A cooperative framework for segmentation of MRI brain scans
Introduction
The development of reliable methods of segmentation is a central prerequisite to exploit in deep information contained in magnetic resonance imaging (MRI) brain scans. In particular, the functional organization of the cortical areas, as assessed by functional brain imaging, can only be visualized and understood with a precise delineation of the cortical ribbon. Automated procedures for the accurate cortex delineation rely on the precise segmentation of the brain tissues. The automatic segmentation of MR images is a complex task for two main reasons: the inter-subject variability of the human brain anatomy that restricts the use of general knowledge and, inherent to the acquisition process, image artifacts that are difficult to correct, such as partial volume effects and non-uniformity of the gray level intensities for a given tissue, essentially due to inhomogenities of the excitation pulse (radio-frequency field). As an example, the non-uniformity of the gray levels for gray matter tissue (GM), within and between images is shown in Fig. 1. The importance of these gray level variations motivates the use of an adaptative segmentation process.
Many approaches have been proposed for MRI segmentation (for a review see Refs. [5], [32]). We classify them in data-driven approaches and model-based approaches. Although generally used independently, we consider the two approaches as complementary, and propose to integrate them in a cooperative framework to benefit from the advantages and specificities of each of them. In order to design such a framework, we introduce three modes of cooperation [12], integrative, augmentative and confrontational cooperation between the three systems we have considered: a multi-agent system, a statistical deformable model and an edge detector. The multi-agent system and the edge detector we use are representative of data-driven approaches and the statistical deformable model of model-based approaches. Each system represents a specific source of information about the image contents. The modes of cooperation combine (integrative cooperation) distribute (augmentation cooperation) and oppose (confrontational cooperation) different solutions to a given problem. Cooperation is used at each step of the segmentation process namely: specialization of refine seeded-region-growing agents, fusion of heterogeneous information and retraction over slices.
- •
The specialization step, based on integrative and augmentative cooperation, customizes two sets of specialized agents that segment successively gray matter and white matter (WM). In addition to general knowledge about brain anatomy and brain scans, the statistical 2D deformable model provides valuable information on the brain boundary to position the GM agents that allow eventually the localization of WM agents.
- •
The fusion step relies on augmentative and confrontational cooperation. It leads to the refinement of the detection of the brain boundary from both the region classification obtained via the multi-agent system and the edge detection provided by the edge detector. The refinement process is based on several specific agents working concurrently along the brain boundary.
- •
The retroaction step uses integrative and confrontational cooperation. It allows the improvement of the current segmentation and the transmission of information to initialize the segmentation of contiguous slices. Although, we use a 2D deformable model, this step achieves a 2.5D segmentation.
In the remainder of the paper, we briefly present in Section 2, a state of the art on MRI brain scans segmentation. We detail, in Section 3, the different systems currently present in our framework. Section 4 describes the complete segmentation process to enlighten the three modes of cooperation we propose. Section 5 is devoted to the evaluation of the system performance in using phantoms provided by the Montreal Neurological Institute (MNI). Then, in Section 6 we discuss several aspects of our work for segmentation of MRI brain scans and point out work under development.
Section snippets
State of the art
We separate the numerous approaches proposed in the literature in two main categories depending whether they use models (model-based approaches) or mainly the gray levels present in the images (data-driven approaches). We note that accordingly to this categorization, region-based classification techniques rather use local models (data-driven approaches) and implicit or explicit knowledge, whilst edge-based detection methods rely on global models and implicit knowledge.
The individual systems
Three individual systems are currently used in our framework, which generate and use different types of information and knowledge (Fig. 2).
- •
The multi-agent system that segments MRI scans, is composed of seeded-region-growing and edge detection autonomous entities called agents. It has a pivotal role in our framework, the other systems playing the role of information providers via our cooperation modes. It processes local gray level information through a priori domain knowledge and a statistical
Complete segmentation process
In our framework, cooperation is the central mechanism to achieve the segmentation. The three modes of cooperation we introduce are detailed in observing the complete process of segmentation at work.
Evaluation
Because it is impossible to establish ground truth with real images, we have used, to perform an accurate evaluation of our framework, the realistic digital brain phantom provided by the Montréal Neurologic Institute (http://www.bic.mni.mcgill.ca/brainweb) and largely used for validation purposes [6].
Discussion
In the context of MRI brain scan segmentation, we propose a framework to operationalize cooperation between several heterogeneous sources of information. Cooperation is often restricted (1) to the sequential ordering of specialized techniques responsible of a part of the segmentation process [15], [28], [30] or (2) to the exchange of low level information contained in the images (gray level, gradient or variance) [19]. Centered on a multi-agent system, our framework introduces three modes of
Acknowledgements
Laurence Germond has a Ph.D. grant from the French Ministry of Research and Technology. Financial support from the European Commission (ALLIANCE project) is gratefully acknowledged. We wish to thank Professor Alain Chehikian for his stimulating advice and for providing us with his software for edge detection.
References (32)
- et al.
MRI segmentation: methods and applications
Mag. Reson. Imag.
(1995) - et al.
Cortical surface-based analysis I: segmentation and surface reconstruction
NeuroImage
(1999) - et al.
Segmentation of the brain tissue from magnetic resonance images
Med. Image Anal.
(1996) - et al.
Deformable models in medical images analysis: a survey
Med. Image Anal.
(1996) - et al.
Segmentation of 2d and 3d objects from MRI volumes using constrained elastic deformations of flexible Fourier contour and surface models
Med. Image Anal.
(1996) Information combination operators for data fusion: a comparative review with classification
IEEE Trans. Syst. Man. Cybernet.
(1996)- et al.
A game theoretic approach to integration of modules
IEEE Trans. Patt. Anal. Mach. Intell.
(1994) Filtres récursifs pour l'estimation du gradient et de la détection des contours par interpolation de splines
Trait Signal
(1997)- et al.
A neural network-based stochastic active contour model (nns-snake) for contour finding of distinct features
Image Vis. Comput.
(1995) - et al.
Design and construction of a realistic digital brain phantom
IEEE Trans. Med. Image
(1998)
The use of active shape models for locating structures in medical images
Image Vis. Comput.
An active contour model for mapping the cortex
IEEE Trans. Med. Image
Segmentation an interpretation of MR brain images
IEEE Trans. Med. Image
Markov random field segmentation of brain MR images
IEEE Trans. Med. Image
Cited by (50)
Multi-agent medical image segmentation: A survey
2023, Computer Methods and Programs in BiomedicineParticle method for segmentation of breast tumors in ultrasound images
2020, Mathematics and Computers in SimulationCitation Excerpt :Clearly, the model is a variant of the charged particles [28], mentioned above. A combination of a multi-agent system, a deformable model and an edge detector is proposed in [23]. The model includes the region and the edge agents constrained by the gray levels, statistical models of the brain structures and general knowledge about MRI brain scans.
On Image Segmentation Methods Applied to Glioblastoma: State of Art and New Trends
2016, IRBMCitation Excerpt :Mainly, edge-based approaches applied in the context of GBM segmentation rely on deformable contours (see Fig. 4). Basically, deformable contour [51–55] are a two or three-dimensional shape (curve or surface) iteratively deformed under the influence of internal and external forces. In such a manner that boundaries fit the target volume.
A computational framework to quantify tissue microstructural integrity using conventional MRI macrostructural volumetry
2011, Computers in Biology and MedicineAccurate and robust extraction of brain regions using a deformable model based on radial basis functions
2009, Journal of Neuroscience MethodsCitation Excerpt :Therefore, they are more robust to both image artifacts and boundary discontinuities and can achieve subvoxel accuracy (Xu et al., 2000). Hybrid approaches integrate the methods of different types with the anticipation to draw on the specific strengths at the expense of more computational cost (Atkins and Mackiewich, 1998; Aboutanos et al., 1999; Germond et al., 2000; Baillard et al., 2001; Rex et al., 2004; Mikheev et al., 2008). Ségonne et al. (2004) applied the watershed algorithm (Hahn and Peitgen, 2000) to generate an initial brain volume and incorporated the prior information of the brain shape into a deformable model to refine the extraction results.
Agentification of Markov model-based segmentation: Application to magnetic resonance brain scans
2009, Artificial Intelligence in Medicine