Fast and robust symmetry detection for brain images based on parallel scale‐invariant feature transform matching and voting
01 Dec 2013-International Journal of Imaging Systems and Technology (John Wiley & Sons, Ltd)-Vol. 23, Iss: 4, pp 314-326
TL;DR: This article presents a fast and robust symmetry detection method for automatically extracting symmetry axis (fissure line) from a brain image based on a set of scale‐invariant feature transform (SIFT) features, where the symmetry axis is determined by parallel matching and voting of distinctive features within the brain image.
Abstract: Symmetry analysis for brain images has been considered as a promising technique for automatically extracting the pathological brain slices in conventional scanning. In this article, we present a fast and robust symmetry detection method for automatically extracting symmetry axis (fissure line) from a brain image. Unlike the existing brain symmetry detection methods which mainly rely on the intensity or edges to determine the symmetry axis, our proposed method is based on a set of scale-invariant feature transform (SIFT) features, where the symmetry axis is determined by parallel matching and voting of distinctive features within the brain image. By clustering and indexing the extracted SIFT features using a GPU KD-tree, we can match multiple pairs of features in parallel based on a novel symmetric similarity metric, which combines the relative scales, orientations, and flipped descriptors to measure the magnitude of symmetry between each pair of features. Finally, the dominant symmetry axis presented in the brain image is determined using a parallel voting algorithm by accumulating the pair-wise symmetry score in a Hough space. Our method was evaluated on both synthetic and in vivo datasets, including both normal and pathological cases. Comparisons with state-of-the-art methods were also conducted to validate the proposed method. Experimental results demonstrated that our method achieves a real-time performance and with a higher accuracy than previous methods, yielding an average polar angle error within 0.69° and an average radius error within 0.71 mm. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 314–326, 2013
Citations
More filters
18 Apr 2017
TL;DR: In this paper, the authors analyzed the existing computational techniques used to find brain symmetric/asymmetric analysis in different neuroimaging techniques such as the magnetic resonance (MR), computed tomography (CT), positron emission tomography(PET), single-photon emission computed (SPECT), which are utilized for detecting various brain related disorders.
Abstract: The brain is the most complex organ in the human body and it is divided into two hemispheres—left and right. The left hemisphere is responsible for control of the right side of our body, whereas the right hemisphere is responsible for control of the left side of our body. Brain image segmentation from different neuroimaging modalities is one of the important parts of clinical diagnostic tools. Neuroimaging based digital imagery generally contain noise, inhomogeneity, aliasing artifacts, and orientational deviations. Therefore, accurate segmentation of brain images is a very difficult task. However, the development of accurate segmentation of brain images is very important and crucial for a correct diagnosis of any brain related diseases. One of the fundamental segmentation tasks is to identify and segment inter-hemispheric fissure/mid-sagittal planes, which separate the two hemispheres of the brain. Moreover, the symmetric/asymmetric analyses of left and right hemispheres of brain structures are important for radiologists to analyze diseases such as Alzheimer’s, autism, schizophrenia, lesions and epilepsy. Therefore, in this paper, we have analyzed the existing computational techniques used to find brain symmetric/asymmetric analysis in different neuroimaging techniques such as the magnetic resonance (MR), computed tomography (CT), positron emission tomography (PET), single-photon emission computed tomography (SPECT), which are utilized for detecting various brain related disorders.
19 citations
Cites background from "Fast and robust symmetry detection ..."
...similarity, 3D edge registration and parameterized surface matching to determine the fissure plane (see also [40])....
[...]
TL;DR: Results from both qualitative and quantitative analyses showed that the method can reach or approach the accuracy of manual extracted, but the stable level of this method is significantly higher than the manual method and this method can shorten the operate time to reduce the doctor’s workload.
Abstract: To prepare for the oral and maxillofacial surgery for the facial symmetry of patients, midsagittal plane of skull in brain computed tomography (CT) images is calculated with points manually chosen from skull by doctor. But the extracted midsagittal plane of the skull is different by different doctor. Even the extracted midsagittal plane of the same patient is also different by the same doctor in different times. The manually extracting operation usually takes a long time to increase the doctor’s workload. Aimed at this problem, a semi-automatic extracting method for midsagittal plane of skull is proposed in this paper. First, the brain tissue is extracted by region growing method and the oriented bounding box (OBB) of the brain tissue is built. Second, the middle symmetry plane of the OBB of brain tissue is extracted as the initial midsagittal plane, which is updated by the mathematical translation and rotation method. Finally, the symmetrical characteristic of the brain tissue based on the updated symmetry plane is calculated by the mutual information method. This procedure is executed iteratively until the symmetrical characteristic of the brain tissue based on the new symmetry plane is no more different from the previous result. The final extracted symmetry plane is the midsagittal plane of skull in brain CT images of the patient. The midsagittal plane which is extracted manually by doctor is used to compare and evaluate the accuracy of this semi-automatic extracting symmetry plane method. The experimental results from both qualitative and quantitative analyses showed that the method can reach or approach the accuracy of manual extracted, but the stable level of this method is significantly higher than the manual method and this method can shorten the operate time to reduce the doctor’s workload.
14 citations
Cites methods from "Fast and robust symmetry detection ..."
...Wu [32], [33] presented a fast and robust MSP extraction method based on 3D scale invariant feature transform (SIFT), which mainly rely on the gray similarity, 3D edge registration or parameterized surfacematching to determine the fissure plane based on distinctive 3D SIFT features....
[...]
TL;DR: This article proposes an automatic symmetry detection method for brain MR images in 2-D slices based on a 2-channel convolutional neural network (CNN) that achieves excellent performance for symmetry detection and compares with the state-of-the-art methods.
Abstract: Symmetry detection is a method to extract the ideal mid-sagittal plane (MSP) from brain magnetic resonance (MR) images, which can significantly improve the diagnostic accuracy of brain diseases. In this article, we propose an automatic symmetry detection method for brain MR images in 2-D slices based on a 2-channel convolutional neural network (CNN). Different from the existing detection methods that mainly rely on the local image features (gradient, edge, etc.) to determine the MSP, we use a CNN-based model to implement the brain symmetry detection, which does not require any local feature detections and feature matchings. By training to learn a wide variety of benchmarks in the brain images, we can further use a 2-channel CNN to evaluate the similarity between the pairs of brain patches, which are randomly extracted from the whole brain slice based on a Poisson sampling. Finally, a scoring and ranking scheme is used to identify the optimal symmetry axis for each input brain MR slice. Our method was evaluated in 2166 artificial synthesized brain images and 3064 collected in vivo MR images, which included both healthy and pathological cases. The experimental results display that our method achieves excellent performance for symmetry detection. Comparisons with the state-of-the-art methods also demonstrate the effectiveness and advantages for our approach in achieving higher accuracy than the previous competitors.
8 citations
Cites background or methods from "Fast and robust symmetry detection ..."
...[23] cannot deal well the data with high blur....
[...]
...[23] extracted the MSP by maximizing global symmetry which was fitted by detecting the...
[...]
TL;DR: In this article, the structural symmetric nature of the pelvic bone is explored and is used to provide interventional image augmentation for treatment of unilateral fractures in patients with traumatic injuries, based on the incorporation of attributes and characteristics that satisfy the properties of intrinsic and extrinsic symmetry and are robust to outliers.
2 citations
Posted Content•
TL;DR: The structurally symmetric nature of the pelvic bone is explored and is used to provide interventional image augmentation for treatment of unilateral fractures in patients with traumatic injuries and on the validity of the novel concepts and the accuracy of the proposed method.
Abstract: We present a novel methodology to detect imperfect bilateral symmetry in CT of human anatomy. In this paper, the structurally symmetric nature of the pelvic bone is explored and is used to provide interventional image augmentation for treatment of unilateral fractures in patients with traumatic injuries. The mathematical basis of our solution is on the incorporation of attributes and characteristics that satisfy the properties of intrinsic and extrinsic symmetry and are robust to outliers. In the first step, feature points that satisfy intrinsic symmetry are automatically detected in the Mobius space defined on the CT data. These features are then pruned via a two-stage RANSAC to attain correspondences that satisfy also the extrinsic symmetry. Then, a disparity function based on Tukey's biweight robust estimator is introduced and minimized to identify a symmetry plane parametrization that yields maximum contralateral similarity. Finally, a novel regularization term is introduced to enhance similarity between bone density histograms across the partial symmetry plane, relying on the important biological observation that, even if injured, the dislocated bone segments remain within the body. Our extensive evaluations on various cases of common fracture types demonstrate the validity of the novel concepts and the robustness and accuracy of the proposed method.
1 citations
References
More filters
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Abstract: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.
46,906 citations
TL;DR: It is proved the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density.
Abstract: A general non-parametric technique is proposed for the analysis of a complex multimodal feature space and to delineate arbitrarily shaped clusters in it. The basic computational module of the technique is an old pattern recognition procedure: the mean shift. For discrete data, we prove the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density. The relation of the mean shift procedure to the Nadaraya-Watson estimator from kernel regression and the robust M-estimators; of location is also established. Algorithms for two low-level vision tasks discontinuity-preserving smoothing and image segmentation - are described as applications. In these algorithms, the only user-set parameter is the resolution of the analysis, and either gray-level or color images are accepted as input. Extensive experimental results illustrate their excellent performance.
11,727 citations
"Fast and robust symmetry detection ..." refers methods in this paper
...We use adaptive mean-shift clustering (Comaniciu and Meer, 2002) to group Figure 3....
[...]
...We use adaptive mean-shift clustering (Comaniciu and Meer, 2002) to group 316 Vol. 23, 314–326 (2013) the detected SIFT feature points....
[...]
01 Dec 2008
TL;DR: This algorithm achieves real-time performance by exploiting the GPU's streaming architecture at all stages of kd-tree construction by developing a special strategy for large nodes at upper tree levels so as to further exploit the fine-grained parallelism of GPUs.
Abstract: We present an algorithm for constructing kd-trees on GPUs. This algorithm achieves real-time performance by exploiting the GPU's streaming architecture at all stages of kd-tree construction. Unlike previous parallel kd-tree algorithms, our method builds tree nodes completely in BFS (breadth-first search) order. We also develop a special strategy for large nodes at upper tree levels so as to further exploit the fine-grained parallelism of GPUs. For these nodes, we parallelize the computation over all geometric primitives instead of nodes at each level. Finally, in order to maintain kd-tree quality, we introduce novel schemes for fast evaluation of node split costs.As far as we know, ours is the first real-time kd-tree algorithm on the GPU. The kd-trees built by our algorithm are of comparable quality as those constructed by off-line CPU algorithms. In terms of speed, our algorithm is significantly faster than well-optimized single-core CPU algorithms and competitive with multi-core CPU algorithms. Our algorithm provides a general way for handling dynamic scenes on the GPU. We demonstrate the potential of our algorithm in applications involving dynamic scenes, including GPU ray tracing, interactive photon mapping, and point cloud modeling.
490 citations
TL;DR: An attention operator based on the intuitive notion of symmetry, which generalized many of the existing methods of detecting regions of interest is presented, a low-level operator that can be applied successfully without a priori knowledge of the world.
Abstract: Active vision systems, and especially foveated vision systems, depend on efficient attentional mechanisms. We propose that machine visual attention should consist of both high-level, context-dependent components, and low-level, context free components. As a basis for the context-free component, we present an attention operator based on the intuitive notion of symmetry, which generalized many of the existing methods of detecting regions of interest. It is a low-level operator that can be applied successfully without a priori knowledge of the world. The resultingsymmetry edge map can be applied in various low, intermediate-and high- level tasks, such as extraction of interest points, grouping, and object recognition. In particular, we have implemented an algorithm that locates interest points in real time, and can be incorporated in active and purposive vision systems. The results agree with some psychophysical findings concerning symmetry as well as evidence concerning selection of fixation points. We demonstrate the performance of the transform on natural, cluttered images.
434 citations
"Fast and robust symmetry detection ..." refers methods in this paper
...According to the phase weighting method presented in Reisfeld et al. (1995), we denote the orientation symmetric similarity Uij as Figure 4....
[...]
...According to the phase weighting method presented in Reisfeld et al. (1995), we denote the orientation symmetric similarity Uij as Vol. 23, 314–326 (2013) 317 Uij5 12cos ð/i1/j22hijÞ 2 (2) where /i, /j, and hij are the angles counterclockwise between the horizontal line and ki, kj, or l,…...
[...]
TL;DR: A sizeable right-asymmetry increase reported here may be a consequence of early abnormal brain growth trajectories in children with high-functioning autism and with developmental language disorder, while higher-order association areas may be most vulnerable to connectivity abnormalities associated with white matter increases.
Abstract: We report a whole-brain MRI morphometric survey of asymmetry in children with high-functioning autism and with developmental language disorder (DLD). Subjects included 46 boys of normal intelligence aged 5.7-11.3 years (16 autistic, 15 DLD, 15 controls). Imaging analysis included grey-white segmentation and cortical parcellation. Asymmetry was assessed at a series of nested levels. We found that asymmetries were masked with larger units of analysis but progressively more apparent with smaller units, and that within the cerebral cortex the differences were greatest in higher-order association cortex. The larger units of analysis, including the cerebral hemispheres, the major grey and white matter structures and the cortical lobes, showed no asymmetries in autism or DLD and few asymmetries in controls. However, at the level of cortical parcellation units, autism and DLD showed more asymmetry than controls. They had a greater aggregate volume of significantly asymmetrical cortical parcellation units (leftward plus rightward), as well as a substantially larger aggregate volume of right-asymmetrical cortex in DLD and autism than in controls; this rightward bias was more pronounced in autism than in DLD. DLD, but not autism, showed a small but significant loss of leftward asymmetry compared with controls. Right : left ratios were reversed, autism and DLD having twice as much right- as left-asymmetrical cortex, while the reverse was found in the control sample. Asymmetry differences between groups were most significant in the higher-order association areas. Autism and DLD were much more similar to each other in patterns of asymmetry throughout the cerebral cortex than either was to controls; this similarity suggests systematic and related alterations rather than random neural systems alterations. We review these findings in relation to previously reported volumetric features in these two samples of brains, including increased total brain and white matter volumes and lack of increase in the size of the corpus callosum. Larger brain volume has previously been associated with increased lateralization. The sizeable right-asymmetry increase reported here may be a consequence of early abnormal brain growth trajectories in these disorders, while higher-order association areas may be most vulnerable to connectivity abnormalities associated with white matter increases.
408 citations