ProfessorPatrick Brennan

Project Opportunities

Title: Phase Contrast Imaging of the Breast

Summary of opportunity:

A novel method for imaging breast cancer

Opportunity synopsis:

X-ray breast imaging is the mainstay for regular screening of women over the age of 40, but current methods present with three significant limitations:

• less than optimal sensitivity and specificity (currently at 60-70 and 80% respectively);
• involvement of excessive radiation dose to the radiosensitive breast;
• painful compression of the breast (to maximise imaging contrast).

These limitations lead to reduced detection of early cancers, excessive recall of disease-free women, higher mortality, unnecessary irradiation of healthy tissue, and poor engagement of women with breast cancer screening.

In collaboration with world experts in Health Sciences, Medicine, Science, and Engineering and Information Technologies, we will explore a completely innovative solution to address these limitations: in-line phase-contrast computed tomography (PCT) of the breast. Since Roentgen's discovery of X-rays in 1895, clinical systems have relied on recording the intensity (number) of X-rays transmitted through the body. Instead our system exploits changes to the X-ray phase (wave-form) occurring within the body, which contains critically important biologic information. Our early pilot data show a 20-fold improvement in the signal-to-noise ratio (thus improved sensitivity and specificity) at the same X-ray dose and a 400-fold reduction in radiation dose without image quality loss, compared to conventional CT breast imaging. With such improvements, painful compression may not be required. The proposed work will involve irradiation of excised breast tissues and a novel patient experiment with images being assessed by the leading expert radiologists in Australia,USA, Europe and SE Asia using our $4m BREAST platform.

Project Opportunities

Title: Enhancing breast cancer detection using a novel research and educational platform: BREAST II

Summary of opportunity:

Developing and implementing BREAST II as an interactive research and educational platform to transform breast cancer detection.

Opportunity synopsis:

Early diagnosis of breast cancer results in a 97% survival rate. However, to achieve this survival rate and even more importantly to achieve zero deaths from breast cancer by 2030, we must significantly reduce the 30-40% of breast cancers that fail to be diagnosed. Through BREAST, a world-first research and educational interactive infrastructure that uses the latest technological innovations, over the last 4-5 years, we, with local and international experts have identified reasons for mis-diagnoses and presented exciting translational solutions. To date the work has been shown to improve radiologists' performance by a mean value of 34%, an improvement unparalleled by any other innovation in recent years. Its unprecedented success has led to engagement by 80% of breast-reading clinicians across all states in Australia and research agreements with world-leading imaging scientists across Australia, North and South America, Asia and Europe. It has contributed to 20 PhD projects and 70 publications.

We have a clear plan for consolidating our achievements with BREAST so that early breast cancer diagnosis within screening and symptomatic facilities continues to be transformed. It also provides a comprehensive work schedule enabling the introduction of 5 highly exciting innovations reflecting recent technological advancements, social responsibilities and educational needs. With regard to these innovations, BREAST II will specifically incorporate:

• Digital breast tomosynthesis (DBT) image sets: DBT is rapidly transforming breast cancer imaging in Australia and elsewhere, however currently there is no on-line training and performance monitoring system anywhere;
• Data files focusing on underserved populations: women of different cultures have different breast densities thus effectiveness of detecting cancer may vary. We will focus on indigenous populations in Australia and women in China and Southeast Asia;
• Educational image sets of high difficulty: particularly those with architectural distortion and lesion speculation so that readers can focus learning in these areas;
• Data sets designed for registrar radiologists.
• Pathology image files for pathologists: pathology is considered to be the diagnostic truth, however agreement between pathologists can be as low as 48%.

Each of the above items can be a PhD project.

Project Opportunities

Title: Are there a subset of normal mammographic images that do not require paired radiologist reading?

Summary of opportunity:

Automatic detection of normal mammography images

Opportunity synopsis:

The efficiency of breast screening programs relies on the accurate interpretation of normal mammograms. Currently normal cases make up approximately 98% of BreastScreen Australia's examinations contributing significant to radiologists' workloads and service expenses. At present, BreastScreen relies on paired reading of each mammogram even though there is a paucity of data on whether all normal mammograms require such a rigorous approach. It is well reported that increased fibroglandular tissue (density) can reduce specificity since obscuring radiopaque regions of the image may look suspicious. On the other hand a breast comprising of mainly fatty tissue is more radiolucent and may facilitate a greater level of confidence that the image is normal. Whilst several publications have provided some overall indicators for recognizing normal cases, there is little awareness of the specific features that define easy-to-interpret normal mammograms that may not require a rigorous double-reading approach. There is even less data supporting cost-effective solutions for the interpretation of the 800,000 normal cases that present each year in Australia.

The current work aims to build on the current evidence by examining a much larger series of normal mammograms available from the BREAST platform and BreastScreen NSW. In particular this work will have the following five aims:

1. Identify those cases where a second read did not add anything extra to the primary diagnosis;
2. Establish a descriptor containing the features that characterizes these easy-to-interpret cases;
3. Test our descriptor prospectively on a further group of cases that contain normal and cancer images;
4. Develop a computed aided platform to automatically recognise these normal images;
5. Identify the cost-effective implications of our recommendations.

With this project, there are opportunities here for PhD students interested in Diagnostic Imaging, Computer Science and Electrical Engineering.

----------Current Research Projects----------

_x000D_ PhD and master's project opportunities

_x000D_

• _x000D_ Phase Contrast Imaging of the Breast
• _x000D_ Enhancing disease detection using novel educational platforms
• _x000D_ Radiomics and Artificial Intelligence