Semi-automated segmentation of pre-operative low grade gliomas in magnetic resonance imaging

Abstract

BackgroundSegmentation of pre-operative low-grade gliomas (LGGs) from magnetic resonance imaging is a crucial step for studying imaging biomarkers. However, segmentation of LGGs is particularly challenging because they rarely enhance after gadolinium administration. Like other gliomas, they have irregular tumor shape, heterogeneous composition, ill-defined tumor boundaries, and limited number of image types. To overcome these challenges we propose a semi-automated segmentation method that relies only on T2-weighted (T2W) and optionally post-contrast T1-weighted (T1W) images.MethodsFirst, the user draws a region-of-interest (ROI) that completely encloses the tumor and some normal tissue. Second, a normal brain atlas and post-contrast T1W images are registered to T2W images. Third, the posterior probability of each pixel/voxel belonging to normal and abnormal tissues is calculated based on information derived from the atlas and ROI. Finally, geodesic active contours use the probability map of the tumor to shrink the ROI until optimal tumor boundaries are found. This method was validated against the true segmentation (TS) of 30 LGG patients for both 2D (1 slice) and 3D. The TS was obtained from manual segmentations of three experts using the Simultaneous Truth and Performance Level Estimation (STAPLE) software. Dice and Jaccard indices and other descriptive statistics were computed for the proposed method, as well as the experts’ segmentation versus the TS. We also tested the method with the BraTS datasets, which supply expert segmentations.Results and discussionFor 2D segmentation vs. TS, the mean Dice index was 0.90 ± 0.06 (standard deviation), sensitivity was 0.92, and specificity was 0.99. For 3D segmentation vs. TS, the mean Dice index was 0.89 ± 0.06, sensitivity was 0.91, and specificity was 0.99. The automated results are comparable with the experts’ manual segmentation results.ConclusionsWe present an accurate, robust, efficient, and reproducible segmentation method for pre-operative LGGs.

Predicting Deletion of Chromosomal Arms 1p/19q in Low-Grade Gliomas from MR Images Using Machine Intelligence

“…We used our semi-automatic LGG segmentation software to segment the tumors in 2D [ 16 ]. First, the user selects the slice where the area of the tumor appears largest, and then draws a region-of-interest (ROI) that completely encloses the tumor and some normal tissue.…”

A Fast Semi-Automatic Segmentation Tool for Processing Brain Tumor Images

“…One note is that the BRATS dataset contained not just glioblastomas but also anaplastic astrocytomas, which are intermediates between GBMs and lower grade gliomas (LGGs). Given the satisfactory accuracy of segmenting this mixed dataset, this provides encouragement that MITKats could be extended to LGGs, which are typically harder to segment (Akkus et al, 2015). Eventual implementation and validation for LGGs and tumors outside the brain would be useful.…”

Volumetric assessment of tumor size changes in pediatric low-grade gliomas: feasibility and comparison with linear measurements

“…Most automatic and semi-automatic algorithms to date, have only reliably been shown to work in gadolinium enhancing lesions such as GBM [14]. In a study by Akkus et al (2015) of semiautomated segmentation of pLGGs on MRI T1 post-contrast and T2 WI, the intra-operator variability was lower than intra-expert variability and inter-operator variability much smaller than inter-expert variability [28]. While this is encouraging for establishing a standardized method of semi-automated analysis tumor volume in future, such methods need specific software, time for the operator to check the segmentation results and may be more useful for very complex and extensive lesions such as plexiform neurofibromas than relatively small pLGG [29].…”