Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 30
Filtrar
1.
Invest Radiol ; 2023 Jan 18.
Artigo em Inglês | MEDLINE | ID: mdl-36728041

RESUMO

BACKGROUND: Detection of rotator cuff tears, a common cause of shoulder disability, can be time-consuming and subject to reader variability. Deep learning (DL) has the potential to increase radiologist accuracy and consistency. PURPOSE: The aim of this study was to develop a prototype DL model for detection and classification of rotator cuff tears on shoulder magnetic resonance imaging into no tear, partial-thickness tear, or full-thickness tear. MATERIALS AND METHODS: This Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included a total of 11,925 noncontrast shoulder magnetic resonance imaging scans from 2 institutions, with 11,405 for development and 520 dedicated for final testing. A DL ensemble algorithm was developed that used 4 series as input from each examination: fluid-sensitive sequences in 3 planes and a sagittal oblique T1-weighted sequence. Radiology reports served as ground truth for training with categories of no tear, partial tear, or full-thickness tear. A multireader study was conducted for the test set ground truth, which was determined by the majority vote of 3 readers per case. The ensemble comprised 4 parallel 3D ResNet50 convolutional neural network architectures trained via transfer learning and then adapted to the targeted domain. The final tear-type prediction was determined as the class with the highest probability, after averaging the class probabilities of the 4 individual models. RESULTS: The AUC overall for supraspinatus, infraspinatus, and subscapularis tendon tears was 0.93, 0.89, and 0.90, respectively. The model performed best for full-thickness supraspinatus, infraspinatus, and subscapularis tears with AUCs of 0.98, 0.99, and 0.95, respectively. Multisequence input demonstrated higher AUCs than single-sequence input for infraspinatus and subscapularis tendon tears, whereas coronal oblique fluid-sensitive and multisequence input showed similar AUCs for supraspinatus tendon tears. Model accuracy for tear types and overall accuracy were similar to that of the clinical readers. CONCLUSIONS: Deep learning diagnosis of rotator cuff tears is feasible with excellent diagnostic performance, particularly for full-thickness tears, with model accuracy similar to subspecialty-trained musculoskeletal radiologists.

3.
Radiat Oncol ; 17(1): 129, 2022 Jul 22.
Artigo em Inglês | MEDLINE | ID: mdl-35869525

RESUMO

BACKGROUND: We describe and evaluate a deep network algorithm which automatically contours organs at risk in the thorax and pelvis on computed tomography (CT) images for radiation treatment planning. METHODS: The algorithm identifies the region of interest (ROI) automatically by detecting anatomical landmarks around the specific organs using a deep reinforcement learning technique. The segmentation is restricted to this ROI and performed by a deep image-to-image network (DI2IN) based on a convolutional encoder-decoder architecture combined with multi-level feature concatenation. The algorithm is commercially available in the medical products "syngo.via RT Image Suite VB50" and "AI-Rad Companion Organs RT VA20" (Siemens Healthineers). For evaluation, thoracic CT images of 237 patients and pelvic CT images of 102 patients were manually contoured following the Radiation Therapy Oncology Group (RTOG) guidelines and compared to the DI2IN results using metrics for volume, overlap and distance, e.g., Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD95). The contours were also compared visually slice by slice. RESULTS: We observed high correlations between automatic and manual contours. The best results were obtained for the lungs (DSC 0.97, HD95 2.7 mm/2.9 mm for left/right lung), followed by heart (DSC 0.92, HD95 4.4 mm), bladder (DSC 0.88, HD95 6.7 mm) and rectum (DSC 0.79, HD95 10.8 mm). Visual inspection showed excellent agreements with some exceptions for heart and rectum. CONCLUSIONS: The DI2IN algorithm automatically generated contours for organs at risk close to those by a human expert, making the contouring step in radiation treatment planning simpler and faster. Few cases still required manual corrections, mainly for heart and rectum.


Assuntos
Aprendizado Profundo , Tomografia Computadorizada por Raios X , Algoritmos , Humanos , Processamento de Imagem Assistida por Computador/métodos , Órgãos em Risco , Planejamento da Radioterapia Assistida por Computador/métodos , Tórax , Tomografia Computadorizada por Raios X/métodos
4.
Artigo em Inglês | MEDLINE | ID: mdl-35682517

RESUMO

In this paper, the authors investigated changes in mass concentrations of particulate matter (PM) during the Coronavirus Disease of 2019 (COVID-19) lockdown. Daily samples of PM1, PM2.5 and PM10 fractions were measured at an urban background sampling site in Zagreb, Croatia from 2009 to late 2020. For the purpose of meteorological normalization, the mass concentrations were fed alongside meteorological and temporal data to Random Forest (RF) and LightGBM (LGB) models tuned by Bayesian optimization. The models' predictions were subsequently de-weathered by meteorological normalization using repeated random resampling of all predictive variables except the trend variable. Three pollution periods in 2020 were examined in detail: January and February, as pre-lockdown, the month of April as the lockdown period, as well as June and July as the "new normal". An evaluation using normalized mass concentrations of particulate matter and Analysis of variance (ANOVA) was conducted. The results showed that no significant differences were observed for PM1, PM2.5 and PM10 in April 2020-compared to the same period in 2018 and 2019. No significant changes were observed for the "new normal" as well. The results thus indicate that a reduction in mobility during COVID-19 lockdown in Zagreb, Croatia, did not significantly affect particulate matter concentration in the long-term..


Assuntos
Poluentes Atmosféricos , Poluição do Ar , COVID-19 , Poluentes Atmosféricos/análise , Poluição do Ar/análise , Teorema de Bayes , COVID-19/epidemiologia , Cidades , Controle de Doenças Transmissíveis , Croácia/epidemiologia , Monitoramento Ambiental/métodos , Humanos , Aprendizado de Máquina , Material Particulado/análise
5.
Sensors (Basel) ; 22(11)2022 Jun 01.
Artigo em Inglês | MEDLINE | ID: mdl-35684856

RESUMO

An optimal control of the combustion process of an engine ensures lower emissions and fuel consumption plus high efficiencies. Combustion parameters such as the peak firing pressure (PFP) and the crank angle (CA) corresponding to 50% of mass fraction burned (MFB50) are essential for a closed-loop control strategy. These parameters are based on the measured in-cylinder pressure that is typically gained by intrusive pressure sensors (PSs). These are costly and their durability is uncertain. To overcome these issues, the potential of using a virtual sensor based on the vibration signals acquired by a knock sensor (KS) for control of the combustion process is investigated. The present work introduces a data-driven approach where a signal-processing technique, designated as discrete wavelet transform (DWT), will be used as the preprocessing step for extracting informative features to perform regression tasks of the selected combustion parameters with extreme gradient boosting (XGBoost) regression models. The presented methodology will be applied to data from two different spark-ignited, single cylinder gas engines. Finally, an analysis is obtained where the important features based on the model's decisions are identified.

6.
IEEE Trans Neural Netw Learn Syst ; 33(12): 7842-7852, 2022 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-34191732

RESUMO

In this work, we investigate the use of three information-theoretic quantities-entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler (KL) divergence-to understand and study the behavior of already trained fully connected feedforward neural networks (NNs). We analyze the connection between these information-theoretic quantities and classification performance on the test set by cumulatively ablating neurons in networks trained on MNIST, FashionMNIST, and CIFAR-10. Our results parallel those recently published by Morcos et al., indicating that class selectivity is not a good indicator for classification performance. However, looking at individual layers separately, both mutual information and class selectivity are positively correlated with classification performance, at least for networks with ReLU activation functions. We provide explanations for this phenomenon and conclude that it is ill-advised to compare the proposed information-theoretic quantities across layers. Furthermore, we show that cumulative ablation of neurons with ascending or descending information-theoretic quantities can be used to formulate hypotheses regarding the joint behavior of multiple neurons, such as redundancy and synergy, with comparably low computational cost. We also draw connections to the information bottleneck theory for NNs.


Assuntos
Teoria da Informação , Redes Neurais de Computação , Neurônios/fisiologia , Entropia
7.
IEEE Trans Neural Netw Learn Syst ; 33(12): 7039-7051, 2022 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-34191733

RESUMO

We review the current literature concerned with information plane (IP) analyses of neural network (NN) classifiers. While the underlying information bottleneck theory and the claim that information-theoretic compression is causally linked to generalization are plausible, empirical evidence was found to be both supporting and conflicting. We review this evidence together with a detailed analysis of how the respective information quantities were estimated. Our survey suggests that compression visualized in IPs is not necessarily information-theoretic but is rather often compatible with geometric compression of the latent representations. This insight gives the IP a renewed justification. Aside from this, we shed light on the problem of estimating mutual information in deterministic NNs and its consequences. Specifically, we argue that, even in feedforward NNs, the data processing inequality needs not to hold for estimates of mutual information. Similarly, while a fitting phase, in which the mutual information is between the latent representation and the target increases, is necessary (but not sufficient) for good classification performance, depending on the specifics of mutual information estimation, such a fitting phase needs to not be visible in the IP.


Assuntos
Compressão de Dados , Redes Neurais de Computação , Teoria da Informação
8.
Entropy (Basel) ; 23(6)2021 Jun 03.
Artigo em Inglês | MEDLINE | ID: mdl-34205211

RESUMO

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

9.
Sci Rep ; 11(1): 11547, 2021 06 02.
Artigo em Inglês | MEDLINE | ID: mdl-34078986

RESUMO

Automated construction of location graphs is instrumental but challenging, particularly in logistics optimisation problems and agent-based movement simulations. Hence, we propose an algorithm for automated construction of location graphs, in which vertices correspond to geographic locations of interest and edges to direct travelling routes between them. Our approach involves two steps. In the first step, we use a routing service to compute distances between all pairs of L locations, resulting in a complete graph. In the second step, we prune this graph by removing edges corresponding to indirect routes, identified using the triangle inequality. The computational complexity of this second step is [Formula: see text], which enables the computation of location graphs for all towns and cities on the road network of an entire continent. To illustrate the utility of our algorithm in an application, we constructed location graphs for four regions of different size and road infrastructures and compared them to manually created ground truths. Our algorithm simultaneously achieved precision and recall values around 0.9 for a wide range of the single hyperparameter, suggesting that it is a valid approach to create large location graphs for which a manual creation is infeasible.

10.
IEEE Trans Neural Netw Learn Syst ; 32(9): 3930-3941, 2021 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-32845846

RESUMO

We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and is implemented in a typical Wasserstein autoencoder framework. We choose a mixture of Gaussians as a target distribution in latent space, which provides a natural splitting of data into clusters. To connect Gaussian components with correct classes, we use a small amount of labeled data and a Gaussian classifier induced by the target distribution. SeGMA is optimized efficiently due to the use of the Cramer-Wold distance as a maximum mean discrepancy penalty, which yields a closed-form expression for a mixture of spherical Gaussian components and, thus, obviates the need of sampling. While SeGMA preserves all properties of its semi-supervised predecessors and achieves at least as good generative performance on standard benchmark data sets, it presents additional features: 1) interpolation between any pair of points in the latent space produces realistically looking samples; 2) combining the interpolation property with disentangling of class and style information, SeGMA is able to perform continuous style transfer from one class to another; and 3) it is possible to change the intensity of class characteristics in a data point by moving the latent representation of the data point away from specific Gaussian components.

11.
Entropy (Basel) ; 22(12)2020 Dec 14.
Artigo em Inglês | MEDLINE | ID: mdl-33327417

RESUMO

The information bottleneck (IB) framework, proposed in [...].

12.
Entropy (Basel) ; 22(11)2020 Oct 29.
Artigo em Inglês | MEDLINE | ID: mdl-33286997

RESUMO

In this short note, we relate the variational bounds proposed in Alemi et al. (2017) and Fischer (2020) for the information bottleneck (IB) and the conditional entropy bottleneck (CEB) functional, respectively. Although the two functionals were shown to be equivalent, it was empirically observed that optimizing bounds on the CEB functional achieves better generalization performance and adversarial robustness than optimizing those on the IB functional. This work tries to shed light on this issue by showing that, in the most general setting, no ordering can be established between these variational bounds, while such an ordering can be enforced by restricting the feasible sets over which the optimizations take place. The absence of such an ordering in the general setup suggests that the variational bound on the CEB functional is either more amenable to optimization or a relevant cost function for optimization in its own regard, i.e., without justification from the IB or CEB functionals.

13.
IEEE Trans Pattern Anal Mach Intell ; 42(9): 2225-2239, 2020 09.
Artigo em Inglês | MEDLINE | ID: mdl-30951462

RESUMO

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First, for deterministic DNNs, either the IB functional is infinite for almost all values of network parameters, making the optimization problem ill-posed, or it is piecewise constant, hence not admitting gradient-based optimization methods. Second, the invariance of the IB functional under bijections prevents it from capturing properties of the learned representation that are desirable for classification, such as robustness and simplicity. We argue that these issues are partly resolved for stochastic DNNs, DNNs that include a (hard or soft) decision rule, or by replacing the IB functional with related, but more well-behaved cost functions. We conclude that recent successes reported about training DNNs using the IB framework must be attributed to such solutions. As a side effect, our results indicate limitations of the IB framework for the analysis of DNNs. We also note that rather than trying to repair the inherent problems in the IB functional, a better approach may be to design regularizers on latent representation enforcing the desired properties directly.

14.
Entropy (Basel) ; 20(1)2018 Jan 17.
Artigo em Inglês | MEDLINE | ID: mdl-33265155

RESUMO

The generator matrices of polar codes and Reed-Muller codes are submatrices of the Kronecker product of a lower-triangular binary square matrix. For polar codes, the submatrix is generated by selecting rows according to their Bhattacharyya parameter, which is related to the error probability of sequential decoding. For Reed-Muller codes, the submatrix is generated by selecting rows according to their Hamming weight. In this work, we investigate the properties of the index sets selecting those rows, in the limit as the blocklength tends to infinity. We compute the Lebesgue measure and the Hausdorff dimension of these sets. We furthermore show that these sets are finely structured and self-similar in a well-defined sense, i.e., they have properties that are common to fractals.

15.
Med Biol Eng Comput ; 55(3): 507-515, 2017 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-27289590

RESUMO

The aim of this study was to evaluate feasibility and reproducibility of quantitative assessment of colonic morphology on CT colonography (CTC). CTC datasets from 60 patients with optimal colonic distension were assessed using prototype software. Metrics potentially associated with poor endoscopic performance were calculated for the total colon and each segment including: length, volume, tortuosity (number of high curvature points <90°), and compactness (volume of box containing centerline divided by centerline length). Sigmoid apex height relative to the lumbosacral junction was also measured. Datasets were quantified twice each, and intra-reader reliability was evaluated using concordance correlation coefficient and Bland-Altman plot. Complete quantitative datasets including the five proposed metrics were generated from 58 of 60 (97 %) CTC examinations. The sigmoid and transverse segments were the longest (55.9 and 51.4 cm), had the largest volumes (0.410 and 0.609 L), and were the most tortuous (3.39 and 2.75 high curvature points) and least compact (3347 and 3595 mm2), noting high inter-patient variability for all metrics. Mean height of the sigmoid apex was 6.7 cm, also with high inter-patient variability (SD 6.8 cm). Intra-reader reliability was high for total and segmental lengths and sigmoid apex height (CCC = 0.9991) with excellent repeatability coefficient (CR = 3.0-3.3). There was low percent variance of metrics dependent upon length (median 5 %). Detailed automated quantitative assessment of colonic morphology on routine CTC datasets is feasible and reproducible, requiring minimal reader interaction.


Assuntos
Colo/anatomia & histologia , Colonografia Tomográfica Computadorizada , Software , Adulto , Idoso , Idoso de 80 Anos ou mais , Estudos de Viabilidade , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Reprodutibilidade dos Testes
16.
AJR Am J Roentgenol ; 201(4): W596-602, 2013 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-24059398

RESUMO

OBJECTIVE: Fibrosis leads to altered liver hemodynamics. The arterial enhancement fraction, which is defined as the ratio of hepatic arterial perfusion to the total hepatic perfusion, can provide noninvasive assessment of hepatic perfusion. The aim of this study was to show that the arterial enhancement fraction values correlate with histopathologic stage of liver fibrosis, thus providing a reliable noninvasive radiologic alternative to liver biopsy for the detection and staging of hepatic fibrosis. MATERIALS AND METHODS: We evaluated hepatic fibrosis stage (denoted by Metavir score [F]) and arterial enhancement fraction of patients who underwent standard triphasic liver MRI and liver biopsy within 1 year from January 2005 to December 2010. Prototype software was used to calculate the arterial enhancement fraction. Statistical analysis included nonparametric tests and area under the receiver operating characteristic curve (AUC). RESULTS: One hundred fourteen patients (69 men and 45 women; median age, 52.5 years) were divided into groups according to the Metavir score. The mean arterial enhancement fraction was 24.2% ± 11.6% for F0, 35.2% ± 18.7% for F1, 30.2% ± 12.5% for F2, 37.5% ± 16.4% for F3, and 59.8% ± 16.6% for F4. The mean arterial enhancement fraction values differed significantly between Metavir scores (p < 0.001) and showed a positive correlation with Metavir score (r = 0.693; p < 0.001). The optimal mean arterial enhancement fraction cutoffs were 32.96% or more (AUC = 0.8343) for detection of mild fibrosis, 33.33% or more (AUC = 0.8524) for detection of moderate fibrosis, 38.43% or more (AUC = 0.8819) for detection of severe fibrosis, and 45.76% or more (AUC = 0.9161) for detection of cirrhosis. CONCLUSION: Arterial enhancement fraction using triple-phase MRI can provide a reliable noninvasive method to assess hepatic fibrosis.


Assuntos
Algoritmos , Artéria Hepática/patologia , Aumento da Imagem/métodos , Interpretação de Imagem Assistida por Computador/métodos , Cirrose Hepática/patologia , Angiografia por Ressonância Magnética/métodos , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Reprodutibilidade dos Testes , Sensibilidade e Especificidade , Adulto Jovem
17.
J Comput Assist Tomogr ; 36(6): 681-9, 2012.
Artigo em Inglês | MEDLINE | ID: mdl-23192205

RESUMO

OBJECTIVE: The objective of this study was to determine whether arterial enhancement fraction (AEF) is associated with the degree of liver fibrosis and cirrhosis in patients with chronic liver disease. METHODS: Sixty-five patients (mean age, 55.8 years; 19 female patients) underwent triple-phase computed tomography scanning. Mean AEF was determined for the left and right hepatic lobe of the liver using a prototypical software module and compared between groups of different liver fibrosis grade. RESULTS: Mean AEF was higher in patients with liver disease compared with those without liver disease. Mean AEF differed significantly between patients with normal liver or mild fibrosis (category 1), moderate to severe fibrosis (category 2), and cirrhosis (category 3). Receiver operating characteristic curve analysis determined an area under the curve of 0.79/0.78, with an optimal cutoff for mean AEF of 9.2/16.8, for differentiating between category 2 or higher/category 3 disease. CONCLUSIONS: The mean hepatic AEF can provide an accurate, fast, noninvasive assessment of the degree of fibrosis in chronic liver disease.


Assuntos
Cirrose Hepática/diagnóstico por imagem , Fígado/diagnóstico por imagem , Fígado/patologia , Área Sob a Curva , Meios de Contraste , Diagnóstico Diferencial , Feminino , Fibrose , Humanos , Iohexol , Circulação Hepática , Hepatopatias/diagnóstico por imagem , Hepatopatias/patologia , Masculino , Pessoa de Meia-Idade , Curva ROC , Intensificação de Imagem Radiográfica/métodos , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Índice de Gravidade de Doença , Tomografia Computadorizada por Raios X/métodos
18.
Eur J Nucl Med Mol Imaging ; 39(9): 1435-40, 2012 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-22669254

RESUMO

PURPOSE: The aim of this study was to evaluate whether a virtual 3-D (18)F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/CT panendoscopy is feasible and can be used for noninvasive imaging of the upper airways and pharyngeal/laryngeal tumours. METHODS: From (18)F-FDG PET/CT data sets of 40 patients (29 men, 11 women; age 61 ± 9 years) with pharyngeal or laryngeal malignancies virtual 3-D (18)F-FDG PET/CT panendoscopies were reconstructed and the image processing time was measured. The feasibility of assessing the oral cavity, nasopharynx, tongue base, soft palate, pharyngeal tonsils, epiglottis, aryepiglottic folds, piriform sinus, postcricoid space, glottis, subglottis, trachea, bronchi and oesophagus and of detecting primary tumours was tested. Results of fibre-optic bronchoscopy and histology served as the reference standard. RESULTS: The nasopharynx, tongue base, soft palate, pharyngeal tonsils, epiglottis, subglottis and the tracheobronchial tree were accessible in all 40, and the aryepiglottic folds, posterior hypopharyngeal wall, postcricoid space, piriform sinus, glottis, oral cavity and oesophagus in 37, 37, 37, 37, 33, 16 and 0 patients, respectively. In all 12 patients with restricted fibre-optic evaluation due to being primarily intubated, the subglottis was accessible via virtual panendoscopy. The primary tumour was depicted in 36 of 40 patients (90 %). The mean processing time for virtual (18)F-FDG PET/CT panendoscopies was 145 ± 98 s. CONCLUSION: Virtual (18)F-FDG PET/CT panendoscopy of the upper airways is technically feasible and can detect pharyngeal and laryngeal malignancies. This new tool can aid in the complete evaluation of the subglottic space in intubated patients and may be used for planning optical panendoscopies, biopsies and surgery in the future.


Assuntos
Endoscopia/métodos , Fluordesoxiglucose F18 , Neoplasias de Cabeça e Pescoço/diagnóstico por imagem , Imagem Multimodal/métodos , Tomografia por Emissão de Pósitrons , Sistema Respiratório/diagnóstico por imagem , Tomografia Computadorizada por Raios X , Interface Usuário-Computador , Idoso , Idoso de 80 Anos ou mais , Estudos de Viabilidade , Feminino , Neoplasias de Cabeça e Pescoço/secundário , Humanos , Neoplasias Laríngeas/diagnóstico por imagem , Neoplasias Laríngeas/patologia , Masculino , Pessoa de Meia-Idade , Neoplasias Faríngeas/diagnóstico por imagem , Neoplasias Faríngeas/patologia , Estudos Retrospectivos , Fatores de Tempo
19.
Eur J Radiol ; 81(10): 2900-6, 2012 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-22127374

RESUMO

PURPOSE: In oxygen-enhanced magnetic resonance imaging of the lung (O2-MRI), motion artifacts related to breathing hamper the quality of the parametric O2-maps. In this study, fully automatic non-rigid image registration was assessed as a post-processing method to improve the quality of O2-MRI. MATERIALS AND METHODS: Twenty healthy volunteers were investigated on a 1.5 T MR system. O2-MRI was obtained in four coronal sections using an IR-HASTE sequence with TE/TI of 12/1200 ms. Each section was repeatedly imaged during oxygen and room-air ventilation. Spatial differences among the images were corrected by fully automatic non-rigid registration. Signal variability, relative enhancement ratio between oxygen and room air images, and spatial heterogeneity of lung enhancement were assessed before and after image registration. RESULTS: Motion artifacts were corrected in 5-10s. Non-rigid registration reduced signal variability of the source images and heterogeneity of the O2-maps by 1.1 ± 0.2% and 11.2 ± 2.9%, respectively (p<0.0001). Registration did not influence O2 relative enhancement ratio (p=0.06). CONCLUSION: Fully automatic non-rigid image registration improves the quality of multislice oxygen-enhanced MRI of the lung.


Assuntos
Aumento da Imagem/métodos , Interpretação de Imagem Assistida por Computador/métodos , Pulmão/anatomia & histologia , Imageamento por Ressonância Magnética/métodos , Oxigênio , Reconhecimento Automatizado de Padrão/métodos , Técnica de Subtração , Administração por Inalação , Adulto , Algoritmos , Meios de Contraste/administração & dosagem , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Oxigênio/administração & dosagem , Reprodutibilidade dos Testes , Sensibilidade e Especificidade
20.
J Nucl Med ; 52(10): 1520-5, 2011 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-21908390

RESUMO

UNLABELLED: The aim of this study was to determine the diagnostic accuracy of (18)F-FDG PET/CT bronchoscopy for the detection of regional lymph node metastases in non-small cell lung cancer (NSCLC) patients; potential differences in the maximum standardized uptake value (SUVmax), mean SUV (SUVmean), short-axis diameter, and distance to the airways when comparing true-positive (TP), false-positive (FP), true-negative (TN), and false-negative (FN) lymph nodes; the smallest bronchus diameter accessible by virtual bronchoscopy; and the duration from the start of the virtual (18)F-FDG PET/CT bronchoscopy viewing tool until the images were displayed. METHODS: Sixty-one consecutive NSCLC patients (mean age ± SD, 58 ± 10 y) underwent whole-body (18)F-FDG PET/CT. From these data, virtual (18)F-FDG PET/CT bronchoscopies were reconstructed. The duration from the start of the tool until the display of virtual bronchoscopy images was determined. The diagnostic accuracy of (18)F-FDG PET/CT bronchoscopy for the detection of regional lymph node metastases was evaluated on a lesion basis. Axial (18)F-FDG PET/CT scans served as the standard of reference. The SUVmax, SUVmean, short-axis diameter, and distance to the airways of regional lymph nodes were measured. Lymph nodes were classified as TP, FP, TN, and FN. The smallest bronchus diameter accessible by (18)F-FDG PET/CT bronchoscopy was measured. RESULTS: The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of virtual (18)F-FDG PET/CT bronchoscopy for the detection of lymph node metastases were 76%, 87%, 85%, 79%, and 81%, respectively. The differences between the SUVmax, SUVmean, short-axis diameter, and distance to the airways of TP and FP as well as TN and FN lymph nodes were statistically significant (P < 0.05). The mean smallest diameter of accessible bronchi by (18)F-FDG PET/CT bronchoscopy was 3 mm. The mean time duration from the start of the virtual (18)F-FDG PET/CT bronchoscopy tool until the display of the images was 22 ± 7 s. CONCLUSION: Virtual fly-through 3-dimensional (18)F-FDG PET/CT bronchoscopy yields a high diagnostic accuracy for the detection of regional lymph node metastases and has access to bronchi even in the periphery of the lung. High SUVmax, high SUVmean, large small-axis diameter, and short distance to the airways aid detection of lymph node metastases with (18)F-FDG PET/CT bronchoscopy.


Assuntos
Broncoscopia/métodos , Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Carcinoma Pulmonar de Células não Pequenas/secundário , Neoplasias Pulmonares/diagnóstico por imagem , Metástase Linfática/diagnóstico por imagem , Tomografia por Emissão de Pósitrons/métodos , Tomografia Computadorizada por Raios X/métodos , Interface Usuário-Computador , Adulto , Idoso , Idoso de 80 Anos ou mais , Broncoscopia/estatística & dados numéricos , Feminino , Fluordesoxiglucose F18 , Humanos , Masculino , Pessoa de Meia-Idade , Tomografia por Emissão de Pósitrons/estatística & dados numéricos , Valor Preditivo dos Testes , Compostos Radiofarmacêuticos , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/estatística & dados numéricos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...