Longitudinal change detection: Inference on the diffusion tensor along white matter pathways

Grigis, Antoine; Noblet, Vincent; Blanc, F.; Heitz, Fabrice; Seze, J. de; Kremer, Stéphane; Armspach, Jean‐Paul

doi:10.1016/j.media.2013.01.004

Cited by 6 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, compared to [19], [17], [6], the proposed method allows to i) analyze multiple DTI features taking into account more than 2 time-points ii) delineate regions, fibers and detect time-points affected by longitudinal changes.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Constrained Tensor Decomposition for Longitudinal Analysis of Diffusion Imaging Data

Stamile

Cotton

Sappey–Marinier

et al. 2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Analysis of complex data is still a challenge in medical image analysis. Due to the heterogeneous information that can be extracted from magnetic resonance imaging (MRI) it can be difficult to fuse such data in a proper way. One interesting case is given by the analysis of diffusion imaging (DI) data. DI techniques give an important variety of information about the status of microstructure in the brain. This is interesting information to use especially in longitudinal setting where the temporal evolution of the pathology is an important added value.In this paper, we propose a new tensor-based framework capable to detect longitudinal changes appearing in DI data in multiple sclerosis (MS) patients. We focus our attention to the analysis of longitudinal changes occurring along different white matter (WM) fiber-bundles. Our main goal is to detect which subset of fibers (within a bundle) and which sections of these fibers contain "pathological" longitudinal changes. The framework consists of three main parts: i) preprocessing of longitudinal diffusion acquisitions and WM fiber-bundles extraction, ii) data tensorization and rank selection, iii) application of a parallelized constrained tensor factorization algorithm to detect longitudinal "pathological" changes.The proposed method was applied on simulated longitudinal variations and on real MS data. High level of accuracy and precision were obtained in the detection of small longitudinal changes along the WM fiber-bundles.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Recently, different efforts were made in order to perform such complex analysis. In [6], the authors showed a method to analyze longitudinal changes in WM. Main limitation of this method is related to its capability to perform a longitudinal analysis restricted to two time-points.…”

Section: Introductionmentioning

confidence: 99%

Constrained Tensor Decomposition for Longitudinal Analysis of Diffusion Imaging Data

Stamile

Cotton

Sappey–Marinier

et al. 2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…DTI is a functional MR imaging technique for studying the diffusion characteristics of water molecules, and it has been widely applied to the quantitative evaluation of white matter changes in various brain disorders [ 19 , 20 , 21 ], white matter pathways [ 22 ], cortical spinal tract [ 23 ], and cognitive [ 24 ] and spinal disorders [ 25 , 26 ]. Previous DTI studies [ 11 ] demonstrated abnormal changes in the normal-appearing white matter of the brain in NMO patients.…”

Section: Discussionmentioning

confidence: 99%

Assessment of Optic Nerve Impairment in Patients with Neuromyelitis Optica by MR Diffusion Tensor Imaging

et al. 2015

View full text Add to dashboard Cite

BackgroundDiffusion tensor imaging (DTI) has been used for the evaluation of the white matter integrity. In this study, we evaluated optic nerve impairment in patients with neuromyelitis optica (NMO) using DTI.Methodology/Principal FindingsOptic nerve DTI were performed on 28 NMO patients and 38 normal controls. Fractional anisotropy (FA) values were measured in the anterior, middle, and posterior parts of the intraorbital optic nerve segment. For the posterior intraorbital optic nerve, FA values of BI (0.20±0.07), MI (0.24±0.16), and NA (0.25±0.14) decreased significantly compared with that of NC (0.43±0.07) (P<0.05), and ROC analysis demonstrated that the area under the curve (AUC) measurements for BI vs. NC, MI vs. NC, NA vs. NC, and NMO (including BI, MI, and NA) vs. NC were 0.99, 0.93, 0.88, and 0.96, respectively. The corresponding diagnostic sensitivities of ROC analysis were 100%, 80%, 80%, and 91%; and the specificities were 93%, 97%, 91%, and 93%.Conclusions/SignificanceDecreased FA value in the intraorbital optic nerve, especially in the posterior part of the nerve, was demonstrated as a characteristic MR feature for NMO-related optic nerve impairment.

show abstract

“…However, this task usually performed by an expert is time consuming and operator dependent. In order to overcome such limitations, fully automated algorithms have been implemented [ 25 , 26 ]. These methods enable systematic, large-scale analysis of fiber bundles in large subject populations.…”

Section: Introductionmentioning

confidence: 99%

A Sensitive and Automatic White Matter Fiber Tracts Model for Longitudinal Analysis of Diffusion Tensor Images in Multiple Sclerosis

et al. 2016

View full text Add to dashboard Cite

Diffusion tensor imaging (DTI) is a sensitive tool for the assessment of microstructural alterations in brain white matter (WM). We propose a new processing technique to detect, local and global longitudinal changes of diffusivity metrics, in homologous regions along WM fiber-bundles. To this end, a reliable and automatic processing pipeline was developed in three steps: 1) co-registration and diffusion metrics computation, 2) tractography, bundle extraction and processing, and 3) longitudinal fiber-bundle analysis. The last step was based on an original Gaussian mixture model providing a fine analysis of fiber-bundle cross-sections, and allowing a sensitive detection of longitudinal changes along fibers. This method was tested on simulated and clinical data. High levels of F-Measure were obtained on simulated data. Experiments on cortico-spinal tract and inferior fronto-occipital fasciculi of five patients with Multiple Sclerosis (MS) included in a weekly follow-up protocol highlighted the greater sensitivity of this fiber scale approach to detect small longitudinal alterations.

show abstract

Longitudinal change detection: Inference on the diffusion tensor along white matter pathways

Cited by 6 publications

References 32 publications

Constrained Tensor Decomposition for Longitudinal Analysis of Diffusion Imaging Data

Constrained Tensor Decomposition for Longitudinal Analysis of Diffusion Imaging Data

Assessment of Optic Nerve Impairment in Patients with Neuromyelitis Optica by MR Diffusion Tensor Imaging

A Sensitive and Automatic White Matter Fiber Tracts Model for Longitudinal Analysis of Diffusion Tensor Images in Multiple Sclerosis

Contact Info

Product

Resources

About