Algorithmic data used in two of the most common methods of breast screening have been analysed in new research led by La Trobe University computer scientist Professor Phoebe Chen.
The two techniques are Microarray DNA tissue sampling and diagnostic medical imaging, such as ultrasound, X-ray, Computed Tomography (CT) scan and Magnetic Resonance Imaging (MRI).
The results of the research suggest an algorithmic formula known as the SMO (Sequential Minimal Optimisation) performs best in early detection of breast cancer.
The study found that SMO achieved better results for the majority of test data than another widely used computational method, the Synthetic Minority Over-sampling Technique (SMOTE), especially for data derived from microarray based DNA sampling diagnostics.
Professor Chen, Chair and Director of Research in Computer Science and Computer Engineering said: ‘From a clinical view, detecting early-stage breast cancer is difficult.
‘Early detection requires accurate and reliable diagnostic processes and the use of robust prediction techniques. Our aim is for these findings to help guide clinicians to the best suited formula to identify breast cancer in its early stages,’ Professor Chen said.
Better chance of treatment success
‘With early identification of tumour types and treatment we hope these findings will help reduce breast cancer-related death.’
Breast cancer is the most common cancer for Australian women. Recent research shows the chance of a woman being affected by invasive breast cancer at some point in her lifetime is about one in eight.
With a fatality rate of one in 35, it is the second leading cause of cancer-related death for Australian women.
Difficult to treat in advanced stages, Professor Chen says, early diagnosis of breast cancer means patients have a much greater chance of being treated successfully.
Step towards better chemo and radiation therapy
Meanwhile other research – this time on the Bendigo campus – has demonstrated partial success in yet another step in the fight against cancer.
A team from the School of Pharmacy and Applied Sciences are testing compounds that may one day be used to improve conventional chemotherapy and radiation treatments by reducing the immunity of cancer cells to such treatments.
The researchers involved are Dr Saleh Ihmaid, Dr Jasim Al-Rawi, Dr Christopher Bradley and Dr Michael Angove. ‘Radiation treatments work by causing breaks in the DNA of tumour cells but tumour cells have ways of repairing the damage caused by conventional treatments,’ said Dr Bradley.
Maximising sensitivity of tumour cells
‘Consequently, very high dosages of radiation therapy and chemotherapy are required, which increases the potential for damage to non-cancerous body tissue.
‘We are testing 60 compounds that carry an enzyme known as DNA-PK. This enzyme has previously been identified as key to inhibiting a tumour cell’s ability to repair its DNA.
‘Our research is intended to identify the compound that maximises a tumour cell’s sensitivity while exposing patients to the least amount of radiation possible.’
The team is compiling its data in laboratories at Bendigo. Samples are grown in the lab and are also collected at the Peter MacCallum Cancer Centre at the Bendigo Radiotherapy Centre.
The researchers, in association with Dr Murray Robertson, a molecular modelling specialist at Strathclyde University, Glasgow, recently published a series of papers in the European Journal of Chemistry announcing the results of tests of a brace of compounds.
‘The four papers have shown that, partially at least, some of the compounds we have tested do increase a cancer cell’s sensitivity and causes them to die with much less radiation.
‘While this research is still many years away from clinical trials with patients, the success of our ongoing tests as well as those by other independent research groups worldwide, are a positive step forward,’ said Dr Bradley.