’Prof Ricky O’Brien, Dr Tess Reynolds, Dr Owen Dillon

Project description:
Respiratory and cardiac motion are challenging to deal with when imaging the lungs for lung cancer radiation therapy.  This project will work on new technologies to account for both cardiac and respiratory motion for better targeted radiation therapy. 

The project will suit students from a science background (engineering, computer science, physics or mathematics.

Monte Carlo simulation of nanoparticle-enhanced lung radiotherapy

Supervisors:
Dr Hilary Byrne, Prof Zdenka Kuncic

Project description:

Using a Monte Carlo radiation transport simulation tool, this project will investigate the micro-scale pattern of dose deposition in the inhomogeneous air-water mix of the lung. Alteration of this pattern in the presence of nanoparticles and magnetic fields can be explored. Experience with Monte Carlo simulation and medical physics would be an advantage.

 

 

Quantitative assessment of liver function using MRI

Supervisors:
Dr Sirisha Tadamilla & Prof Annette Haworth

Project description:

Many patients with liver cancer have underlying liver cirrhosis with low baseline liver function. Treating the cancer with high doses of radiation can cause major complications. We are investigating novel magnetic resonance imaging techniques to accurately measure liver function prior to, and during treatment so that we can deliver radiation to the tumour safely.

The summer project will develop methods for quantitative assessment of  liver perfusion and function from different phase data.

Using kurtosis as a measure of prostate cancer aggressiveness

Supervisors:
Dr Sirisha Tadamilla, Ms Erin Wang & Prof Annette Haworth

Project description:

Diffusion-weighted imaging (DWI) is an MRI technique that is often used to assess tumour composition and microstructure.

Quantitative analysis of DWI data is used to generate apparent diffusion coefficient (ADC) parametric maps, under the assumption that the diffusion of water molecules follows a Gaussian distribution. However, this assumption is only true for pure liquids and gels, not for complex biological tissues which contain cell membranes and other barriers to diffusion. Kurtosis (K) is a statistical metric used to quantify the shape of a probability distribution.

In this project we will investigate the hypothesis that kurtosi can better stratify prostate aggressiveness. Within the project, a DWI analysis pipeline will be developed using Python to obtain kurtosis as a measure of prostate cancer aggressiveness in patients undergoing radiation therapy.

AI model for prediction of operability of breast cancer after primary systemic therapy

Supervisors:
Dr Sirisha Tadamilla, Dr Robert Finnegan & Prof Annette Haworth

Project description:

The PET-LABRADOR clinical trial (https://www.trog.com.au/TROG-1202-PET-LABRADOR) was designed to test the hypothesis that breast MRI and PET-CT imaging can accurately predict operability after radiotherapy, without compromising local control or disease-free survival.

This project will analyse imaging data from this trial to establish the concordance of tumour detection in multiple imaging modalities. This project would suit a student interested in developing this project further through Masters or PhD studies to develop an AI model for prediction of operability of breast cancer after primary systemic therapy