CAD method provides earlier detection of brain tumor growth

A computer-assisted diagnosis procedure is able to help clinicians detect the growth of low-grade gliomas, a deadly form of brain tumor, earlier and at smaller volumes than visual comparison alone.

“There is no universally accepted objective technique available for detection of enlargement of low-grade gliomas in the clinical setting; subjective evaluation by clinicians using visual comparison of longitudinal radiological studies is the gold standard,” according to a new study published on Tuesday in the journal PLOS Medicine.

However, researchers contend that a CAD method that digitizes the tumor—leveraging imaging scans to segment it and generate volumetric measures—could help provide clinicians with objective detection of tumor growth.

In the study, tumors of 63 patients in 627 MRI scans were digitized, including 34 grade 2 gliomas with radiological progression and 22 radiologically stable grade 2 gliomas. Investigators compared growth detection by seven physicians aided by the CAD method with retrospective clinical reports.

What they found was that in the case of CAD accurate detection of tumor enlargement was possible with a median of only 57 percent change in tumor volume as opposed to a median of 174 percent change in volume required using standard-of-care clinical methods.

journal.pmed.1002810.g004 (1).tif

Also See: Machine learning automatically identifies brain tumors

Further, in 29 of the 34 patients with radiological progression, the median time-to-growth detection was 14 months for the CAD method vs. 44 months for current standard-of-care radiological evaluation.

“The current practice of visual comparison of longitudinal MRI scans is associated with significant delays in detecting growth of low-grade gliomas,” conclude the study’s authors. “Our findings support the idea that physicians aided by CAD detect growth at significantly smaller volumes than physicians using visual comparison alone.”

Being able to detect low-grade brain tumors earlier and at smaller volumes is critical given that smaller tumor sizes are associated with longer survival times and less neurological morbidity.

“This study does not answer the questions whether to treat or not and which treatment modality is optimal,” acknowledge the authors. “Nonetheless, early growth detection sets the stage for future clinical studies that address these questions and whether early therapeutic interventions prolong survival and improve quality of life.”

For reprint and licensing requests for this article, click here.