Subcortical structure segmentation using probabilistic atlas priors

Gouttard, Sylvain; Styner, Martin; Joshi, Sarang; Smith, Rachel G.; Hazlett, Heather C.; Gerig, Guido

doi:10.1117/12.708626

Cited by 55 publications

(51 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The atlas is first warped to the image and then used to label the structures. Two kind of atlases are mainly used: either atlases of labels that directly provide segmentation map after warping [34], or probabilistic atlases that provide a priori knowledge to the segmentation models [20], [35]. In a recent approach, Pohl et al [19] propose to interleave atlas registration and structure segmentation, gradually improving both procedures.…”

Section: B Subcortical Structure Segmentation As a Separate Taskmentioning

confidence: 99%

“…On the low resolution and low contrast images from the IBSR database (see Figure 11), LOCUS-T and the FAST algorithm of FSL are less efficient, which is probably due to an over regularization of the MRFs on such images. For structure segmentation we bypass the use of an atlas to provide an a priori knowledge [20], [35]. These methods are expected to segment a higher number of structures but atlas registration algorithms are extremely time consuming.…”

Section: Evaluation Of the Cooperative Tissue And Structure Segmenmentioning

confidence: 99%

See 1 more Smart Citation

Distributed Local MRF Models for Tissue and Structure Brain Segmentation

Scherrer

Forbes

Garbay

et al. 2009

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

To cite this version:Benoît Scherrer, Florence Forbes, Catherine Garbay, Michel Dojat. Distributed local MRF models for tissue and structure brain segmentation. IEEE Abstract-Accurate tissue and structure segmentation of Magnetic Resonance (MR) brain scans is critical in several applications. In most approaches this task is handled through two sequential steps. We propose to carry out cooperatively both tissue and subcortical structure segmentation by distributing a set of local and cooperative Markov Random Field (MRF) models. Tissue segmentation is performed by partitioning the volume into subvolumes where local MRFs are estimated in cooperation with their neighbors to ensure consistency. Local estimation fits precisely to the local intensity distribution and thus handles nonuniformity of intensity without any bias field modelization. Similarly, subcortical structure segmentation is performed via local MRF models that integrate localization constraints provided by a priori fuzzy description of brain anatomy. Subcortical structure segmentation is not reduced to a subsequent processing step but joined with tissue segmentation: the two procedures cooperate to gradually and conjointly improve model accuracy.We propose a framework to implement this distributed modeling integrating cooperation, coordination, and local model checking in an efficient way. Its evaluation was performed using both phantoms and real 3T brain scans, showing good results and in particular robustness to nonuniformity and noise with a low computational cost. This original combination of local MRF models, including anatomical knowledge, appears as a powerful and promising approach for MR brain scan segmentation.

show abstract

Section: B Subcortical Structure Segmentation As a Separate Taskmentioning

confidence: 99%

Section: Evaluation Of the Cooperative Tissue And Structure Segmenmentioning

confidence: 99%

Distributed Local MRF Models for Tissue and Structure Brain Segmentation

Scherrer

Forbes

Garbay

et al. 2009

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…As can be seen from Table 1 in terms of the Dice coefficient our method achieves better results (80%,73%,75%,82%) for the segmentation of the caudate nuclei, hippocampi, globi pallidi, and putamina on the same IBSR 18 data set than the methods of Akselrod-Ballin et al [7] (80%, 69%, 74%, 79%) and Gouttard et al [12] (76%,67%,71%,78%) except for the caudate nuclei in comparison to the method of Akselrod-Ballin et al [7], where we reach a comparable accuracy. It also reaches a higher score for the caudate nuclei and putamina on IBSR 18 than the method of Bazin and Pham [14] (78%,81%), which does not address segmentation of the hippocampi and globi pallidi.…”

Section: Resultsmentioning

confidence: 73%

“…The first one is a subset of the "Designed Database of MR Brain Images of Healthy Volunteers" 1 [11] (DDHV) containing 20 scans. The associated ground-truth annotations were manually recovered from automatically generated segmentations [12] of the structures of interest. The second collection of 18 MRI scans was provided by the Center of Morphometric Analysis at the Massachusetts General Hospital and is publicly available on the Internet Brain Segmentation Repository 2 (IBSR 18).…”

Section: Materials and Experimental Settingmentioning

confidence: 99%

Fast and Robust 3-D MRI Brain Structure Segmentation

Wels

Zheng

Carneiro

et al. 2009

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

View full text Add to dashboard Cite

Abstract. We present a novel method for the automatic detection and segmentation of (sub-)cortical gray matter structures in 3-D magnetic resonance images of the human brain. Essentially, the method is a topdown segmentation approach based on the recently introduced concept of Marginal Space Learning (MSL). We show that MSL naturally decomposes the parameter space of anatomy shapes along decreasing levels of geometrical abstraction into subspaces of increasing dimensionality by exploiting parameter invariance. At each level of abstraction, i.e., in each subspace, we build strong discriminative models from annotated training data, and use these models to narrow the range of possible solutions until a final shape can be inferred. Contextual information is introduced into the system by representing candidate shape parameters with high-dimensional vectors of 3-D generalized Haar features and steerable features derived from the observed volume intensities. Our system allows us to detect and segment 8 (sub-)cortical gray matter structures in T1-weighted 3-D MR brain scans from a variety of different scanners in on average 13.9 sec., which is faster than most of the approaches in the literature. In order to ensure comparability of the achieved results and to validate robustness, we evaluate our method on two publicly available gold standard databases consisting of several T1-weighted 3-D brain MR scans from different scanners and sites. The proposed method achieves an accuracy better than most state-of-the-art approaches using standardized distance and overlap metrics.

show abstract

“…One common feature of the above-mentioned methods [3,4,5,7,8,9,10,11,12,13,14] is the need of sufficient training samples. The training process usually requires a considerable number of segmented images with the known ground truths.…”

Section: Introductionmentioning

confidence: 99%

Markov Dependence Tree-Based Segmentation of Deep Brain Structures

Chung

2008

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2008

View full text Add to dashboard Cite

Abstract. We propose a new framework for multi-object segmentation of deep brain structures, which have significant shape variations and relatively small sizes in medical brain images. In the images, the structure boundaries may be blurry or even missing, and the surrounding background is a clutter and full of irrelevant edges. We suggest a templatebased framework, which fuses the information of edge features, region statistics and inter-structure constraints to detect and locate all the targeted brain structures such that manual initialization is unnecessary. The multi-object template is organized in the form of a hierarchical Markov dependence tree. It makes the matching of multiple objects efficient. Our approach needs only one example as training data and alleviates the demand of a large training set. The obtained segmentation results on real data are encouraging and the proposed method enjoys several important advantages over existing methods.

show abstract

Subcortical structure segmentation using probabilistic atlas priors

Cited by 55 publications

References 19 publications

Distributed Local MRF Models for Tissue and Structure Brain Segmentation

Distributed Local MRF Models for Tissue and Structure Brain Segmentation

Fast and Robust 3-D MRI Brain Structure Segmentation

Markov Dependence Tree-Based Segmentation of Deep Brain Structures

Contact Info

Product

Resources

About