Sizing up tumours

A US researcher has received $400,000 from the National Institutes of Health to develop a computer program to analyse brain scans produced by magnetic resonance imaging (MRI).

Prof Mubarak Shah and his collaborators from the University of Central Florida (UCF) plan to work together on the complex task of automatically measuring and comparing the size of tumours in 3D from MRI scans.

'Radiologists use computers to look at scans, but this is taking the next step - allowing computers to help radiologists analyse the pictures and enabling an automated method to calculate the size of tumours,' he said.

Radiologists are typically hindered in their analyses by a variety of factors, such as tumours that are irregular in shape or have jagged edges, tumours with liquefied centres, or surrounding tissue that is deformed or changing shape.

Shah said some of the challenges include making sure the typically low-resolution scans can be converted to the high-resolution images needed for computers to precisely measure the tumours.

He also must perform extensive experiments with a large data set to validate his method. To do so, he has formed a partnership with a UCF biostatistician, Xiaogang Su, to ensure that the measurements are statistically correct.

The automated analysis of a small data set using Shah’s preliminary method has already shown to be up to 90 per cent accurate compared to the analyses provided by the radiologists.