Elimination of partial volume effect on low grade gliomas segmentation

An accurate segmentation is critical, especially when the low grade gliomas morphological changes remain subtle, resembles peritumeral tissue characteristics. This quantitative measurement depends on the accuracy of the segmentation method used. The undesired partial volume effect, which lies on a boundary between a highly infiltrating low grade gliomas and peritumeral vasogenic edema, makes unerring boundary determination a difficult task. A new approach to segmentation is proposed, that removes the adverse effect on the boundary, which is unwanted especially from the point of view of volume rendering. This approach gives more accurate boundary detection and holes filling after segmentation. A semi-automatic calculation of volumetric size of low grade gliomas has been implemented in this approach. A comparative analysis of manual, seeded region growing and the proposed approach shows more accurate and better performance for 3D volume measurements.