Glioma Dynamics and Computational Models: A Review of Segmentation, Registration, and In Silico Growth Algorithms and their Clinical Applications

Abstract

Tracking gliomas dynamics on MRI has became more and more important for therapeutic management. Powerful computational tools have been recently developed in this context enabling in silico growth on a virtual brain that can be matched with real 3D segmented evolution through registration between atlases and patient brain MRI data. In this paper, we provide an extensive review of existing algorithms for the three computational tasks involved in patient-specific tumor modeling: image segmentation, image registration, and in silico growth modelling (with special emphasis on the proliferation-diffusion model). Accuracy and limits of the reviewed algorithms are systematically discussed. Finally applications of these methods for both clinical practice and fundamental research are also discussed.

Multi-parametric (ADC/PWI/T2-w) image fusion approach for accurate semi-automatic segmentation of tumorous regions in glioblastoma multiforme

“…Recently, several segmentation methods have been proposed for characterization of different brain tumor compartments: region-based active contour models [14][15][16], clustering-based segmentation techniques, such as k-nearest neighbor [17], knowledge-based fuzzy C-means (FCM) clustering [18][19][20][21] or classification approaches [7,22,23], which have shown promise in terms of reduced intra-and inter-observer variability and time efficiency [24,25]. Nevertheless, segmentation of tumor tissues remains a challenging issue, since borders of the heterogeneous tumor and its surrounding tissue are not well-defined in many cases and partial volume effects and MRI inherent noise could complicate the delineation of various regions of the GBM tumor [19].…”

Integrated segmentation of brain tumor images for radiotherapy and neurosurgery

“…The segmentation of tumor-bearing brain images is a highly relevant, but difficult problem in medical image analysis (Angelini et al, 2007). It is desirable to be able to perform this task in an automatized way because manual segmentations are time-consuming and tedious.…”

A Medical Software System for Volumetric Analysis of Cerebral Pathologies in Magnetic Resonance Imaging (MRI) Data

“…In their evaluation, the authors have used six magnetic resonance (MR) studies of three subjects and the Dice Similarity Coefficient (DSC) [9] ranged from 67.21% to 75.63%. Angelini et al [10] have presented an extensive overview of some deterministic and statistical approaches. The majority of them are region-based approaches; more recent ones are based on deformable models and include edge information.…”