Spectral clustering applied for dynamic contrast-enhanced MR analysis of time–intensity curves

Tartare, Guillaume; Hamad, Denis; Azahaf, Mustapha; Puech, Philippe; Betrouni, Nacim

doi:10.1016/j.compmedimag.2014.07.005

Cited by 8 publications

(4 citation statements)

References 29 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are aware, that the images do not exhibit signal distributions similar to those observed on real MR images, however they could be used to perform a validation of the multisteps process of pharmacokinetics maps estimation [15]. As future evolution, the signals could be merged and combined with a real MR simulator.…”

Section: Discussion -Conclusionmentioning

confidence: 98%

ProstateAtlas SimDCE: A simulation tool for dynamic contrast enhanced imaging of prostate

Betrouni

Tartare

2015

IRBM

View full text Add to dashboard Cite

T1-weighted Dynamic Contrast Enhanced (DCE) MR imaging is emerging as a method with the potential of predicting pharmacodynamic response of biomarkers for cancer. It is becoming an important tool for the detection, staging, and monitoring of highly vascularized tumors. Pixel-wise model-based methods are used for analysis purposes through the computation of quantitative parameters maps. These methods are multi-steps algorithms and their technical and clinical implementations remain difficult. In this study, we describe a dedicated simulation tool to create dynamic images of prostate. Ground truths of the pharmacokinetics parameters maps are well known allowing an effective platform for the validation.

show abstract

Section: Discussion -Conclusionmentioning

confidence: 98%

ProstateAtlas SimDCE: A simulation tool for dynamic contrast enhanced imaging of prostate

Betrouni

Tartare

2015

IRBM

View full text Add to dashboard Cite

show abstract

“…TC representation in a DCE image sequence may be either parametric [Agner et al, 2013;Tartare et al, 2014;Irving et al, 2016a;Shou et al, 2016] or nonparametric [Li et al, 2012]. The latter is known to provide a representation adaptive to the unknown TC regularity.…”

Section: Prior Approaches To Dce Image Sequence Segmentationmentioning

confidence: 99%

“…Zelnik-Manor and Perona [2004] addressed these two requirements through a self-tuning local scaling and a maximization of a cost function that depends on the number of clusters which is allowed to vary in a predefined set of values. Such approach has been used to segment DCE image sequences of prostate tumor [Tartare et al, 2014], with the number of clusters ranging between 1 and 5 only. In the context of tumor segmentation, Irving et al [2016a] used a supervised step to discriminate between tissues/behaviors.…”

Section: Prior Approaches To Dce Image Sequence Segmentationmentioning

confidence: 99%

“…Region (object)-based segmentation has been investigated for detecting lesions [Chen et al, 2006;Irving et al, 2016a;Tartare et al, 2014], or for retrieving internal structure of organs using prior knowledge on the number of tissues in the organ of interest [Lecoeur et al, 2009;Li et al, 2012]. All these works use clustering-based image segmentation methods generally together with a supervised refinement step requiring a training dataset.…”

Section: Prior Approaches To Dce Image Sequence Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical segmentation using equivalence test (HiSET): Application to DCE image sequences

Liu

Cuénod

Thomassin‐Naggara

et al. 2019

Medical Image Analysis

View full text Add to dashboard Cite

Dynamical contrast enhanced (DCE) imaging allows non invasive access to tissue micro-vascularization. It appears as a promising tool to build imaging biomarkers for diagnostic, prognosis or anti-angiogenesis treatment monitoring of cancer.However, quantitative analysis of DCE image sequences suffers from low signal to noise ratio (SNR). SNR may be improved by averaging functional information in a large region of interest when it is functionally homogeneous.We propose a novel method for automatic segmentation of DCE image sequences into functionally homogeneous regions, called DCE-HiSET. Using an observation model which depends on one parameter a and is justified a posteriori, DCE-HiSET is a hierarchical clustering algorithm. It uses the p-value of a multiple equivalence test as dissimilarity measure and consists of two steps. The first exploits the spatial neighborhood structure to reduce complexity and takes advantage of the regularity of anatomical features, while the second recovers (spatially) disconnected homogeneous structures at a larger (global) scale.Given a minimal expected homogeneity discrepancy for the multiple equivalence test, both steps stop automatically by controlling the Type I error. This provides an adaptive choice for the number of clusters. Assuming that the DCE image sequence is functionally piecewise constant with signals on each piece sufficiently separated, we prove that DCE-HiSET will retrieve the exact partition with high probability as soon as the number of images in the sequence is large enough. The minimal expected homogeneity discrepancy appears as the tuning parameter controlling the size of the segmentation. DCE-HiSET has been implemented in C++ for 2D and 3D image sequences with competitive speed.

show abstract

Functional Connectivity Analysis of Cognitive Reappraisal Using Sparse Spectral Clustering Method

Zou

Jiang

et al. 2016

Advances in Cognitive Neurodynamics (V)

View full text Add to dashboard Cite

Spectral clustering applied for dynamic contrast-enhanced MR analysis of time–intensity curves

Cited by 8 publications

References 29 publications

ProstateAtlas SimDCE: A simulation tool for dynamic contrast enhanced imaging of prostate

ProstateAtlas SimDCE: A simulation tool for dynamic contrast enhanced imaging of prostate

Hierarchical segmentation using equivalence test (HiSET): Application to DCE image sequences

Functional Connectivity Analysis of Cognitive Reappraisal Using Sparse Spectral Clustering Method

Contact Info

Product

Resources

About