Purpose
To study the influence of gradient echo–based contrasts as input channels to a 3D patch‐based neural network trained for synthetic CT (sCT) generation in canine and human populations.
Methods
...Magnetic resonance images and CT scans of human and canine pelvic regions were acquired and paired using nonrigid registration. Magnitude MR images and Dixon reconstructed water, fat, in‐phase and opposed‐phase images were obtained from a single T1‐weighted multi‐echo gradient‐echo acquisition. From this set, 6 input configurations were defined, each containing 1 to 4 MR images regarded as input channels. For each configuration, a UNet‐derived deep learning model was trained for synthetic CT generation. Reconstructed Hounsfield unit maps were evaluated with peak SNR, mean absolute error, and mean error. Dice similarity coefficient and surface distance maps assessed the geometric fidelity of bones. Repeatability was estimated by replicating the training up to 10 times.
Results
Seventeen canines and 23 human subjects were included in the study. Performance and repeatability of single‐channel models were dependent on the TE‐related water–fat interference with variations of up to 17% in mean absolute error, and variations of up to 28% specifically in bones. Repeatability, Dice similarity coefficient, and mean absolute error were statistically significantly better in multichannel models with mean absolute error ranging from 33 to 40 Hounsfield units in humans and from 35 to 47 Hounsfield units in canines.
Conclusion
Significant differences in performance and robustness of deep learning models for synthetic CT generation were observed depending on the input. In‐phase images outperformed opposed‐phase images, and Dixon reconstructed multichannel inputs outperformed single‐channel inputs.
In diffusion tensor magnetic resonance imaging (DT-MRI), limitations concerning complex fiber architecture (when an image voxel contains fiber populations with more than one dominant orientation) are ...well-known. Fractional anisotropy (FA) values are lower in such areas because of a lower directionality of diffusion on the voxel-scale, which makes the interpretation of FA less straightforward. Moreover, the interpretation of the axial and radial diffusivities is far from trivial when there is more than one dominant fiber orientation within a voxel. In this work, using (i) theoretical considerations, (ii) simulations, and (iii) experimental data, it is demonstrated that the mean diffusivity (or the trace of the diffusion tensor) is lower in complex white matter configurations, compared with tissue where there is a single dominant fiber orientation within the voxel. We show that the magnitude of this reduction depends on various factors, including configurational and microstructural properties (e.g., the relative contributions of different fiber populations) and acquisition settings (e.g., the b-value). These results increase our understanding of the quantitative metrics obtained from DT-MRI and, in particular, the effect of the microstructural architecture on the mean diffusivity. More importantly, they reinforce the growing awareness that differences in DT-MRI metrics need to be interpreted cautiously.
► The mean diffusivity (MD) in diffusion tensor MRI is affected by crossing fibers. ► MD values are lower in complex fiber architecture than in single fiber voxels. ► This is shown using theoretical considerations, simulations and in vivo experiments. ► In vivo, mean diffusivity values decrease when fibers cross at larger angles.
Heavy smokers undergoing screening with low-dose chest CT are affected by cardiovascular disease as much as by lung cancer. Low-dose chest CT scans acquired in screening enable quantification of ...atherosclerotic calcifications and thus enable identification of subjects at increased cardiovascular risk. This paper presents a method for automatic detection of coronary artery, thoracic aorta, and cardiac valve calcifications in low-dose chest CT using two consecutive convolutional neural networks. The first network identifies and labels potential calcifications according to their anatomical location and the second network identifies true calcifications among the detected candidates. This method was trained and evaluated on a set of 1744 CT scans from the National Lung Screening Trial. To determine whether any reconstruction or only images reconstructed with soft tissue filters can be used for calcification detection, we evaluated the method on soft and medium/sharp filter reconstructions separately. On soft filter reconstructions, the method achieved F 1 scores of 0.89, 0.89, 0.67, and 0.55 for coronary artery, thoracic aorta, aortic valve, and mitral valve calcifications, respectively. On sharp filter reconstructions, the F 1 scores were 0.84, 0.81, 0.64, and 0.66, respectively. Linearly weighted kappa coefficients for risk category assignment based on per subject coronary artery calcium were 0.91 and 0.90 for soft and sharp filter reconstructions, respectively. These results demonstrate that the presented method enables reliable automatic cardiovascular risk assessment in all low-dose chest CT scans acquired for lung cancer screening.
Automatic segmentation in MR brain images is important for quantitative analysis in large-scale studies with images acquired at all ages. This paper presents a method for the automatic segmentation ...of MR brain images into a number of tissue classes using a convolutional neural network. To ensure that the method obtains accurate segmentation details as well as spatial consistency, the network uses multiple patch sizes and multiple convolution kernel sizes to acquire multi-scale information about each voxel. The method is not dependent on explicit features, but learns to recognise the information that is important for the classification based on training data. The method requires a single anatomical MR image only. The segmentation method is applied to five different data sets: coronal T 2 -weighted images of preterm infants acquired at 30 weeks postmenstrual age (PMA) and 40 weeks PMA, axial T 2 -weighted images of preterm infants acquired at 40 weeks PMA, axial T 1 -weighted images of ageing adults acquired at an average age of 70 years, and T 1 -weighted images of young adults acquired at an average age of 23 years. The method obtained the following average Dice coefficients over all segmented tissue classes for each data set, respectively: 0.87, 0.82, 0.84, 0.86, and 0.91. The results demonstrate that the method obtains accurate segmentations in all five sets, and hence demonstrates its robustness to differences in age and acquisition protocol.
During the last decade, diffusion tensor imaging (DTI) has been used extensively to investigate microstructural properties of white matter fiber pathways. In many of these DTI-based studies, fiber ...tractography has been used to infer relationships between bundle-specific mean DTI metrics and measures-of-interest (e.g., when studying diffusion changes related to age, cognitive performance, etc.) or to assess potential differences between populations (e.g., comparing males vs. females, healthy vs. diseased subjects, etc.). As partial volume effects (PVEs) are known to affect tractography and, subsequently, the estimated DTI measures sampled along these reconstructed tracts in an adverse way, it is important to gain insight into potential confounding factors that may modulate this PVE. For instance, for thicker fiber bundles, the contribution of PVE-contaminated voxels to the mean metric for the entire fiber bundle will be smaller, and vice-versa — which means that the extent of PVE-contamination will vary from bundle to bundle. With the growing popularity of tractography-based methods in both fundamental research and clinical applications, it is of paramount importance to examine the presence of PVE-related covariates, such as thickness, orientation, curvature, and shape of a fiber bundle, and to investigate the extent to which these hidden confounds affect diffusion measures. To test the hypothesis that these PVE-related covariates modulate DTI metrics depending on the shape of a bundle, we performed simulations with synthetic diffusion phantoms and analyzed bundle-specific DTI measures of the cingulum and the corpus callosum in 55 healthy subjects. Our results indicate that the estimated bundle-specific mean values of diffusion metrics, including the frequently used fractional anisotropy and mean diffusivity, were indeed modulated by fiber bundle thickness, orientation, and curvature. Correlation analyses between gender and diffusion measures yield different results when volume is included as a covariate. This indicates that incorporating these PVE-related factors in DTI analyses is imperative to disentangle changes in “true microstructural” tissue properties from these hidden covariates.
► In fiber tract simulations, DTI measures (e.g., FA, MD) correlate with bundle volume. ► Confirming these simulations, FA was correlated with bundle volume in the cingulum. ► Correlations of FA with gender change when bundle volume is included as a covariate. ► We suggest to include tract volume as a covariate to improve DTI analysis specificity.
•Presence of functionally significant coronary stenosis is determined automatically.•Functional significance of the stenosis is determined by myocardium analysis.•Deep learning is applied to analyze ...the left ventricle myocardium in coronary CTA.•The results demonstrate that identification of patients with low FFR is feasible.•This may potentially reduce the number of patients undergoing invasive FFR.
Display omitted
In patients with coronary artery stenoses of intermediate severity, the functional significance needs to be determined. Fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA), is most often used in clinical practice. To reduce the number of ICA procedures, we present a method for automatic identification of patients with functionally significant coronary artery stenoses, employing deep learning analysis of the left ventricle (LV) myocardium in rest coronary CT angiography (CCTA).
The study includes consecutively acquired CCTA scans of 166 patients who underwent invasive FFR measurements. To identify patients with a functionally significant coronary artery stenosis, analysis is performed in several stages. First, the LV myocardium is segmented using a multiscale convolutional neural network (CNN). To characterize the segmented LV myocardium, it is subsequently encoded using unsupervised convolutional autoencoder (CAE). As ischemic changes are expected to appear locally, the LV myocardium is divided into a number of spatially connected clusters, and statistics of the encodings are computed as features. Thereafter, patients are classified according to the presence of functionally significant stenosis using an SVM classifier based on the extracted features.
Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coefficient of 0.91 and an average mean absolute distance between the segmented and reference LV boundaries of 0.7 mm. Twenty CCTA images were used to train the LV myocardium encoder. Classification of patients was evaluated in the remaining 126 CCTA scans in 50 10-fold cross-validation experiments and resulted in an area under the receiver operating characteristic curve of 0.74 ± 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding specificity was 0.77, 0.71 and 0.59, respectively.
The results demonstrate that automatic analysis of the LV myocardium in a single CCTA scan acquired at rest, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally significant coronary artery stenosis. This might reduce the number of patients undergoing unnecessary invasive FFR measurements.
The calcium burden as estimated from non-ECG-synchronized computed tomography (CT) exams acquired in screening of heavy smokers has been shown to be a strong predictor of cardiovascular events. We ...present a method for automatic coronary calcium scoring with low-dose, non-contrast-enhanced, non-ECG-synchronized chest CT. First, a probabilistic coronary calcium map was created using multi-atlas segmentation. This map assigned an a priori probability for the presence of coronary calcifications at every location in a scan. Subsequently, a statistical pattern recognition system was designed to identify coronary calcifications by texture, size, and spatial features; the spatial features were computed using the coronary calcium map. The detected calcifications were quantified in terms of volume and Agatston score. The best results were obtained by merging the results of three different supervised classification systems, namely direct classification with a nearest neighbor classifier, and two-stage classification with nearest neighbor and support vector machine classifiers. We used a total of 231 test scans containing 45 674mm of coronary calcifications. The presented method detected on average 157/198mm (sensitivity 79.2%) of coronary calcium volume with on average 4 mm false positive volume. Calcium scoring can be performed automatically in low-dose, noncontrast enhanced, non-ECG-synchronized chest CT in screening of heavy smokers to identify subjects who might benefit from preventive treatment.
We are continuously exposed to food and during the day we make many food choices. These choices play an important role in the regulation of food intake and thereby in weight management. Therefore, it ...is important to obtain more insight into the mechanisms that underlie these choices. While several food choice functional MRI (fMRI) studies have been conducted, the effect of energy content on neural responses during food choice has, to our knowledge, not been investigated before. Our objective was to examine brain responses during food choices between equally liked high- and low-calorie foods in the absence of hunger. During a 10-min fMRI scan 19 normal weight volunteers performed a forced-choice task. Food pairs were matched on individual liking but differed in perceived and actual caloric content (high-low). Food choice compared with non-food choice elicited stronger unilateral activation in the left insula, superior temporal sulcus, posterior cingulate gyrus and (pre)cuneus. This suggests that the food stimuli were more salient despite subject's low motivation to eat. The right superior temporal sulcus (STS) was the only region that exhibited greater activation for high versus low calorie food choices between foods matched on liking. Together with previous studies, this suggests that STS activation during food evaluation and choice may reflect the food's biological relevance independent of food preference. This novel finding warrants further research into the effects of hunger state and weight status on STS, which may provide a marker of biological relevance.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Neuro-imaging holds great potential for predicting choice behavior from brain responses. In this study we used both traditional mass-univariate and state-of-the-art multivariate pattern analysis to ...establish which brain regions respond to preferred packages and to what extent neural activation patterns can predict realistic low-involvement consumer choices. More specifically, this was assessed in the context of package-induced binary food choices. Mass-univariate analyses showed that several regions, among which the bilateral striatum, were more strongly activated in response to preferred food packages. Food choices could be predicted with an accuracy of up to 61.2% by activation patterns in brain regions previously found to be involved in healthy food choices (superior frontal gyrus) and visual processing (middle occipital gyrus). In conclusion, this study shows that mass-univariate analysis can detect small package-induced differences in product preference and that MVPA can successfully predict realistic low-involvement consumer choices from functional MRI data.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
To determine the agreement and reliability of fully automated coronary artery calcium (CAC) scoring in a lung cancer screening population.
1793 low-dose chest CT scans were analyzed ...(non-contrast-enhanced, non-gated). To establish the reference standard for CAC, first automated calcium scoring was performed using a preliminary version of a method employing coronary calcium atlas and machine learning approach. Thereafter, each scan was inspected by one of four trained raters. When needed, the raters corrected initially automaticity-identified results. In addition, an independent observer subsequently inspected manually corrected results and discarded scans with gross segmentation errors. Subsequently, fully automatic coronary calcium scoring was performed. Agatston score, CAC volume and number of calcifications were computed. Agreement was determined by calculating proportion of agreement and examining Bland-Altman plots. Reliability was determined by calculating linearly weighted kappa (κ) for Agatston strata and intraclass correlation coefficient (ICC) for continuous values.
44 (2.5%) scans were excluded due to metal artifacts or gross segmentation errors. In the remaining 1749 scans, median Agatston score was 39.6 (P25-P75∶0-345.9), median volume score was 60.4 mm3 (P25-P75∶0-361.4) and median number of calcifications was 2 (P25-P75∶0-4) for the automated scores. The κ demonstrated very good reliability (0.85) for Agatston risk categories between the automated and reference scores. The Bland-Altman plots showed underestimation of calcium score values by automated quantification. Median difference was 2.5 (p25-p75∶0.0-53.2) for Agatston score, 7.6 (p25-p75∶0.0-94.4) for CAC volume and 1 (p25-p75∶0-5) for number of calcifications. The ICC was very good for Agatston score (0.90), very good for calcium volume (0.88) and good for number of calcifications (0.64).
Fully automated coronary calcium scoring in a lung cancer screening setting is feasible with acceptable reliability and agreement despite an underestimation of the amount of calcium when compared to reference scores.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK