Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 75
Filtrar
1.
Magn Reson Med ; 87(2): 896-903, 2022 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-34554602

RESUMO

PURPOSE: The number of glomeruli is different in men and women, as they also present different prevalence and progression of chronic kidney disease. A recent study has demonstrated a potential difference in renal metabolism between sexes, and a potential explanation could be the differences in glomeruli number. This study investigates the potential correlation between glomerular number and pyruvate metabolism in healthy kidneys. METHODS: This study is an experimental study with rats (N = 12). We used cationized-ferritin MRI to visualize and count glomeruli and hyperpolarized [1-13 C]pyruvate to map the metabolism. Dynamic contrast-enhanced MRI was used to analyze kidney hemodynamics using gadolinium tracer. RESULTS: Data showed no or subtle correlation between the number of glomeruli and the pyruvate metabolism. Minor differences were observed in the number of glomeruli (female = 24,509 vs. male = 26 350; p = .16), renal plasma flow (female = 606.6 vs. male= 455.7 ml/min/100 g; p = .18), and volume of distribution (female = 87.44 vs. male = 76.61 ml/100 ml; p = .54) between sexes. Mean transit time was significantly prolonged in males compared with females (female = 8.868 s vs. male = 10.63 s; p = .04). CONCLUSION: No strong statistically significant correlation between the number of glomeruli and the pyruvate metabolism was found in healthy rat kidneys.

2.
Diagnostics (Basel) ; 11(11)2021 Nov 17.
Artigo em Inglês | MEDLINE | ID: mdl-34829478

RESUMO

Abdominal aortic aneurysms (AAA) may remain clinically silent until they enlarge and patients present with a potentially lethal rupture. This necessitates early detection and elective treatment. The goal of this study was to develop an easy-to-train algorithm which is capable of automated AAA screening in CT scans and can be applied to an intra-hospital environment. Three deep convolutional neural networks (ResNet, VGG-16 and AlexNet) were adapted for 3D classification and applied to a dataset consisting of 187 heterogenous CT scans. The 3D ResNet outperformed both other networks. Across the five folds of the first training dataset it achieved an accuracy of 0.856 and an area under the curve (AUC) of 0.926. Subsequently, the algorithms performance was verified on a second data set containing 106 scans, where it ran fully automated and resulted in an accuracy of 0.953 and an AUC of 0.971. A layer-wise relevance propagation (LRP) made the decision process interpretable and showed that the network correctly focused on the aortic lumen. In conclusion, the deep learning-based screening proved to be robust and showed high performance even on a heterogeneous multi-center data set. Integration into hospital workflow and its effect on aneurysm management would be an exciting topic of future research.

3.
Magn Reson Med ; 2021 Oct 15.
Artigo em Inglês | MEDLINE | ID: mdl-34652819

RESUMO

PURPOSE: To design and manufacture a pelvis phantom for magnetic resonance (MR)-guided prostate interventions, such as MRGB (MR-guided biopsy) or brachytherapy seed placement. METHODS: The phantom was designed to mimic the human pelvis incorporating bones, bladder, prostate with four lesions, urethra, arteries, veins, and six lymph nodes embedded in ballistic gelatin. A hollow rectum enables transrectal access to the prostate. To demonstrate the feasibility of the phantom for minimal invasive MRI-guided interventions, a targeted inbore MRGB was performed. The needle probe was rectally inserted and guided using an MRI-compatible remote controlled manipulator (RCM). RESULTS: The presented pelvis phantom has realistic imaging properties for MR imaging (MRI), computed tomography (CT) and ultrasound (US). In the targeted inbore MRGB, a prostate lesion was successfully hit with an accuracy of 3.5 mm. The experiment demonstrates that the limited size of the rectum represents a realistic impairment for needle placements. CONCLUSION: The phantom provides a valuable platform for evaluating the performance of MRGB systems. Interventionalists can use the phantom to learn how to deal with challenging situations, without risking harm to patients.

4.
Vasa ; 50(6): 468-474, 2021 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-34269078

RESUMO

Background: In peripheral arterial disease (PAD) the femoropopliteal (FP) artery is the most frequently recanalized lower limb artery. Stent-based interventions change the biomechanical properties of FP arteries. However, no clinical tool for functional imaging is established for quantitative measurements in vivo. Four-dimensional-flow magnetic resonance imaging enables a detailed evaluation of the hemodynamics of the central and - more challenging - the peripheral arteries. The present study aimed to determine the feasibility of assessing pulse wave velocities (PWV) as a marker of vessel stiffness in PAD patients with multiple spot stents and to compare the values with age-matched subjects and young-adult healthy subjects. Patients and methods: Contrast-free 4D-flow MRI was performed in seven PAD patients with focally stented FP arteries, five age-matched subjects after exclusion of PAD, and five young, healthy adults. PWV values were calculated from flow curves by using the foot-to-foot method. Results: Four-D-flow MRI sequences offering high spatial and temporal resolution enables quantification of flow velocity measurements and estimation of PWVs. Assessment of segmental PWV as a surrogate of vascular stiffness in focally stented femoral arteries is feasible. PWV values across all groups were 15.6±5.2 m/s, 13.3±4.1 m/s, and 9.9±2.2 m/s in PAD patients, senior-aged volunteers, and young-adult volunteers respectively. PWV values in PAD patients were similar with those in the senior-aged volunteers group (15.6±5.2 vs. 13.3 ±4.1 years, p=0.43). However, when compared to the young-adult volunteers, PAD patients had a statistically significantly higher mean local PWV (15.6±5.2 m/s vs. 9.9±2.2 m/s, p<0.05). Conclusions: Calculating segmental PWV in the femoral arteries is feasible in PAD patients with focally stented FP arteries. PWV values in PAD patients were similar to those in senior-aged volunteers, both of which were higher than in young-adult volunteers.


Assuntos
Análise de Onda de Pulso , Rigidez Vascular , Adulto , Idoso , Velocidade do Fluxo Sanguíneo , Artéria Femoral/diagnóstico por imagem , Humanos , Imageamento por Ressonância Magnética , Stents
5.
Radiologe ; 61(9): 829-838, 2021 Sep.
Artigo em Alemão | MEDLINE | ID: mdl-34251481

RESUMO

CLINICAL/METHODOLOGICAL ISSUE: Multiparametric magnetic resonance imaging (mpMRI) of the prostate plays a crucial role in the diagnosis and local staging of primary prostate cancer. STANDARD RADIOLOGICAL METHODS: Image-guided biopsy techniques such as MRI-ultrasound fusion not only allow guidance for targeted tissue sampling of index lesions for diagnostic confirmation, but also improve the detection of clinically significant prostate cancer. METHODOLOGICAL INNOVATIONS: Minimally invasive, focal therapies of localized prostate cancer complement the treatment spectrum, especially for low- and intermediate-risk patients. PERFORMANCE: In patients of low and intermediate risk, MR-guided, minimally invasive therapies could enable local tumor control, improved functional outcomes and possible subsequent therapy escalation. Further study results related to multimodal approaches and the application of artificial intelligence (AI) by machine and deep learning algorithms will help to leverage the full potential of focal therapies for prostate cancer in the upcoming era of precision medicine. ACHIEVEMENTS: Completion of ongoing randomized trials comparing each minimally invasive therapy approach with established whole-gland procedures is needed before minimally invasive therapies can be implemented into existing treatment guidelines. PRACTICAL RECOMMENDATIONS: This review article highlights minimally invasive therapies of prostate cancer and the key role of mpMRI for planning and conducting these therapies.


Assuntos
Inteligência Artificial , Neoplasias da Próstata , Humanos , Biópsia Guiada por Imagem , Imageamento por Ressonância Magnética , Masculino , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/cirurgia
6.
BMC Med Imaging ; 21(1): 107, 2021 07 08.
Artigo em Inglês | MEDLINE | ID: mdl-34238246

RESUMO

BACKGROUND: To develop a regression neural network for the reconstruction of lesion probability maps on Magnetic Resonance Fingerprinting using echo-planar imaging (MRF-EPI) in addition to [Formula: see text], [Formula: see text], NAWM, and GM- probability maps. METHODS: We performed MRF-EPI measurements in 42 patients with multiple sclerosis and 6 healthy volunteers along two sites. A U-net was trained to reconstruct the denoised and distortion corrected [Formula: see text] and [Formula: see text] maps, and to additionally generate NAWM-, GM-, and WM lesion probability maps. RESULTS: WM lesions were predicted with a dice coefficient of [Formula: see text] and a lesion detection rate of [Formula: see text] for a threshold of 33%. The network jointly enabled accurate [Formula: see text] and [Formula: see text] times with relative deviations of 5.2% and 5.1% and average dice coefficients of [Formula: see text] and [Formula: see text] for NAWM and GM after binarizing with a threshold of 80%. CONCLUSION: DL is a promising tool for the prediction of lesion probability maps in a fraction of time. These might be of clinical interest for the WM lesion analysis in MS patients.

7.
Int J Comput Assist Radiol Surg ; 16(8): 1277-1285, 2021 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-33934313

RESUMO

PURPOSE: Sparsity of annotated data is a major limitation in medical image processing tasks such as registration. Registered multimodal image data are essential for the diagnosis of medical conditions and the success of interventional medical procedures. To overcome the shortage of data, we present a method that allows the generation of annotated multimodal 4D datasets. METHODS: We use a CycleGAN network architecture to generate multimodal synthetic data from the 4D extended cardiac-torso (XCAT) phantom and real patient data. Organ masks are provided by the XCAT phantom; therefore, the generated dataset can serve as ground truth for image segmentation and registration. Realistic simulation of respiration and heartbeat is possible within the XCAT framework. To underline the usability as a registration ground truth, a proof of principle registration is performed. RESULTS: Compared to real patient data, the synthetic data showed good agreement regarding the image voxel intensity distribution and the noise characteristics. The generated T1-weighted magnetic resonance imaging, computed tomography (CT), and cone beam CT images are inherently co-registered. Thus, the synthetic dataset allowed us to optimize registration parameters of a multimodal non-rigid registration, utilizing liver organ masks for evaluation. CONCLUSION: Our proposed framework provides not only annotated but also multimodal synthetic data which can serve as a ground truth for various tasks in medical imaging processing. We demonstrated the applicability of synthetic data for the development of multimodal medical image registration algorithms.


Assuntos
Algoritmos , Simulação por Computador , Tomografia Computadorizada de Feixe Cônico/métodos , Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Imagens de Fantasmas , Humanos
8.
J Vis Exp ; (171)2021 05 13.
Artigo em Inglês | MEDLINE | ID: mdl-34057435

RESUMO

The purpose of this study is to introduce and evaluate a modified surgical approach to induce acute ischemia in mice that can be implemented in most animal laboratories. Contrary to the conventional approach for double ligation of the femoral artery (DLFA), a smaller incision on the right inguinal region was made to expose the proximal femoral artery (FA) to perform DLFA. Then, using a 7-0 suture, the incision was dragged to the knee region to expose the distal FA. Magnetic resonance imaging (MRI) on bilateral hind limbs was used to detect FA occlusion after the surgery. At 0, 1, 3, 5, and 7 days after the surgery, functional recovery of the hind limbs was visually assessed and graded using the Tarlov scale. Histologic evaluation was performed after euthanizing the animals 7 days after DLFA. The procedures were successfully performed on the right leg in ten ApoE-/- mice, and no mice died during subsequent observation. The incision sizes in all 10 mice were less than 5 mm (4.2 ± 0.63 mm). MRI results showed that FA blood flow in the ischemic side was clearly blocked. The Tarlov scale results demonstrated that hind limb function significantly decreased after the procedure and slowly recovered over the following 7 days. Histologic evaluation showed a significant inflammatory response on the ischemic side and reduced microvascular density in the ischemic hind limb. In conclusion, this study introduces a modified technique using a miniature incision to perform hind limb ischemia (HLI) using DLFA.


Assuntos
Apolipoproteínas E , Isquemia , Músculo Esquelético , Animais , Apolipoproteínas E/genética , Modelos Animais de Doenças , Membro Posterior , Isquemia/cirurgia , Camundongos , Modelos Anatômicos
9.
Diagnostics (Basel) ; 11(4)2021 Mar 30.
Artigo em Inglês | MEDLINE | ID: mdl-33808402

RESUMO

We examined the impact of chronic prostatitis on the diagnostic performance of multiparametric magnetic resonance imaging (mpMRI). In this retrospective study, 63 men underwent 3T mpMRI followed by MRI/ultrasound fusion biopsy to exclude/confirm clinically significant prostate cancer (csPCa). A total of 93 lesions were included for evaluation. Images were assessed by two radiologists. Prostatitis was graded visually on T2-weighted and contrast-enhanced sequences. The correlation of prostatitis features with the assigned Prostate Imaging Reporting and Data System (PI-RADS) and the presence of csPCa were assessed, and the clinical and functional imaging parameters for differentiating between prostatitis and significant tumors were examined. Histopathological analysis was used as the reference standard. The rate of PI-RADS 3 scores tended to be higher in the presence of radiologically severe prostatitis compared with no/discrete prostatitis (n = 52 vs. n = 9; p = 0.225). In severe prostatitis, csPCa was determined in only 7.7% (4/52) of PI-RADS 3 lesions. In severe chronic prostatitis, a binary prostatitis suffix (e.g., PI-RADS 3 i+ versus i-) within the radiological report may help assess the limitations of mpMRI interpretability because of severe prostatitis and avoid unnecessary biopsies. Mean apparent diffusion coefficient (ADCmean) was the best marker (cutoff 0.93 × 10-3 mm2/s) to differentiate between csPCa/non csPCa in severe prostatitis.

10.
Magn Reson Med ; 86(1): 471-486, 2021 07.
Artigo em Inglês | MEDLINE | ID: mdl-33547656

RESUMO

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.


Assuntos
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
11.
Methods Mol Biol ; 2216: 205-227, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33476002

RESUMO

Dynamic contrast-enhanced (DCE) MRI monitors the transit of contrast agents, typically gadolinium chelates, through the intrarenal regions, the renal cortex, the medulla, and the collecting system. In this way, DCE-MRI reveals the renal uptake and excretion of the contrast agent. An optimal DCE-MRI acquisition protocol involves finding a good compromise between whole-kidney coverage (i.e., 3D imaging), spatial and temporal resolution, and contrast resolution. By analyzing the enhancement of the renal tissues as a function of time, one can determine indirect measures of clinically important single-kidney parameters as the renal blood flow, glomerular filtration rate, and intrarenal blood volumes. Gadolinium-containing contrast agents may be nephrotoxic in patients suffering from severe renal dysfunction, but otherwise DCE-MRI is clearly useful for diagnosis of renal functions and for assessing treatment response and posttransplant rejection.Here we introduce the concept of renal DCE-MRI, describe the existing methods, and provide an overview of preclinical DCE-MRI applications to illustrate the utility of this technique to measure renal perfusion and glomerular filtration rate in animal models.This publication is based upon work from the COST Action PARENCHIMA, a community-driven network funded by the European Cooperation in Science and Technology (COST) program of the European Union, which aims to improve the reproducibility and standardization of renal MRI biomarkers. This introduction is complemented by two separate publications describing the experimental procedure and data analysis.


Assuntos
Biomarcadores/análise , Meios de Contraste/química , Imagem de Difusão por Ressonância Magnética/métodos , Taxa de Filtração Glomerular , Aumento da Imagem/métodos , Processamento de Imagem Assistida por Computador/métodos , Rim/fisiologia , Animais , Humanos , Monitorização Fisiológica/métodos , Perfusão , Circulação Renal , Software
12.
Methods Mol Biol ; 2216: 257-266, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33476005

RESUMO

The handling of sodium by the renal system is a key indicator of renal function. Alterations in the corticomedullary distribution of sodium are considered important indicators of pathology in renal diseases. The derangement of sodium handling can be noninvasively imaged using sodium magnetic resonance imaging (23Na MRI), with data analysis allowing for the assessment of the corticomedullary sodium gradient. Here we introduce sodium imaging, describe the existing methods, and give an overview of preclinical sodium imaging applications to illustrate the utility and applicability of this technique for measuring renal sodium handling.This chapter is based upon work from the COST Action PARENCHIMA, a community-driven network funded by the European Cooperation in Science and Technology (COST) program of the European Union, which aims to improve the reproducibility and standardization of renal MRI biomarkers. This introduction chapter is complemented by two separate chapters describing the experimental procedure and data analysis.


Assuntos
Biomarcadores/análise , Processamento de Imagem Assistida por Computador/métodos , Rim/fisiologia , Imageamento por Ressonância Magnética/métodos , Monitorização Fisiológica/métodos , Isótopos de Sódio/análise , Animais , Humanos , Software
13.
Methods Mol Biol ; 2216: 429-441, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33476015

RESUMO

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can provide a noninvasive way for assessing renal functional information following the administration of a small molecular weight gadolinium-based contrast agent. This method may be useful for investigating renal perfusion and glomerular filtration rates of rodents in vivo under various experimental (patho)physiological conditions. Here we describe a step-by-step protocol for DCE-MRI studies in small animals providing practical notes on acquisition parameters, sequences, T1 mapping approaches and procedures.This chapters is based upon work from the COST Action PARENCHIMA, a community-driven network funded by the European Cooperation in Science and Technology (COST) program of the European Union, which aims to improve the reproducibility and standardization of renal MRI biomarkers. This experimental protocol chapter is complemented by two separate chapters describing the basic concept and data analysis.


Assuntos
Meios de Contraste , Aumento da Imagem/métodos , Processamento de Imagem Assistida por Computador/métodos , Rim/fisiologia , Imageamento por Ressonância Magnética/métodos , Monitorização Fisiológica/métodos , Algoritmos , Animais , Taxa de Filtração Glomerular , Camundongos , Camundongos Endogâmicos BALB C , Camundongos Endogâmicos C57BL , Camundongos Nus , Perfusão , Software
14.
Methods Mol Biol ; 2216: 473-480, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33476018

RESUMO

Sodium handling is a key physiological hallmark of renal function. Alterations are generally considered a pathophysiologic event associated with kidney injury, with disturbances in the corticomedullary sodium gradient being indicative of a number of conditions. This experimental protocol review describes the individual steps needed to perform 23Na MRI; allowing accurate monitoring of the renal sodium distribution in a step-by-step experimental protocol for rodents.This chapter is based upon work from the PARENCHIMA COST Action, a community-driven network funded by the European Cooperation in Science and Technology (COST) program of the European Union, which aims to improve the reproducibility and standardization of renal MRI biomarkers. This experimental protocol chapter is complemented by two separate chapters describing the basic concept and data analysis.


Assuntos
Processamento de Imagem Assistida por Computador/métodos , Rim/fisiologia , Imageamento por Ressonância Magnética/métodos , Monitorização Fisiológica/métodos , Isótopos de Sódio/análise , Animais , Imagens de Fantasmas , Ratos , Ratos Endogâmicos Lew , Ratos Sprague-Dawley , Ratos Wistar , Software
15.
Methods Mol Biol ; 2216: 637-653, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33476028

RESUMO

Here we present an analysis protocol for dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) data of the kidneys. It covers comprehensive steps to facilitate signal to contrast agent concentration mapping via T1 mapping and the calculation of renal perfusion and filtration parametric maps using model-free approaches, model free analysis using deconvolution, the Toft's model and a Bayesian approach.This chapter is based upon work from the COST Action PARENCHIMA, a community-driven network funded by the European Cooperation in Science and Technology (COST) program of the European Union, which aims to improve the reproducibility and standardization of renal MRI biomarkers. This analysis protocol chapter is complemented by two separate chapters describing the basic concept and experimental procedure.


Assuntos
Algoritmos , Meios de Contraste/química , Taxa de Filtração Glomerular , Processamento de Imagem Assistida por Computador/métodos , Rim/fisiologia , Imageamento por Ressonância Magnética/métodos , Circulação Renal , Animais , Aumento da Imagem , Rim/irrigação sanguínea , Monitorização Fisiológica , Perfusão , Software
16.
Methods Mol Biol ; 2216: 689-696, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33476031

RESUMO

The signal acquired in sodium (23Na) MR imaging is proportional to the concentration of sodium in a voxel, and it is possible to convert between the two using external calibration phantoms. Postprocessing, and subsequent analysis, of sodium renal images is a simple task that can be performed with readily available software. Here we describe the process of conversion between sodium signal and concentration, estimation of the corticomedullary sodium gradient and the procedure used for quadrupolar relaxation analysis.This chapter is based upon work from the COST Action PARENCHIMA, a community-driven network funded by the European Cooperation in Science and Technology (COST) program of the European Union, which aims to improve the reproducibility and standardization of renal MRI biomarkers. This analysis protocol chapter is complemented by two separate chapters describing the basic concept and experimental procedure.


Assuntos
Processamento de Imagem Assistida por Computador/métodos , Rim/fisiologia , Imageamento por Ressonância Magnética/métodos , Monitorização Fisiológica/métodos , Imagens de Fantasmas , Isótopos de Sódio/análise , Animais , Meios de Contraste/química , Imageamento Tridimensional , Ratos , Software
17.
NMR Biomed ; 34(4): e4474, 2021 04.
Artigo em Inglês | MEDLINE | ID: mdl-33480128

RESUMO

Quantitative 23 Na magnetic resonance imaging (MRI) provides tissue sodium concentration (TSC), which is connected to cell viability and vitality. Long acquisition times are one of the most challenging aspects for its clinical establishment. K-space undersampling is an approach for acquisition time reduction, but generates noise and artifacts. The use of convolutional neural networks (CNNs) is increasing in medical imaging and they are a useful tool for MRI postprocessing. The aim of this study is 23 Na MRI acquisition time reduction by k-space undersampling. CNNs were applied to reduce the resulting noise and artifacts. A retrospective analysis from a prospective study was conducted including image datasets from 46 patients (aged 72 ± 13 years; 25 women, 21 men) with ischemic stroke; the 23 Na MRI acquisition time was 10 min. The reconstructions were performed with full dataset (FI) and with a simulated dataset an image that was acquired in 2.5 min (RI). Eight different CNNs with either U-Net-based or ResNet-based architectures were implemented with RI as input and FI as label, using batch normalization and the number of filters as varying parameters. Training was performed with 9500 samples and testing included 400 samples. CNN outputs were evaluated based on signal-to-noise ratio (SNR) and structural similarity (SSIM). After quantification, TSC error was calculated. The image quality was subjectively rated by three neuroradiologists. Statistical significance was evaluated by Student's t-test. The average SNR was 21.72 ± 2.75 (FI) and 10.16 ± 0.96 (RI). U-Nets increased the SNR of RI to 43.99 and therefore performed better than ResNet. SSIM of RI to FI was improved by three CNNs to 0.91 ± 0.03. CNNs reduced TSC error by up to 15%. The subjective rating of CNN-generated images showed significantly better results than the subjective image rating of RI. The acquisition time of 23 Na MRI can be reduced by 75% due to postprocessing with a CNN on highly undersampled data.

18.
IEEE Trans Biomed Eng ; 68(5): 1518-1526, 2021 05.
Artigo em Inglês | MEDLINE | ID: mdl-33275574

RESUMO

OBJECTIVE: Three-dimensional (3D) blood vessel structure information is important for diagnosis and treatment in various clinical scenarios. We present a fully automatic method for the extraction and differentiation of the arterial and venous vessel trees from abdominal contrast enhanced computed tomography (CE-CT) volumes using convolutional neural networks (CNNs). METHODS: We used a novel ratio-based sampling method to train 2D and 3D versions of the U-Net, the V-Net and the DeepVesselNet. Networks were trained with a combination of the Dice and cross entropy loss. Performance was evaluated on 20 IRCAD subjects. Best performing networks were combined into an ensemble. We investigated seven different weighting schemes. Trained networks were additionally applied to 26 BTCV cases to validate the generalizability. RESULTS: Based on our experiments, the optimal configuration is an equally weighted ensemble of 2D and 3D U- and V-Nets. Our method achieved Dice similarity coefficients of 0.758 ± 0.050 (veins) and 0.838 ± 0.074 (arteries) on the IRCAD data set. Application to the BTCV data set showed a high transfer ability. CONCLUSION: Abdominal vascular structures can be segmented more accurately using ensembles than individual CNNs. 2D and 3D networks have complementary strengths and weaknesses. Our ensemble of 2D and 3D U-Nets and V-Nets in combination with ratio-based sampling achieves a high agreement with manual annotations for both artery and vein segmentation. Our results surpass other state-of-the-art methods. SIGNIFICANCE: Our segmentation pipeline can provide valuable information for the planning of living donor organ transplantations.


Assuntos
Redes Neurais de Computação , Tomografia Computadorizada por Raios X , Abdome/diagnóstico por imagem , Artérias , Humanos , Processamento de Imagem Assistida por Computador
19.
Acta Radiol ; 62(5): 695-704, 2021 May.
Artigo em Inglês | MEDLINE | ID: mdl-32600068

RESUMO

BACKGROUND: The combination of motion-insensitive, high-temporal, and spatial resolution imaging with evaluation of quantitative perfusion has the potential to increase the diagnostic capabilities of magnetic resonance imaging (MRI) in the female pelvis. PURPOSE: To compare a free-breathing compressed-sensing VIBE (fbVIBE) with flexible temporal resolution (range = 4.6-13.8 s) with breath-hold VIBE (bhVIBE) and to evaluate the potential value of quantifying uterine perfusion. MATERIAL AND METHODS: A total of 70 datasets from 60 patients (bhVIBE: n = 30; fbVIBE: n = 40) were evaluated by two radiologists. Only temporally resolved reconstruction (fbVIBE) was performed on 30 of the fbVIBE datasets. For a subset (n = 10) of the fbVIBE acquisitions, a time- and motion-resolved reconstruction (mrVIBE) was evaluated. Image quality (IQ), artifacts, diagnostic confidence (DC), and delineation of uterine structures (DoS) were graded on Likert scales (IQ/DC/DoS: 1 (non-diagnostic) to 5 (perfect); artifacts: 1 (no artifacts) to 5 (severe artifacts)). A Tofts model was applied for perfusion analysis. Ktrans was obtained in the myometrium (Mm), junctional zone (Jz), and cervix (Cx). RESULTS: The median IQ/DoS/DC scores of fbVIBE (4/5/5 κ >0.7-0.9) and bhVIBE (4/4/4; κ = 0.5-0.7; P > 0.05) were high, but Artifacts were graded low (fbVIBE/bhVIBE: 2/2; κ = 0.6/0.5; P > 0.05). Artifacts were only slightly improved by the additional motion-resolved reconstruction (fbVIBE/mrVIBE: 2/1.5; P = 0.08); fbVIBE was preferred in most cases (7/10). Significant differences of Ktrans values were found between Cx, Jz, and Mm (0.12/0.21/0.19; P < 0.05). CONCLUSION: The fbVIBE sequence allows functional and morphological assessment of the uterus at comparable IQ to bhVIBE.


Assuntos
Imageamento por Ressonância Magnética/métodos , Doenças Uterinas/diagnóstico por imagem , Doenças Uterinas/fisiopatologia , Útero/diagnóstico por imagem , Útero/fisiologia , Adulto , Artefatos , Feminino , Humanos , Processamento de Imagem Assistida por Computador , Pessoa de Meia-Idade , Respiração
20.
J Magn Reson Imaging ; 2020 Nov 02.
Artigo em Inglês | MEDLINE | ID: mdl-33140551

RESUMO

BACKGROUND: Phase-contrast (PC) MRI is a feasible and valid noninvasive technique to measure renal artery blood flow, showing potential to support diagnosis and monitoring of renal diseases. However, the variability in measured renal blood flow values across studies is large, most likely due to differences in PC-MRI acquisition and processing. Standardized acquisition and processing protocols are therefore needed to minimize this variability and maximize the potential of renal PC-MRI as a clinically useful tool. PURPOSE: To build technical recommendations for the acquisition, processing, and analysis of renal 2D PC-MRI data in human subjects to promote standardization of renal blood flow measurements and facilitate the comparability of results across scanners and in multicenter clinical studies. STUDY TYPE: Systematic consensus process using a modified Delphi method. POPULATION: Not applicable. SEQUENCE FIELD/STRENGTH: Renal fast gradient echo-based 2D PC-MRI. ASSESSMENT: An international panel of 27 experts from Europe, the USA, Australia, and Japan with 6 (interquartile range 4-10) years of experience in 2D PC-MRI formulated consensus statements on renal 2D PC-MRI in two rounds of surveys. Starting from a recently published systematic review article, literature-based and data-driven statements regarding patient preparation, hardware, acquisition protocol, analysis steps, and data reporting were formulated. STATISTICAL TESTS: Consensus was defined as ≥75% unanimity in response, and a clear preference was defined as 60-74% agreement among the experts. RESULTS: Among 60 statements, 57 (95%) achieved consensus after the second-round survey, while the remaining three showed a clear preference. Consensus statements resulted in specific recommendations for subject preparation, 2D renal PC-MRI data acquisition, processing, and reporting. DATA CONCLUSION: These recommendations might promote a widespread adoption of renal PC-MRI, and may help foster the set-up of multicenter studies aimed at defining reference values and building larger and more definitive evidence, and will facilitate clinical translation of PC-MRI. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY STAGE: 1.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...