Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 4 de 4
Mais filtros

Base de dados
Intervalo de ano de publicação
Magn Reson Med ; 86(1): 471-486, 2021 07.
Artigo em Inglês | MEDLINE | ID: mdl-33547656


PURPOSE: To develop an accelerated postprocessing pipeline for reproducible and efficient assessment of white matter lesions using quantitative magnetic resonance fingerprinting (MRF) and deep learning. METHODS: MRF using echo-planar imaging (EPI) scans with varying repetition and echo times were acquired for whole brain quantification of T 1 and T 2 ∗ in 50 subjects with multiple sclerosis (MS) and 10 healthy volunteers along 2 centers. MRF T 1 and T 2 ∗ parametric maps were distortion corrected and denoised. A CNN was trained to reconstruct the T 1 and T 2 ∗ parametric maps, and the WM and GM probability maps. RESULTS: Deep learning-based postprocessing reduced reconstruction and image processing times from hours to a few seconds while maintaining high accuracy, reliability, and precision. Mean absolute error performed the best for T 1 (deviations 5.6%) and the logarithmic hyperbolic cosinus loss the best for T 2 ∗ (deviations 6.0%). CONCLUSIONS: MRF is a fast and robust tool for quantitative T 1 and T 2 ∗ mapping. Its long reconstruction and several postprocessing steps can be facilitated and accelerated using deep learning.

Aprendizado Profundo , Substância Branca , Encéfalo/diagnóstico por imagem , Humanos , Processamento de Imagem Assistida por Computador , Imageamento por Ressonância Magnética , Espectroscopia de Ressonância Magnética , Imagens de Fantasmas , Reprodutibilidade dos Testes , Substância Branca/diagnóstico por imagem
Neuroimage ; 219: 117014, 2020 10 01.
Artigo em Inglês | MEDLINE | ID: mdl-32534123


Demyelination is the key pathological process in multiple sclerosis (MS). The extent of demyelination can be quantified with magnetic resonance imaging by assessing the myelin water fraction (MWF). However, long computation times and high noise sensitivity hinder the translation of MWF imaging to clinical practice. In this work, we introduce a more efficient and noise robust method to determine the MWF using a joint sparsity constraint and a pre-computed B1+-T2 dictionary. A single component analysis with this dictionary is used in an initial step to obtain a B1+ map. The T2 distribution is then determined from a reduced dictionary corresponding to the estimated B1+ map using a combination of a non-negativity and a joint sparsity constraint. The non-negativity constraint ensures that a feasible solution with non-negative contribution of each T2 component is obtained. The joint sparsity constraint restricts the T2 distribution to a small set of T2 relaxation times shared between all voxels and reduces the noise sensitivity. The applied Sparsity Promoting Iterative Joint NNLS (SPIJN) algorithm can be implemented efficiently, reducing the computation time by a factor of 50 compared to the commonly used regularized non-negative least squares algorithm. The proposed method was validated in simulations and in 8 healthy subjects with a 3D multi-echo gradient- and spin echo scan at 3 â€‹T. In simulations, the absolute error in the MWF decreased from 0.031 to 0.013 compared to the regularized NNLS algorithm for SNR â€‹= â€‹250. The in vivo results were consistent with values reported in literature and improved MWF-quantification was obtained especially in the frontal white matter. The maximum standard deviation in mean MWF in different regions of interest between subjects was smaller for the proposed method (0.0193) compared to the regularized NNLS algorithm (0.0266). In conclusion, the proposed method for MWF estimation is less computationally expensive and less susceptible to noise compared to state of the art methods. These improvements might be an important step towards clinical translation of MWF measurements.

Encéfalo/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Bainha de Mielina , Algoritmos , Humanos , Processamento de Imagem Assistida por Computador/métodos , Modelos Neurológicos , Água
Magn Reson Med ; 83(2): 521-534, 2020 02.
Artigo em Inglês | MEDLINE | ID: mdl-31418918


PURPOSE: To develop an efficient algorithm for multi-component analysis of magnetic resonance fingerprinting (MRF) data without making a priori assumptions about the exact number of tissues or their relaxation properties. METHODS: Different tissues or components within a voxel are potentially separable in MRF because of their distinct signal evolutions. The observed signal evolution in each voxel can be described as a linear combination of the signals for each component with a non-negative weight. An assumption that only a small number of components are present in the measured field of view is usually imposed in the interpretation of multi-component data. In this work, a joint sparsity constraint is introduced to utilize this additional prior knowledge in the multi-component analysis of MRF data. A new algorithm combining joint sparsity and non-negativity constraints is proposed and compared to state-of-the-art multi-component MRF approaches in simulations and brain MRF scans of 11 healthy volunteers. RESULTS: Simulations and in vivo measurements show reduced noise in the estimated tissue fraction maps compared to previously proposed methods. Applying the proposed algorithm to the brain data resulted in 4 or 5 components, which could be attributed to different brain structures, consistent with previous multi-component MRF publications. CONCLUSIONS: The proposed algorithm is faster than previously proposed methods for multi-component MRF and the simulations suggest improved accuracy and precision of the estimated weights. The results are easier to interpret compared to voxel-wise methods, which combined with the improved speed is an important step toward clinical evaluation of multi-component MRF.

Encéfalo/diagnóstico por imagem , Imageamento por Ressonância Magnética , Algoritmos , Teorema de Bayes , Simulação por Computador , Voluntários Saudáveis , Humanos , Processamento de Imagem Assistida por Computador , Análise dos Mínimos Quadrados , Modelos Teóricos , Neuroimagem , Imagens de Fantasmas
PLoS One ; 7(9): e44973, 2012.
Artigo em Inglês | MEDLINE | ID: mdl-23028713


PURPOSE: The ciliary body (CB) of the human eye consists of the non-pigmented (NPE) and pigmented (PE) neuro-epithelia. We investigated the gene expression of NPE and PE, to shed light on the molecular mechanisms underlying the most important functions of the CB. We also developed molecular signatures for the NPE and PE and studied possible new clues for glaucoma. METHODS: We isolated NPE and PE cells from seven healthy human donor eyes using laser dissection microscopy. Next, we performed RNA isolation, amplification, labeling and hybridization against 44×k Agilent microarrays. For microarray conformations, we used a literature study, RT-PCRs, and immunohistochemical stainings. We analyzed the gene expression data with R and with the knowledge database Ingenuity. RESULTS: The gene expression profiles and functional annotations of the NPE and PE were highly similar. We found that the most important functionalities of the NPE and PE were related to developmental processes, neural nature of the tissue, endocrine and metabolic signaling, and immunological functions. In total 1576 genes differed statistically significantly between NPE and PE. From these genes, at least 3 were cell-specific for the NPE and 143 for the PE. Finally, we observed high expression in the (N)PE of 35 genes previously implicated in molecular mechanisms related to glaucoma. CONCLUSION: Our gene expression analysis suggested that the NPE and PE of the CB were quite similar. Nonetheless, cell-type specific differences were found. The molecular machineries of the human NPE and PE are involved in a range of neuro-endocrinological, developmental and immunological functions, and perhaps glaucoma.

Corpo Ciliar/citologia , Perfilação da Expressão Gênica , Epitélio Pigmentado Ocular/citologia , Epitélio Pigmentado Ocular/metabolismo , Glaucoma/genética , Humanos , Análise de Sequência com Séries de Oligonucleotídeos