UC San Diego

Background and purpose

Robust, automated segmentation algorithms are required for quantitative analysis of large imaging datasets. We developed an automated method that identifies and labels brain tumor-associated pathology by using an iterative probabilistic voxel labeling using k-nearest neighbor and Gaussian mixture model classification. Our purpose was to develop a segmentation method which could be applied to a variety of imaging from The Cancer Imaging Archive.

Materials and methods

Images from 2 sets of 15 randomly selected subjects with glioblastoma from The Cancer Imaging Archive were processed by using the automated algorithm. The algorithm-defined tumor volumes were compared with those segmented by trained operators by using the Dice similarity coefficient.

Results

Compared with operator volumes, algorithm-generated segmentations yielded mean Dice similarities of 0.92 ± 0.03 for contrast-enhancing volumes and 0.84 ± 0.09 for FLAIR hyperintensity volumes. These values compared favorably with the means of Dice similarity coefficients between the operator-defined segmentations: 0.92 ± 0.03 for contrast-enhancing volumes and 0.92 ± 0.05 for FLAIR hyperintensity volumes. Robust segmentations can be achieved when only postcontrast T1WI and FLAIR images are available.

Conclusions

Iterative probabilistic voxel labeling defined tumor volumes that were highly consistent with operator-defined volumes. Application of this algorithm could facilitate quantitative assessment of neuroimaging from patients with glioblastoma for both research and clinical indications.