Computer-assisted diagnostics detect brain tumour growth earlier

A computer-assisted diagnostic procedure helps physicians detect the growth of low-grade brain tumours earlier and at smaller volumes than visual comparison alone, according to new research from the University of Alabama at Birmingham.

Low-grade gliomas constitute 15% of all adult brain tumours and cause significant neurological problems, but there is no universally accepted objective technique available for detecting the enlargement of low-grade gliomas in the clinical setting. The current gold standard is subjective evaluation through visual comparison of 2D images from longitudinal radiological studies.

A computer-assisted diagnostic procedure that digitises the tumour and uses imaging scans to segment the tumour and generate volumetric measures could aid in the objective detection of tumour growth by directing the attention of the physician to changes in volume. This is important because smaller tumour sizes are associated with longer survival times and less neurological morbidity.

In the new study, the authors evaluated 63 patients — 56 diagnosed with grade 2 gliomas and seven followed for an imaging abnormality without pathological diagnosis — for a median follow-up period of 150 months, and compared tumour growth detection by seven physicians aided by a computer-assisted diagnostic procedure versus retrospective clinical reports. The computer-assisted diagnostic procedure involved digitising magnetic resonance imaging scans of the tumours, including 34 grade-2 gliomas with radiological progression and 22 radiologically stable grade-2 gliomas. The results of the study are published in the journal PLOS Medicine.

Physicians aided by the computer-assisted method diagnosed tumour growth in 13 of 22 glioma patients labelled as clinically stable by the radiological reports, but did not detect growth in the imaging-abnormality group. In 29 of the 34 patients with progression, the median time-to-growth detection was 14 months for the computer-assisted method compared with 44 months for current standard-of-care radiological evaluation. Using the computer-assisted method, accurate detection of tumour enlargement was possible with a median of only 57% change in tumour volume compared with a median of 174% change in volume required using standard-of-care clinical methods.

The findings suggest that current clinical practice is associated with significant delays in detecting the growth of low-grade gliomas, and computer-assisted methods could reduce these delays. Additional clinical studies are needed to determine whether early therapeutic interventions enabled by early tumour growth detection prolong survival times and improve quality of life.

Image credit: ©stock.adobe.com/au/peterschreiber.media

Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletters and bimonthly magazine.