Gaussian mixture model for texture characterization with application to brain DTI images

Moraru, Luminița; Moldovanu, Simona; Dimitrievici, Lucian Traian; Dey, Nilanjan; Ashour, Amira S.; Shi, Fuqian; Fong, Simon; Khan, Salam; Biswas, Anjan

doi:10.1016/j.jare.2019.01.001

Cited by 31 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These two steps are alternated until a stopping criterion is met, when there is no further change in the assignment of the data points. The k-means algorithm aims at minimizing an objective function, which in this case is the squared error function between µ k and the data point in cluster c k [21,26,27]:…”

Section: Mathematical Approachesmentioning

confidence: 99%

“…For, SC ∈ [0.81-1.00], the object is very well-clustered; SC ∈ [0.51-0.80] the object is well-clustered; SC∈ [0.26-0.50] the object is poor-clustered, and SC ≤ 0.25 occurs with the artificial cluster [26]. Accordingly, when S(i) is close to 1, the 'within' dissimilarity a(i) is much smaller than the smallest 'between' dissimilarity b(i), and the object is 'well-clustered', while for S(i)-0, the a(i), and b(i) are approximately equal; thus, it is unclear as to which cluster the object i is assigned.…”

Section: Mathematical Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Brain Tissue Evaluation Based on Skeleton Shape and Similarity Analysis between Hemispheres

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background: The purpose of this article is to provide a new evaluation tool based on skeleton maps to assess the tumoral and non-tumoral regions of the 2D MRI in PD-weighted (proton density) and T2w (T2-weighted type) brain images. Methods: The proposed method investigated inter-hemisphere brain tissue similarity using a mask in the right hemisphere and its mirror reflection in the left one. At the hemisphere level and for each ROI (region of interest), a morphological skeleton algorithm was used to efficiently investigate the similarity between hemispheres. Two datasets with 88 T2w and PD images belonging to healthy patients and patients diagnosed with glioma were investigated: D1 contains the original raw images affected by Rician noise and D2 consists of the same images pre-processed for noise removal. Results: The investigation was based on structural similarity assessment by using the Structural Similarity Index (SSIM) and a modified Jaccard metrics. A novel S-Jaccard (Skeleton Jaccard) metric was proposed. Cluster accuracy was estimated based on the Silhouette method (SV). The Silhouette coefficient (SC) indicates the quality of the clustering process for the SSIM and S-Jaccard. To assess the overall classification accuracy an ROC curve implementation was carried out. Conclusions: Consistent results were obtained for healthy patients and for PD images of glioma. We demonstrated that the S-Jaccard metric based on skeletal similarity is an efficient tool for an inter-hemisphere brain similarity evaluation. The accuracy of the proposed skeletonization method was smaller for the original images affected by Rician noise (AUC = 0.883 (T2w) and 0.904 (PD)) but increased for denoised images (AUC = 0.951 (T2w) and 0.969 (PD)).

show abstract

Section: Mathematical Approachesmentioning

confidence: 99%

Section: Mathematical Approachesmentioning

confidence: 99%

Brain Tissue Evaluation Based on Skeleton Shape and Similarity Analysis between Hemispheres

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…GMM is a kind of model to describe mixture density distribution, which is widely used in pattern recognition, cluster analysis, and other fields [28]- [30]. It is not limited to a specific form of the probability density function, and any probability density distribution can be approximated by a linear combination of several Gaussian density functions.…”

Section: B Construction Of the Probability Density Function Distribumentioning

confidence: 99%

Utilizing Statistical Information for Interval Analysis: A Method for Analyzing the Interval Uncertainty of Line-of-Sight Measurement Error of Space-Borne Observation Platforms

Ding

Yang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Analyzing the space-borne observation platform's line-of-sight measurement error (SOPLME) is of great significance for the improvement of the space-borne optical tracking system. In this regard, we consider the space-borne observation platform (SOP) as a multi-body system and build both the target imaging model from the inertial space to the optical camera image plane and the line-of-sight measurement model. The relationship between the SOPLME and the satellite's orbit error, attitude error, platform angular vibration error, inner and outer frame rotation error, and position quantization error of target image point is deduced theoretically. However, since there are many error sources and the modeling process is highly nonlinear, the amplification of the output range caused by the ''wrapping effect'' may occur when using the interval calculation method to analyze the output range of the SOPLME. To solve this problem, we propose a novel method of interval analysis by using statistical information. This method combines the convenience of interval representation with the high accuracy of probability calculation, which can effectively avoid the overestimation problem caused by the inherent ''wrapping effect'' of the interval calculation method. Firstly, we describe the parameters of each error source with the interval constructed by upper and lower bounds. Secondly, the optimal Latin hypercube sampling (LHS) matrix of error source parameters is designed by the quasi-optimization method. Then we use the Gaussian mixture model (GMM) to approximate the distribution function of the SOPLME. Finally, the output range of the SOPLME is estimated by Taylor expansion. The simulation test verifies the reliability of the model and interval calculation method in this paper. The simulation example shows that the proposed method can get a more reliable error output interval with less sampling amount, which is suitable for analyzing the dynamic process of the output interval of the SOPLME. INDEX TERMS Space-borne observation platform, line-of-sight measurement error, interval analysis, Latin hypercube sampling, Gaussian mixture model.

show abstract

“…The classes follow a probability distribution (law), normal in the case of Gaussian mixture models (GMM). GMMs [74][75][76][77][78] require few parameters estimated by a simple likelihood function. These parameters can be estimated by adopting the EM algorithm in order to maximize the likelihood function of the log.…”

mentioning

confidence: 99%

“…Gaussian mixing model: GMM suggested by many neuroimaging researchers [76,[168][169][170][171][172] is easy to implement. Effective and robust due to its probabilistic basis.…”

mentioning

confidence: 99%

A Survey on Computer-Aided Diagnosis of Brain Disorders through MRI Based on Machine Learning and Data Mining Methodologies with an Emphasis on Alzheimer Disease Diagnosis and the Contribution of the Multimodal Fusion

2020

View full text Add to dashboard Cite

Computer-aided diagnostic (CAD) systems use machine learning methods that provide a synergistic effect between the neuroradiologist and the computer, enabling an efficient and rapid diagnosis of the patient’s condition. As part of the early diagnosis of Alzheimer’s disease (AD), which is a major public health problem, the CAD system provides a neuropsychological assessment that helps mitigate its effects. The use of data fusion techniques by CAD systems has proven to be useful, they allow for the merging of information relating to the brain and its tissues from MRI, with that of other types of modalities. This multimodal fusion refines the quality of brain images by reducing redundancy and randomness, which contributes to improving the clinical reliability of the diagnosis compared to the use of a single modality. The purpose of this article is first to determine the main steps of the CAD system for brain magnetic resonance imaging (MRI). Then to bring together some research work related to the diagnosis of brain disorders, emphasizing AD. Thus the most used methods in the stages of classification and brain regions segmentation are described, highlighting their advantages and disadvantages. Secondly, on the basis of the raised problem, we propose a solution within the framework of multimodal fusion. In this context, based on quantitative measurement parameters, a performance study of multimodal CAD systems is proposed by comparing their effectiveness with those exploiting a single MRI modality. In this case, advances in information fusion techniques in medical imagery are accentuated, highlighting their advantages and disadvantages. The contribution of multimodal fusion and the interest of hybrid models are finally addressed, as well as the main scientific assertions made, in the field of brain disease diagnosis.

show abstract

Gaussian mixture model for texture characterization with application to brain DTI images

Abstract: Graphical abstract

Cited by 31 publications

References 41 publications

Brain Tissue Evaluation Based on Skeleton Shape and Similarity Analysis between Hemispheres

Brain Tissue Evaluation Based on Skeleton Shape and Similarity Analysis between Hemispheres

Utilizing Statistical Information for Interval Analysis: A Method for Analyzing the Interval Uncertainty of Line-of-Sight Measurement Error of Space-Borne Observation Platforms

A Survey on Computer-Aided Diagnosis of Brain Disorders through MRI Based on Machine Learning and Data Mining Methodologies with an Emphasis on Alzheimer Disease Diagnosis and the Contribution of the Multimodal Fusion

Contact Info

Product

Resources

About