• Corpus ID: 3458549

Unmixing dynamic PET images for voxel-based kinetic component analysis

  title={Unmixing dynamic PET images for voxel-based kinetic component analysis},
  author={Yanna Cruz Cavalcanti and Thomas Oberlin and Nicolas Dobigeon and Simon Stute and Maria Ribeiro and Clovis Tauber},
To analyze dynamic positron emission tomography (PET) images, various generic multivariate data analysis techniques have been considered in the literature, such as clustering, principal component analysis (PCA), independent component analysis (ICA) and non-negative matrix factorization (NMF). Nevertheless, these conventional approaches generally fail to recover a reliable, understandable and interpretable description of the data. In this paper, we propose an alternative analysis paradigm based… 
1 Citations

Démélange d'images TEP dynamiques

Cet article introduit une methode de demelange pour l’analyse d’images de tomographie par emission de positons (TEP) dynamiques du cerveau. Plus precisement, on souhaite estimer conjointement les



Non-Local Means Denoising of Dynamic PET Images

The experimental data analysis revealed that the denoising technique leads to clear improvement in contrast-to-noise ratio in Patlak parametric images generated from denoised preclinical and clinical dynamic images, indicating its ability to preserve image contrast and high intensity details while lowering the background noise variance.

Clustering-Initiated Factor Analysis Application for Tissue Classification in Dynamic Brain Positron Emission Tomography

Clustering-initiated factor analysis can be an accurate and convenient tool for measuring specific binding tissue concentration and for analyzing tracer kinetics from dynamic images for a variety of PET tracers.

Spatio-temporal diffusion of dynamic PET images

A new post-reconstruction filter to increase the signal-to-noise ratio in dynamic PET imaging consisting in a spatio-temporal robust diffusion of the 4D image based on the time activity curve (TAC) in each voxel based on a robust statistical analysis of the distances between TACs is described.

Segmentation of dynamic PET images with kinetic spectral clustering

A new method based on spectral clustering that does not require any prior information on the shape of clusters in the space in which they are identified is proposed and appears as a promising pre-processing tool before parametric map calculation or ROI-based quantification tasks.

A cluster analysis approach for the characterization of dynamic PET data

NMF on Positron Emission Tomography

This work proposes another method to estimate time-activity curves (TAC) extracted directly from dynamic positron emission tomography (PET) scans by non-negative matrix factorization (NMF).

Dynamic PET Denoising with HYPR Processing

The modified HYPR algorithm (the HYPR method constraining the backprojections to local regions of interest [HYPR-LR]) is introduced for the processing of dynamic PET studies and it is demonstrated that significant improvements in SNR can be realized in the PET time series, particularly for voxel-based analysis, without sacrificing spatial resolution.

Clustering dynamic PET images on the Gaussian distributed sinogram domain

  • M. Kamasak
  • Computer Science
    2007 15th European Signal Processing Conference
  • 2007

Segmentation of Rodent Whole-Body Dynamic PET Images: An Unsupervised Method Based on Voxel Dynamics

The segmentation method proved efficient on whole-body numerical rat phantom simulations, including 3-14 organs, together with physiological movements (heart beating, breathing, and bladder filling) and was resistant to spillover and physiological movements, while other methods failed to obtain a correct segmentation.

Non-negative matrix factorization of dynamic images in nuclear medicine

Recently suggested non-negative matrix factorization (NMF) seems to overcome fundamental limitations of factor analysis at least In theoretical aspect. NMF cost function uses Poisson statistics as a