Search

Altres ajuts: Additionally, this work was funded by the CIBERNED program (Program 1, Alzheimer Disease), FondoEuropeo de Desarrollo Regional (FEDER), Unión Europea, "Una manera de hacer Europa" and a "Marató TV3" grant (grant number: 201412.10). The cerebrospinal fluid (CSF) biomarkers amyloid-β 1-42 (Aβ), total and phosphorylated tau (t-tau, p-tau) are increasingly used to assist in the clinical diagnosis of Alzheimer's disease (AD). However, CSF biomarker levels can be affected by confounding factors. To investigate the association of white matter hyperintensities (WMHs) present in the brain with AD CSF biomarker levels. We included CSF biomarker and magnetic resonance imaging (MRI) data of 172 subjects (52 controls, 72 mild cognitive impairment (MCI), and 48 AD patients) from 9 European Memory Clinics. A computer aided detection system for standardized automated segmentation of WMHs was used on MRI scans to determine WMH volumes. Association of WMH volume with AD CSF biomarkers was determined using linear regression analysis. A small, negative association of CSF Aβ, but not p -tau and t -tau, levels with WMH volume was observed in the AD (r 2 = 0.084, p = 0.046), but not the MCI and control groups, which was slightly increased when including the distance of WMHs to the ventricles in the analysis (r 2 = 0.105, p = 0.025). Three global patterns of WMH distribution, either with 1) a low, 2) a peak close to the ventricles, or 3) a high, broadly-distributed WMH volume could be observed in brains of subjects in each diagnostic group. Despite an association of WMH volume with CSF Aβ levels in AD patients, the occurrence of WMHs is not accompanied by excess release of cellular proteins in the CSF, suggesting that WMHs are no major confounder for AD CSF biomarker assessment.

Convolutional neural networks (CNN) have been widely used for visual recognition tasks including semantic segmentation of images. While the existing methods consider uniformly sampled single-or multi-scale patches from the neighborhood of each voxel, this approach might be sub-optimal as it captures and processes unnecessary details far away from the center of the patch. We instead propose to train CNNs with non-uniformly sampled patches that allow a wider extent for the sampled patches. This results in more captured contextual information, which is in particular of interest for biomedical image analysis, where the anatomical location of imaging features are often crucial. We evaluate and compare this strategy for white matter hyperintensity segmentation on a test set of 46 MRI scans. We show that the proposed method not only outperforms identical CNNs with uniform patches of the same size (0.780 Dice coefficient compared to 0.736), but also gets very close to the performance of an independent human expert (0.796 Dice coefficient).

Dissimilarity measures for DTI clustering are abundant. However, for HARDI, the L2 norm has up to now been one of only few practically feasible measures. In this paper we propose a new measure, that not only compares the amplitude of diffusion profiles, but also rewards coincidence of the extrema. We tested this on phantom and real brain data. In both cases, our measure significantly outperformed the L2 norm.

Cerebral small vessel disease (SVD) is a disorder frequently found among the old people and is associated with deterioration in cognitive performance, parkinsonism, motor and mood impairments. White matter hyperintensities (WMH) as well as lacunes, microbleeds and subcortical brain atrophy are part of the spectrum of image findings, related to SVD. Accurate segmentation of WMHs is important for prognosis and diagnosis of multiple neurological disorders such as MS and SVD. Almost all of the published (semi-)automated WMH detection models employ multiple complex hand-crafted features, which require in-depth domain knowledge. In this paper we propose to apply a single-layer network unsupervised feature learning (USFL) method to avoid hand-crafted features, but rather to automatically learn a more efficient set of features. Experimental results show that a computer aided detection system with a USFL system outperforms a hand-crafted approach. Moreover, since the two feature sets have complementary properties, a hybrid system that makes use of both hand-crafted and unsupervised learned features, shows a significant performance boost compared to each system separately, getting close to the performance of an independent human expert.

Cerebral small vessel disease (SVD) is a common finding on magnetic resonance images of elderly people. White matter lesions (WML) are important markers for not only the small vessel disease, but also neuro-degenerative diseases including multiple sclerosis, Alzheimer’s disease and vascular dementia. Volumetric measurements such as the “total lesion load”, have been studied and related to these diseases. With respect to SVD we conjecture that small lesions are important, as they have been observed to grow over time and they form the majority of lesions in number. To study these small lesions they need to be annotated, which is a complex and time-consuming task. Existing (semi) automatic methods have been aimed at volumetric measurements and large lesions, and are not suitable for the detection of small lesions. In this research we established a supervised voxel classification CAD system, optimized and trained to exclusively detect small WMLs. To achieve this, several preprocessing steps were taken, which included a robust standardization of subject intensities to reduce inter-subject intensity variability as much as possible. A number of features that were found to be well identifying small lesions were calculated including multimodal intensities, tissue probabilities, several features for accurate location description, a number of second order derivative features as well as multi-scale annular filter for blobness detection. Only small lesions were used to learn the target concept via Adaboost using random forests as its basic classifiers. Finally the results were evaluated using Free-response receiver operating characteristic.

We propose a deep study on tissue modelization and classification techniques on T1-weighted MR images. Six approaches have been taken into account to perform this validation study. We consider first the Finite Gaussian Mixture model (A-FGMM) and a Bayes classification. Second method is the same as A-FGMM but introducing a Hidden Markov Random Field (HMRF) model to encode spatial information and classification is then performed by Maximum a Posteriori (MAP). Third, we study a method that models mixture tissues as a linear combination Gaussian pure tissue distributions (C-GPV) and it also performs a Bayes classification. Fourth, method D-GPV-HMRF uses the same image model as method C-GPV but encode spatial information as done in method B-HMRF. Fifth algorithm do not parameterize the intensity distribution but they directly classifies from intensity probabilities (Error Probability, E-EP). Last method it is also non-parametric but uses a HMRF to introduce spatial information (F-NPHMRF). All methods have been tested on a Digital Brain Phantom image considered as the ground truth. Noise and intensity non-uniformities have been added to simulate real image conditions. Results demonstrate that methods relying in both intensity and spatial information are in general more robust to noise and inhomogeneities. We demonstrate also that partial volume (PV) is still not completely well-model even if methods that uses this mixture model perform less errors.

Screening with automated 3D breast ultrasound (ABUS) is gaining popularity. However, the acquisition of multiple views required to cover an entire breast makes radiologic reading time-consuming. Linking lesions across views can facilitate the reading process. In this paper, we propose a method to automatically predict the position of a lesion in the target ABUS views, given the location of the lesion in a source ABUS view. We combine features describing the lesion location with respect to the nipple, the transducer and the chestwall, with features describing lesion properties such as intensity, spiculation, blobness, contrast and lesion likelihood. By using a grid search strategy, the location of the lesion was predicted in the target view. Our method achieved an error of 15.64 mm±16.13 mm. The error is small enough to help locate the lesion with minor additional interaction.

White matter lesions (WML) are diffuse white matter abnormalities commonly found in older subjects and are important indicators of stroke, multiple sclerosis, dementia and other disorders. We present an automated WML detection method and evaluate it on a dataset of small vessel disease (SVD) patients. In early SVD, small WMLs are expected to be of importance for the prediction of disease progression. Commonly used WML segmentation methods tend to ignore small WMLs and are mostly validated on the basis of total lesion load or a Dice coefficient for all detected WMLs. Therefore, in this paper, we present a method that is designed to detect individual lesions, large or small, and we validate the detection performance of our system with FROC (free-response ROC) analysis. For the automated detection, we use supervised classification making use of multimodal voxel based features from different magnetic resonance imaging (MRI) sequences, including intensities, tissue probabilities, voxel locations and distances, neighborhood textures and others. After preprocessing, including co-registration, brain extraction, bias correction, intensity normalization, and nonlinear registration, ventricle segmentation is performed and features are calculated for each brain voxel. A gentle-boost classifier is trained using these features from 50 manually annotated subjects to give each voxel a probability of being a lesion voxel. We perform ROC analysis to illustrate the benefits of using additional features to the commonly used voxel intensities; significantly increasing the area under the curve (Az) from 0.81 to 0.96 (p