Abstract
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. 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. 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. 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.
Highlights
BACKGROUND AND PURPOSERobust, automated segmentation algorithms are required for quantitative analysis of large imaging datasets
Iterative probabilistic voxel labeling defined tumor volumes that were highly consistent with operator-defined volumes
Analysis showed no statistical difference among operator-derived volumes, so operator 1 was selected as the basis for image comparison
Summary
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. The Cancer Imaging Archive MR images of glioblastoma tumors from The Cancer Imaging Archive were downloaded in June 2013. Subjects were excluded when images contained a prohibitive amount of motion or distortion artifacts. Our algorithm was developed in a “pilot” set of 10 subjects from the TCIA. The algorithm was tested in 2 sets of 15 subjects selected from the TCIA that were not used during development. TCIA MR images were acquired from a number of institutions whose scanners differed by manufacturer and model and whose images varied by sequence, quality, and spatial resolution. TCIA MR images were acquired from a number of institutions whose scanners differed by manufacturer and model and whose images varied by sequence, quality, and spatial resolution. (On-line Tables 1 and 2)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
