|
 A team of European
researchers has developed a computer- based programme that enables physicians
treating patients with brain tumours to obtain faster, more accurate and
entirely objective diagnoses without the need for brain biopsy. In a preliminary
test, the system was used on 16 patients and achieved a 92 per cent rate
of reliability in diagnoses.
Carles Arús, professor at the Department of Biochemistry and Molecular
Biology of Barcelona Autonomous University, led the team in carrying out
the EU funded project INTERPRET (international network for pattern recognition
of tumours using magnetic resonance). He explains that 'The goal of this
project was to develop a computer-based decision support tool, installed
in hospital MRI centres, that enables radiologists and other clinicians
without special knowledge or expertise to diagnose and grade brain tumours
routinely using magnetic resonance spectroscopy (MRS).'
There are 50 different types and grades of malignant tumours. This new
user-friendly tool, drawing on a database with information on 300 brain
tumours, visually classifies the different types of tumours according
to their magnetic resonance spectra. A point on a graph represents each
type of brain tumour. Tumours with a similar origin appear on the graph
in positions close to one another. Radiologists can, therefore, obtain
information on the likelihood of an unknown tumour being either one type
or another according to the area of the graph on which it is found.
Previously, 'although MRS gives significantly improved brain tumour categorisation,
it was not widely used, partly because radiologists had difficulty in
interpreting spectral data,' said Professor Arús. Now, radiologists can
diagnose and grade brain tumours in a simple and efficient way, and; more
importantly, no longer need to resort to brain biopsy which is invasive,
dangerous and does not always give the right answer.
This knowledge-based system is expected to enhance the applicability of
the MRS technique and accelerate its take-up in Europe
For more information in INTERPRET, please visit: http://carbon.uab.es/INTERPRET/
|
