Arnaldo Mayer

Probabilistic space-time video modeling via piecewise GMM

In this paper, we describe a statistical video representation and modeling scheme. Video representation schemes are needed to segment a video stream into meaningful video-objects, useful for later indexing and retrieval applications. In the proposed methodology, unsupervised clustering via Gaussian mixture modeling extracts coherent space-time regions in feature space, and corresponding coherent segments (video-regions) in the video content. A key feature of the system is the analysis of video input as a single entity as opposed to a sequence of separate frames. Space and time are treated uniformly. The probabilistic space-time video representation scheme is extended to a piecewise GMM framework in which a succession of GMMs are extracted for the video sequence, instead of a single global model for the entire sequence. The piecewise GMM framework allows for the analysis of extended video sequences and the description of nonlinear, nonconvex motion patterns. The extracted space-time regions allow for the detection and recognition of video events. Results of segmenting video content into static versus dynamic video regions and video content editing are presented.

An Adaptive Mean-Shift Framework for MRI Brain Segmentation

An automated scheme for magnetic resonance imaging (MRI) brain segmentation is proposed. An adaptive mean-shift methodology is utilized in order to classify brain voxels into one of three main tissue types: gray matter, white matter, and cerebro-spinal fluid. The MRI image space is represented by a high-dimensional feature space that includes multimodal intensity features as well as spatial features. An adaptive mean-shift algorithm clusters the joint spatial-intensity feature space, thus extracting a representative set of high-density points within the feature space, otherwise known as modes. Tissue segmentation is obtained by a follow-up phase of intensity-based mode clustering into the three tissue categories. By its nonparametric nature, adaptive mean-shift can deal successfully with nonconvex clusters and produce convergence modes that are better candidates for intensity based classification than the initial voxels. The proposed method is validated on 3-D single and multimodal datasets, for both simulated and real MRI data. It is shown to perform well in comparison to other state-of-the-art methods without the use of a preregistered statistical brain atlas.

A Probabilistic Framework for Spatio-Temporal Video Representation & Indexing

In this work we describe a novel statistical video representation and modeling scheme. Video representation schemes are needed to enable segmenting a video stream into meaningful video-objects, useful for later indexing and retrieval applications. In the proposed methodology, unsupervised clustering via Guassian mixture modeling extracts coherent space-time regions in feature space, and corresponding coherent segments (video-regions) in the video content. A key feature of the system is the analysis of video input as a single entity as opposed to a sequence of separate frames. Space and time are treated uniformly. The extracted space-time regions allow for the detection and recognition of video events. Results of segmenting video content into static vs. dynamic video regions and video content editing are presented.

Co-registration of White Matter Tractographies by Adaptive-Mean-Shift and Gaussian Mixture Modeling

In this paper, we present a robust approach to the registration of white matter tractographies extracted from diffusion tensor-magnetic resonance imaging scans. The fibers are projected into a high dimensional feature space based on the sequence of their 3-D coordinates. Adaptive mean-shift clustering is applied to extract a compact set of representative fiber-modes (FM). Each FM is assigned to a multivariate Gaussian distribution according to its population thereby leading to a Gaussian mixture model (GMM) representation for the entire set of fibers. The registration between two fiber sets is treated as the alignment of two GMMs and is performed by maximizing their correlation ratio. A nine-parameters affine transform is recovered and eventually refined to a twelve-parameters affine transform using an innovative mean-shift based registration refinement scheme presented in this paper. The validation of the algorithm on synthetic intrasubject data demonstrates its robustness to interrupted and deviating fiber artifacts as well as outliers. Using real intrasubject data, a comparison is conducted to other intensity based and fiber-based registration algorithms, demonstrating competitive results. An option for tracking-in-time, on specific white matter fiber tracts, is also demonstrated on the real data.

A Supervised Framework for the Registration and Segmentation of White Matter Fiber Tracts

A supervised framework is presented for the automatic registration and segmentation of white matter (WM) tractographies extracted from brain DT-MRI. The framework relies on the direct registration between the fibers, without requiring any intensity-based registration as preprocessing. An affine transform is recovered together with a set of segmented fibers. A recently introduced probabilistic boosting tree classifier is used in a segmentation refinement step to improve the precision of the target tract segmentation. The proposed method compares favorably with a state-of-the-art intensity-based algorithm for affine registration of DTI tractographies. Segmentation results for 12 major WM tracts are demonstrated. Quantitative results are also provided for the segmentation of a particularly difficult case, the optic radiation tract. An average precision of 80% and recall of 55% were obtained for the optimal configuration of the presented method.

Segmentation of brain MRI by adaptive mean shift

A new automatic segmentation method for MRI images of the brain is presented, based on the adaptive mean-shift algorithm. Existing parametric methods utilize the intensity information for the segmentation task. When spatial information is introduced, parametric models may fail due to the non-convex nature of the brain tissue anatomy. A natural integration of intensity and spatial features is enabled in the non-parametric mean-shift formalism. The proposed method is validated on both simulated and real datasets

Adaptive mean-shift registration of white matter tractographies

In this paper we present a robust approach to the registration of white matter tractographies extracted from DT-MRI scans. The fibers are projected into a high dimensional feature space defined by the sequence of their 3D coordinates. Adaptive mean-shift (AMS) clustering is applied to extract a compact set of representative fiber-modes (FM). Each FM is assigned to a multivariate Gaussian distribution according to its population thereby leading to a Mixture of Gaussians (MoG) representation for the entire set of fibers. The registration between two fiber sets is treated as the alignment of two MoGs and is performed by maximizing their correlation ratio. A 9 parameter affine transform is recovered and eventually refined to a 12 parameters affine transform using an innovative mean-shift (MS) based registration refinement scheme presented in this paper. The validation of the algorithm on intra-subject data demonstrates its robustness against two main tractography artifacts: interrupted and deviating fiber tracts.

Efficient Low-Dose CT Denoising by Locally-Consistent Non-Local Means (LC-NLM)

The never-ending quest for lower radiation exposure is a major challenge to the image quality of advanced CT scans. Post-processing algorithms have been recently proposed to improve low-dose CT denoising after image reconstruction. In this work, a novel algorithm, termed the locally-consistent non-local means (LC-NLM), is proposed for this challenging task. By using a database of high-SNR CT patches to filter noisy pixels while locally enforcing spatial consistency, the proposed algorithm achieves both powerful denoising and preservation of fine image details. The LC-NLM is compared both quantitatively and qualitatively, for synthetic and real noise, to state-of-the-art published algorithms. The highest structural similarity index (SSIM) were achieved by LC-NLM in 8 out of 10 denoised chest CT volumes. Also, the visual appearance of the denoised images was clearly better for the proposed algorithm. The favorable comparison results, together with the computational efficiency of LC-NLM makes it a promising tool for low-dose CT denoising.

Bundles of interest based registration of White Matter tractographies

We present an efficient and robust method for direct registration between fiber bundles of interest and the complete White Matter (WM) tractography of the same or another brain. The method does not require any previous registration between the brains, such as DTI registration, and it can be used for both intra and inter-subject registration. The algorithm is inspired by the well known iterative closest point method. Here, 3D points are replaced by feature vectors representing WM fibers, and the neighborhood is determined by the efficient approximation framework of the locality sensitive hashing. Initial results demonstrate the successful application of the proposed registration method to the automatic extraction of anatomical WM structures in un- segmented brain tractographies.

A Neural Regression Framework for Low-Dose Coronary CT Angiography (CCTA) Denoising.

In the last decade, the technological progress of multi-slice CT imaging has turned CCTA into a valuable tool for coronary assessment in many low to medium risk patients. Nevertheless, CCTA protocols expose the patient to high radiation doses, imposed by image quality and multiple cardiac phase acquisition requirements. Widespread use of CCTA calls for significant reduction of radiation exposure while maintaining high image quality as required for coronary assessment. Denoising algorithms have been recently applied to low-dose CT scans after image reconstruction. In this work, a fast neural regression framework is proposed for the denoising of low-dose CCTA. For this purpose, regression networks are trained to synthesize high-SNR patches directly from low-SNR input patches. In contrast to published methods, the denoising network is trained on real noise directly learned from noisy CT data rather than assuming a known parametric noise model. The denoised value for each pixel is computed as a function of the synthesized patches overlapping the pixel. The proposed algorithm is compared to state-of-the-art published algorithms for synthetic and real noise. The feature similarity index (FSIM) achieved by the proposed method is superior in all the comparisons with other methods, for synthetic radiation dose reductions higher than 90%. The results are further supported qualitatively, by observing a significant improvement in subsequent coronary reconstruction performed by commercial software on denoised images. The fast and high quality denoising capability suggests the proposed algorithm as a promising method for low-dose CCTA denoising.