ScienceBeta

Menu

Computer-assisted Method Helps Diagnose Glioma Tumor Growth

glioma diagnosis

A computer-assisted diagnostic procedure helps physicians detect the growth of low-grade brain tumors earlier and at smaller volumes than visual comparison alone, according to a new study by Hassan Fathallah-Shaykh of the University of Alabama at Birmingham, and colleagues. Additional clinical studies are needed to determine whether early therapeutic interventions enabled by early tumor growth detection prolong survival times and improve quality of life.

Low-grade gliomas constitute 15% of all adult brain tumors and cause significant neurological problems. 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.

Tumor Growth Detection

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

Time to growth detected by computer-assisted-diagnosis and visual comparison.
Time to growth detected by computer-assisted-diagnosis and visual comparison.
Credit: Fathallah-Shaykh HM, et al

In this study, the authors evaluated 63 patients – 56 diagnosed with grade 2 gliomas and 7 followed for an imaging abnormality without pathological diagnosis – for a median follow-up period of 150 months, and compared tumor growth detection by seven physicians aided by a computer-assisted diagnostic procedure versus retrospective clinical reports.

The computer-assisted diagnostic procedure involved digitizing magnetic resonance imaging scans of the tumors, including 34 grade 2 gliomas with radiological progression and 22 radiologically stable grade 2 gliomas. Physicians aided by the computer-assisted method diagnosed tumor growth in 13 of 22 glioma patients labeled as clinically stable by the radiological reports, but did not detect growth in the imaging-abnormality group.

Delay Reduction

In 29 of the 34 patients with progression, the median time-to-growth detection was 14 months for the computer-assisted method compared to 44 months for current standard-of-care radiological evaluation.

Using the computer-assisted method, accurate detection of tumor enlargement was possible with a median of only 57% change in tumor volume compared to a median of 174% change in volume required using standard-of-care clinical methods.

Because low-grade gliomas grow at variable but slow rates, clinicians need to compare a large number of longitudinal images spanning several months or years to detect growth, leading to significant delays in detection of tumor enlargement. Readily available computer-generated tumor outlines combined with longitudinal volumetric data and the identification of a statistically significant change of point aid a rapid diagnosis of tumor enlargement.

Hence, CAD could avoid unpredictable delays and improve the determination of efficacy of new therapeutic interventions. Furthermore, early growth detection holds the potential of lowering the morbidity, and perhaps mortality, of patients with low-grade gliomas, a possibility that needs to be tested in prospective studies.

Fathallah-Shaykh HM, DeAtkine A, Coffee E, Khayat E, Bag AK, Han X, et al.
Diagnosing growth in low-grade gliomas with and without longitudinal volume measurements: A retrospective observational study
PLoS Med 16(5): e1002810. https://doi.org/10.1371/journal.pmed.1002810