J Neurol Surg A Cent Eur Neurosurg 2014; 75 - p36
DOI: 10.1055/s-0034-1383771

Multi-modal Glioblastoma Segmentation: Man versus Machine

N. Porz 1, S. Bauer 2, A. Pica 3, P. Schucht 1, J. Beck 1, R. Kumar Verma 4, J. Slotboom 4, M. Reyes 2, R. Wiest 4
  • 1Department of Neurosurgery, University Hospital Inselspital and University of Bern, Bern, Switzerland
  • 2Institute of Surgical Technology and Biomechanics, University of Bern, Bern, Switzerland
  • 3Department of Radiation Oncology, University Hospital Inselspital and University of Bern, Bern, Switzerland
  • 4Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, University Hospital Inselspital and University of Bern, Bern, Switzerland

Aim: This study was designed to evaluate the reliability of a novel fully automated segmentation tool for brain tumor image analysis in comparison to manually defined tumor segmentations to ease the access of subcompartmental segmentations for neurosurgical planning and adjuvant therapies.

Methods: In this prospective study, we evaluated preoperative MR Images from 25 glioblastoma patients. Two independent expert raters performed manual segmentations. Automatic segmentations were performed using the Brain Tumor Image Analysis software (BraTumIA, http://www.istb.unibe.ch/content/research/medical_image_analysis/software/index_eng.html..). To study the different tumor compartments: the complete tumor volume TV (enhancing part plus non-enhancing part plus necrotic core of the tumor), the TV+ (TV plus edema) and the contrast enhancing tumor volume CETV were identified. We quantified the overlap between manual and automated segmentation by calculation of the sum of product of diameters SPD according to 2D diameter-based criteria for brain tumor assessment, as well as the Dice coefficients, the positive predictive values, sensitivity, relative volume error and absolute volume error.

Results: Comparison of automated versus manual extraction of 2-dimensional diameter measurements showed no significant difference (p = 0.29). Comparison of automated versus manual segmentation of volumetric segmentations showed significant differences for TV+ and TV (p < 0.05) but no significant differences for CETV (p > 0.05) with regard to the Dice overlap coefficients. Spearman’s rank correlation coefficients (ρ) of TV+, TV and CETV showed highly significant correlations between automatic and manual segmentations. Tumor localization did not influence the accuracy of segmentation.

Conclusions: In summary, we demonstrated that BraTumIA supports radiologists and neurosurgeons by providing accurate measures of cross-sectional diameter-based tumor extensions. The automated volume measurements were comparable to manual tumor delineation for CETV tumor volumes, and outperformed inter-rater variability for overlap and sensitivity and constitute a novel tool to ease clinical daily routine.