Data-Driven Approaches to the Early Detection of Heart Disease II

Location: Melbourne, VIC

Duration: 3-4 months

Project Background

Early identification or prediction of the likely onset of cardiovascular disease, diabetes and obesity are crucial to improving public health. The Baker Heart and Diabetes Institute is a globally significant medical research organisation working to address these medical challenges.

In partnership with the Centre for Astrophysics & Supercomputing and the Iverson Health Innovation research Institute at Swinburne University of Technology, the Baker Heart and Diabetes Institute is investigating the translation of data-driven processes and techniques from astronomy and astrophysics into the domain of medical imaging and diagnosis, with the aim of developing faster, more robust, and more powerful diagnostic tools.

The goal is to apply established and well-tested methods from astrophysics to the early detection of heart disease, through two initial projects: (1) detection of early aortic valve disease; and (2) quantification of cardiac calcification. In both cases, discovery and diagnosis requires new visualisation and analysis methods within a data-intensive context.

This Project is an initiative of the Australian Government being conducted as part of the National Collaborative Research Infrastructure Strategy and administered by Astronomy Australia Ltd.

Research to be Conducted

The Baker Heart and Diabetes Institute has identified two projects with a focus on discovery in imaging data and thus are expected to have strong synergies with astronomy data analysis and visualisation processes:

1. Detection of early aortic valve disease from echocardiograms. This requires low-signal-to-noise detection within grey scale images, where the overall gain of the image is suppressing the visibility of the disease signature. Early detection of aortic valve disease in the preclinical phase may allow interventions to limit progression, which have failed in advanced disease.

2. Quantification of cardiac calcification. This involves the automated detection and quantification of specks of calcium in the heart, in a lung computed tomography (CT) scan. Historically, this signal has been ignored as irrelevant to the reason for the CT scan (e.g. screening for cancer). However, there is now clear evidence that this is an important marker of occult cardiac disease which warrants treatment and follow-up.

The research will follow a four-stage process: (1) Establish (understand the problem for the medical researchers, select and gain access to relevant data); (2) Prototype (identify and trial relevant methods from astronomy); (3) Implement (implement the most promising technique); and (4) Evaluate (critically assess the approach and outcomes).

Skills Required

If you’re a PhD student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:

• Demonstrated experience in conducting astronomy/astrophysics research
• Demonstrated computer programming skills
• Experience with astronomical image processing or analysis
• Experience with machine learning or artificial intelligence techniques

Expected Outcomes

The goal is to identify and translate astronomical data analysis and discovery methods to medical research, achieving a positive impact on public health through the development of new techniques for the early detection of heart disease. The intern will be expected to complete a pilot study demonstrating the choice of suitable methods, application of the methods to one, or both, of the research challenges (detection of early aortic disease and quantification of cardiac calcification), and develop a detailed research plan for the next stages of the investigation. The intern will be required to produce a technical report and present the outcomes of the project to researchers at the Baker Heart and Diabetes Institute and Swinburne University of Technology.

Additional Details

The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.

It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner.  The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

Applications Close

22 January 2020

Reference

APR – 1311