Semi-automated segmentation of brain tumor lesions in MR Images.
Saraswathy S, Crawford F, Nelson S
University of California
Objective, rapid and reproducible methods of measuring tumor volume are of utmost importance to clinicians in assessing the response to treatment and in guiding appropriate therapy for serial studies. We implemented and validated a region growing method based on simple statistics that could be applied to images with different types of contrast and has the potential for not only reducing the variability in measurements, but also the time required to analyze serial changes in lesion volume. The algorithm was used to successfully segment hyperintense lesions in FLAIR and T2 images and both hyper-and hypointense lesions separately in T1 contrast enhanced images. The results show that volume measurements obtained using this method are in good agreement with manually segmented data.