Warwick uses wavelets for diagnosis

researchers have devised a technique using wavelets to help physicians rapidly diagnose the precise type of brain tumour a patient is suffering from.

Meningiomas are tumours of the brain and nervous system and they account for 20 per cent of all brain tumours. Doctors have to discriminate between the four different subtypes of meningiomas to propose appropriate treatment.

Researchers at Warwick’s Department of Computer Science use wavelets to give an automated analysis of the varying texture of the tumours and guidance to doctors within seconds of being presented the data.

A wavelet filter is a computing tool that acts like a virtual microscope to analyse signals at various frequencies and positions in space. Each different kind of wavelet can be used to analyse a different aspect of a signal.

The Warwick researchers used their wavelet analysis to examine slides of tumour structure and texture from patient case history that have already been diagnosed and treated.

The technique can be used to can examine hundreds of slides with hundreds of thousands of pixels of data and is able to give a full diagnosis of precise tumour type with 80 per cent accuracy. It is intended to support a tumour specialist’s own expert abilities.