Search

Quantification of brain growth is crucial for the assessment of fetal well being, for which ultrasound (US) images are the chosen clinical modality. However, they present artefacts, such as acoustic occlusion, especially after the 18th gestational week, when cranial calcification appears. Fetal US volume registration is useful in one or all of the following cases: to monitor the evolution of fetometry indicators, to segment different structures using a fetal brain atlas, and to align and combine multiple fetal brain acquisitions. This paper presents a new approach for automatic registration of real 3D US fetal brain volumes, volumes that contain a considerable degree of occlusion artefacts, noise, and missing data. To achieve this, a novel variant of the coherent point drift method is proposed. This work employs supervised learning to segment and conform a point cloud automatically and to estimate their subsequent weight factors. These factors are obtained by a random forest-based classification and are used to appropriately assign nonuniform membership probability values of a Gaussian mixture model. These characteristics allow for the automatic registration of 3D US fetal brain volumes with occlusions and multiplicative noise, without needing an initial point cloud. Compared to other intensity and geometry-based algorithms, the proposed method achieves an error reduction of 7.4% to 60.7%, with a target registration error of only 6.38 ± 3.24 mm. This makes the herein proposed approach highly suitable for 3D automatic registration of fetal head US volumes, an approach which can be useful to monitor fetal growth, segment several brain structures, or even compound multiple acquisitions taken from different projections.

The 3D tortuosity determined in several brain areas is proposed as a new morphological biomarker (BM) to be considered in early detection of Alzheimer’s disease (AD). It is measured using the sum of angles method and it has proven to be sensitive to anatomical changes that appear in gray and white matter and temporal and parietal lobes during mild cognitive impairment (MCI). Statistical analysis showed significant differences (p<0.05) between tortuosity indices determined for healthy controls (HC) vs. MCI and HC vs. AD in most of the analyzed structures. Other clinically used BMs have also been incorporated in the analysis: beta-amyloid and tau protein CSF and plasma concentrations, as well as other image-extracted parameters. A classification strategy using random forest (RF) algorithms was implemented to discriminate between three samples of the studied populations, selected from the ADNI database. Classification rates considering only image-extracted parameters show an increase of 9.17%, when tortuosity is incorporated. An enhancement of 1.67% is obtained when BMs measured from several modalities are combined with tortuosity.

Symmetry is an important feature in natural and man-made objects; particularly, mirror symmetry is a relevant task in fields such as computer vision and pattern recognition. In the current work, we propose a new method to characterize mirror-symmetry in open and closed curves represented by means of the Slope Chain Code. This representation is invariant under scale, rotation, and translation, highly desirable properties for object recognition applications. The proposed method detects symmetries through simple inversion, concatenation and reflection operations on the chains, thus allowing the classification of symmetrical and asymmetrical contours. It also introduces a measure to quantify the degree of symmetry in quasi-mirror-symmetrical objects. Furthermore, it allows the identification of multiple symmetry axes and their location. Results show high performances in symmetrical/asymmetrical classification (0.9 recall, 0.9 accuracy, 0.97 precision) and axes’ detection (0.8 recall, 0.84 accuracy, 0.99 precision). Compared to other methods, the proposed algorithm provides properties such as: global, local, and multiple axes’ detection, as well as the capability to classify symmetrical objects, which makes it adequate for several practical applications, like the three exemplified in the paper.

3D ultrasound systems have been widely used for fetal brain structures’ analysis. However, the obtained images present several artifacts such as multiplicative noise and acoustic shadows appearing as a function of acquisition angle. The purpose of this research is to merge several partially occluded ultrasound volumes, acquired by placing the transducer at different projections of the fetal head, to compound a new US volume containing the whole brain anatomy. To achieve this, the proposed methodology consists on the pipeline of four convolutional neural networks (CNN). Two CNNs are used to carry out fetal skull segmentations, by incorporating an incidence angle map and the segmented structures are then described with a Gaussian mixture model (GMM). For multiple US volumes registration, a feature set, based on distance maps computed from the GMM centroids is proposed. The third CNN learns the relation between distance maps of the volumes to be registered and estimates optimal rotation and translation parameters. Finally, the weighted root mean square is proposed as composition operator and weighting factors are estimated with the last CNN, which assigns a higher weight to those regions containing brain tissue and less ponderation to acoustic shadowed areas. The procedure was qualitatively and quantitatively validated in a set of fetal volumes obtained during gestation’s second trimester. Results show registration errors of 1.31 ± 0.2 mm and an increase of image sharpness of 34.9% compared to a single acquisition and of 25.2% compared to root mean square compounding.

Heart failure is defined as a syndrome characterized by a remodeling in the cardiac muscle structure that diminishes the strength and synchrony of contractions, leading the subject to a functional capacity deterioration that progressively triggers fatal clinical outcomes. There are specific pharmacological therapies to reduce failure progression. However, once the symptoms have developed, it is necessary to combine different treatments to alleviate them and to improve the quality of life. The most advanced therapies in recent years utilize implantable electronic devices known as cardiac resynchronizers. Cardiac resynchronization therapy has proven to be highly beneficial to patients with severe heart failure, because it reduces the number of hospitalizations, increases exercise resistance, and improves left ventricle systolic function and patient’s survival. Nonetheless, 20–30% of patients do not respond to this therapy, thus requiring reliable techniques to predict the probability of a successful outcome in a case-by-case basis. This chapter analyzes several methods that have been proposed to achieve this goal.

ObjectiveAn obsessive-compulsive disorder (OCD) subtype has been associated with streptococcal infections and is called pediatric autoimmune neuropsychiatric disorders associated with streptococci (PANDAS). The neuroanatomical characterization of subjects with this disorder is crucial for the better understanding of its pathophysiology; also, evaluation of these features as classifiers between patients and controls is relevant to determine potential biomarkers and useful in clinical diagnosis. This was the first multivariate pattern analysis (MVPA) study on an early-onset OCD subtype.MethodsFourteen pediatric patients with PANDAS were paired with 14 healthy subjects and were scanned to obtain structural magnetic resonance images (MRI). We identified neuroanatomical differences between subjects with PANDAS and healthy controls using voxel-based morphometry, diffusion tensor imaging (DTI), and surface analysis. We investigated the usefulness of these neuroanatomical differences to classify patients with PANDAS using MVPA.ResultsThe pattern for the gray and white matter was significantly different between subjects with PANDAS and controls. Alterations emerged in the cortex, subcortex, and cerebellum. There were no significant group differences in DTI measures (fractional anisotropy, mean diffusivity, radial diffusivity, and axial diffusivity) or cortical features (thickness, sulci, volume, curvature, and gyrification). The overall accuracy of 75% was achieved using the gray matter features to classify patients with PANDAS and healthy controls.ConclusionThe results of this integrative study allow a better understanding of the neural substrates in this OCD subtype, suggesting that the anatomical gray matter characteristics could have an immune origin that might be helpful in patient classification.

Alzheimer's disease is a multifactorial neurodegenerative disorder preceded by a prodromal stage called mild cognitive impairment (MCI). Early diagnosis of MCI is crucial for delaying the progression and optimizing the treatment. In this study we propose a random forest (RF) classifier to distinguish between MCI and healthy control subjects (HC), identifying the most relevant features computed from structural T1-weighted and diffusion-weighted magnetic resonance images (sMRI and DWI), combined with neuro-psychological scores. To train the RF we used a set of 60 subjects (HC = 30, MCI = 30) drawn from the Alzheimer's disease neuroimaging initiative database, while testing with unseen data was carried out on a 23-subjects Mexican cohort (HC = 12, MCI = 11). Features from hippocampus, thalamus and amygdala, for left and right hemispheres were fed to the RF, with the most relevant being previously selected by applying extra trees classifier and the mean decrease in impurity index. All the analyzed brain structures presented changes in sMRI and DWI features for MCI, but those computed from sMRI contribute the most to distinguish from HC. However, sMRI+DWI improves classification performance in training area under the receiver operating characteristic curve (AUROC = 93.5 ± 8%, accuracy = 88.8 ± 9%) and testing with unseen data (AUROC = 93.79%, accuracy = 91.3%), having a better performance when neuro-psychological scores were included. Compared to other classifiers the proposed RF provide the best performance for HC/MCI discrimination and the application of a feature selection step improves its performance. These findings imply that multimodal analysis gives better results than unimodal analysis and hence may be a useful tool to assist in early MCI diagnosis.

Birth weight (BW) is an important indicator of neonatal well–being associated with multiple adverse conditions and thus its early estimation may be crucial for timely treatment. In this paper we propose a BW estimation strategy based on Support Vector Regression of a set of multimodal maternal–fetal features obtained in pregnancy’s first trimester. The obtained results show an average difference of 250 g between the estimated and the real BW, with percentage errors below 3% in all cases. These results contrast with other reported studies, that estimate BW very close to delivery.

Mild cognitive impairment (MCI) is an abnormal deterioration of cognitive functions, whose prevalence is considerable in adults older than 65 years old. Several of these cases will convert to Alzheimer’s disease and therefore, MCI’s simple, proper and opportune diagnosis continues to be a research field with great impact in public health. In this paper we propose tortuosity, which is defined as a shape measure that has been applied to quantify morphological changes in several anatomical structures, as a potential biomarker sensitive enough to depict early brain changes that appear in MCI subjects in comparison with healthy controls (HC). Also, a random forest (RF) classification strategy was implemented to discriminate between MCI and HC populations. A training population selected from the ADNI database and a test group of 21 mexican subjects were analyzed. Statistical analysis showed significant differences (p < 0.05) in tortuosity indices determined for MCI vs HC populations in most of the measured cortical structures. Classification rates increased by 6.7% during training and 4.77% during the test stage, when incorporating tortuosity to other image-based features set. This suggests that tortuosity is a promising morphological parameter to be considered for early stages of Alzheimer disease (AD) and that, combined with an RF classifier, it can adequately separate HC and MCI subjects.

An indirect method of tissue consistency measurement is proposed, based on intensity and texture features of conventional ultrasound (US) cervix images. Calibration and validation were carried out in five phantoms simulating different cervical firmness, as well as in short and long cervices. Several image features attributed to the histogram, the co–occurrence matrix and the run–length encoding matrix were extracted and analyzed to evaluate their ability to distinguish between degrees of phantoms’ firmness. The most indicative of firmness indices were selected by correlating their values with the phantoms’ elasticities determined through Young’s moduli. Also, a random forest classifier was implemented, allowing to identify the features that contribute the most to class separation between phantoms. Using both tests, six features were selected: mean, standard deviation, entropy, skewness and two RLE-matrix features. A 6–fold cross validation was used to evaluate the model, obtaining a 98.9±0.79% accuracy. Finally, a preliminary case study was conducted upon closed and opened cervical US images, classifying them between both groups using a random forest model, obtaining an 84.34% accuracy. The indicated tests show that intensity and texture features extracted from conventional US images provide indirect and less–invasive information than other methods regarding tissue consistency, and therefore may be used to measure changes in cervical firmness.

Diverse neuro-psychological tasks have been designed for expressing intention mostly in the form of evoked potentials uncovered by time-coherent averaging, spectral analysis, or other digital signal processing techniques. Among others, the elicitation of the so-called P300 event-related potential has been found reproducible, reliable and suitable for environment control and communication applications that are not time-critical. The nature, elicitation and exploitation of the P300 potential for BCI is the subject of this chapter, organized in three sections: P300 event-related potential, P300 for spelling task and P300 for non-spelling tasks.

Electroencephalography (EEG) is the most frequently used technique to monitor functional activity of the brain. It has been widely employed in brain-computer interfaces based on the detection of P300 potentials. However, the P300 waves often contain physiological and non-physiological artifacts such as steady state visually evoked potential, power line or environment noise. The aim of this work is to eliminate undesirable periodic independent components from EEG, in order to enhance the P300 wave. The proposed method combines independent component analysis with a suitable selection of the most representative P300 components according to power features estimated from time measures using Parseval's theorem. The results show statistical differences (p

International audience; A new method to address the problem of shadowing in fetal brain ultrasound volumes is presented. The proposed approach is based on the spatial composition of multiple 3-D fetal head projections using the weighted Euclidean norm as an operator. A support vector machine, which is trained with optimal textural features, was used to assign weighting according to the posterior probabilities of brain tissue and shadows. Both phantom and real fetal head ultrasound volumes were compounded using previously reported operators and compared with the proposed composition method to validate it. The quantitative evaluations revealed increases in signal-to-noise ratio ≤35% and in contrast-to-noise ratio ≤135% using real data. Qualitative comparisons made by obstetricians indicated that this novel method adequately recovers brain tissue and improves the visibility of the main cerebral structures. This may prove useful both for fetal monitoring and in the diagnosis of brain defects. Overall this new approach outperforms spatial composition methods previously reported.

During the first trimester of pregnancy fetal health assessment is especially important. In the clinical practice, the gestational sac (GS) volume estimation is manually done using a tedious procedure which is prone to physicians' subjectivity. The method proposed in this paper consists on a semiautomatic delimitation of the GS and a segmentation of its content with minimal expert intervention. It is based on spreading active contours (SAC), following a planimetric strategy to define the GS' edges. Additionally, an optimal thresholding method was used to separate solid matter and amniotic fluid. The comparison between manual GS segmentations and those obtained with the proposed SAC method, shows Dice similarities of 90% and a mean Hausdor distance of 5.63 ± 1.94 mm, while the correlation index between SAC and the clinical reference (VOCAL) is 0.997. However, with statistical tests (t-paired) a value of p < 0.05 was obtained, which suggests a difference in the measured volume by the compared methods. The proposed method (SAC) has shown to be reliable, besides of being easy to implement.

Ultrasound (US) images of the fetal brain provide the experts with valuable indicators of the fetal development. However as the skull thickens, it obstructs the transmission of the acoustic waves, which in turn occludes the anatomy behind the thickened fetal skull. A viable option to improve the visibility of the fetal brain, before complete calcification of the skull, is the calculation of a compounded image made of different views of the same anatomical plane. In this work we report a new method for the composition of ultrasound images based on the Weighted Mean of the pixels, from different views, which correspond to each position (x, y) in the final compounded image. A support vector machine (SVM) is used to calculate the weights of each pixel from a different view, based on intensity, entropy and variance features. We present the initial test results of our method on synthetic US images of a head phantom, contaminated with speckle noise; we report the signal to noise ratio (SNR) and the normalized mutual information (NMI), for different number of views (2, 3, and 5), and compare the results against images compounded using the Mean, Root Mean Square (RMS), and Geometrical Mean composition methods. With our scheme we were able to recover the occluded information to increase the NMI from 16% to 26%, representing a 58% improvement.

Objective The goal of this research was to design, set up, use and evaluate a realistic simulation platform that could host real-time simulated robotics applications controlled with a brain-computer interface based on an event-related potential paradigm. Materials and methods The platform is composed of the following modules: (i) six band-limited channels of electroencephalographic signal acquisition; (ii) signal processing and classification with the BCI2000 software platform; (iii) stimulus presentation and (iv) robotics simulation. A modified Donchin speller matrix that uses iconic elements to indicate diverse navigational commands was implemented as the stimuli for the brain-computer interface, and an alternative interface was also included for independent manual navigation. A physically realistic wheelchair model with both autonomous and user control was used as the robotic element in the system. Results Two healthy subjects were asked to perform a given navigation task throughout a simulated home environment using both navigational interfaces. For each task, each subject drove the wheelchair along similar paths and distances. The task execution time was greater when using the brain-computer interface, but both subjects were successful in adequately driving the wheelchair with the BCI. Discussion The wheelchair model within the simulation and control platform serves as a proof of purpose of the proposed system and demonstrates its potential. Further tests and experiments are needed, along with the definition of adequate metrics to characterize the entire user-controller-robot-task ensemble. Conclusions With the developed platform, evaluation of prospective brain-computer interfaces can go beyond classical measurements of error and bit transfer rates, to include metrics accounting for the integrated system.

Factorial phase analysis (FaPI) represents an alternative method to Fourier phase analysis (FoPI) in the evaluation and detection of abnormalities on cardiac contraction patterns, but it has limitations in representing the sequence in abnormal contraction patterns. In this work we propose a modified factorial phase image (FaPIm) that incorporates more complete information regarding the ventricular contraction sequence. In particular, we analyze and evaluate the contribution of the third eigenimage, in the presence of ventricular dyssynchrony, which has not been sufficiently explored in the literature. We have validated the proposed FaPIm using two Equilibrium Radionuclide Angiography (ERNA) sets of images obtained with a dynamic cardiac phantom and with a numerically simulated phantom. Also, we have tested the proposed representation for a control group of 23 normal subjects and for a sample of 15 patients with Complete Left Bundle Branch Block (LBBB). Whereas FoPI allows us to obtain an image that synthesizes ventricular contraction with the smallest dispersion around the mean values, FaPI and FaPIm show that external areas surrounding ventricular cavities present more dephasing than the rest of the ventricular region and contain more detailed information about the progression of contraction. Also, in the presence of an abnormal contraction pattern, the magnitude of the third eigenvalue was greater than the corresponding eigenvalue obtained for normal simulations. The dispersion plots obtained for a normal contraction pattern show that left ventricle (LV) and right ventricle (RV) information overlap. Therefore, when there is a dyssynchrony between LV and RV contraction it becomes necessary to incorporate the information corresponding to the third factor to achieve a clear separation between regions. In the comparison of the indices of control and LBBB populations, FaPIm shows significant differences in five out of six contraction indices, showing its promising value as a clinical tool.

We present a novel approach to describe a P300 by a shape-feature vector, which offers several advantages over the feature vector used by the BCI2000 system. Additionally, we present a calibration algorithm that reduces the dimensionality of the shape-feature vector, the number of trials, and the electrodes needed by a Brain Computer Interface to accurately detect P300s; we also define a method to find a template that best represents, for a given electrode, the subject’s P300 based on his/her own acquired signals. Our experiments with 21 subjects showed that the SWLDA’s performance using our shape-feature vector was93%, that is,10%higher than the one obtained with BCI2000-feature’s vector. The shape-feature vector is 34-dimensional for every electrode; however, it is possible to significantly reduce its dimensionality while keeping a high sensitivity. The validation of the calibration algorithm showed an averaged area under the ROC (AUROC) curve of0.88. Also, most of the subjects needed less than15trials to have an AUROC superior to0.8. Finally, we found that the electrode C4 also leads to better classification.

A computational platform for the simulation, design and analysis of the Polylactic (PLA) acid production process using different lignocellulosic raw materials has been developed. The computational platform considers three main reactive-separation processes: 1) the bio-conversion process, where an hydrolysis-saccharification-culture process to produce the inoculated hydrolysate is coupled with a fermentation-separation process producing the broth with crude lactic acid; 2) the purification process, where a sequence of conventional and reactive distillation columns to perform the esterification and hydrolysis reactions, respectively, are used to produce a polymer grade lactic acid; and 3) the polymerization process, where a ring-opening polymerization reaction scheme to produce high molecular weight PLA is carried out. The platform was constructed on the Aspen Plus Environment. The implementation of the platform in a systematic manner allowed the evaluation of various mono and disaccharide materials to produce PLA. The results show that with a higher concentration of glucose the molecular weight of the PLA produced increased. However, the operation of the purification section, that is, the reactive distillation columns should be carried out carefully in order to obtain a purified lactic acid near to 88% mass fraction.

In this paper we present a fully automatic approach based on texture maps and optimal ellipse detection to segment and obtain measurements of the fetal head. The goals are to segment the fetal head and to measure the biparietal diameter (BPD) and head circumference (HC) using ultrasound images. By incorporating texture maps, morphological operations and active contours together with optimal ellipse detection, the segmentation and measurement of the fetal skull was performed. The results’ quality was evaluated by two obstetrician experts. A set of 10 studies was used to validate the segmentation process, obtaining a precision of 94.61%, a Dice similarity index of 97.19% and a maximum distance of 2.64 mm. To evaluate the head measures, a set of 23 images was used. The differences between experts and the proposed method are 2.72 mm for BPD and 2.73 mm for HC, with a correlation of 99.8% in both cases. These results suggest that the proposed method is suitable to be used for clinical applications in maternal medicine.

Brain magnetic resonance imaging segmentation is accomplished in this work by applying nonparametric density estimation, using the mean shift algorithm in the joint spatial-range domain. The quality of the class boundaries is improved by including an edge confidence map, that represents the confidence of truly being in the presence of a border between adjacent regions; an adjacency graph is then constructed with the labeled regions, and analyzed and pruned to merge adjacent regions. In order to assign image regions to a cerebral tissue type, a spatial normalization between image data and standard probability maps is carried out, so that for each structure a maximum a posteriori probability criterion is applied. The method was applied to synthetic and real images, keeping all parameters constant throughout the process for each type of data. The combination of region segmentation and edge detection proved to be a robust technique, as adequate clusters were automatically identified, regardless of the noise level and bias. In a comparison with reference segmentations, average Tanimoto indexes of 0.90-0.99 were obtained for synthetic data and of 0.59-0.99 for real data, considering gray matter, white matter, and background.

Magnetic resonance (MR) has been accepted as the reference image study in the clinical environment. The development of new sequences has allowed obtaining diverse images with high clinical importance and whose interpretation requires their joint analysis (multispectral MRI). Recent approaches to segment MRI point toward the definition of hybrid models, where the advantages of region and contour-based methods can be exploited to look for the integration or fusion of information, thus enhancing the performance of the individual approaches. Following this perspective, a hybrid model for multispectral brain MRI segmentation is presented. The model couples a segmenter, based on a radial basis network (RBFNNcc), and an active contour model, based on a cubic spline active contour (CSAC) interpolation. Both static and dynamic coupling of RBFNNcc and CSAC are proposed; the RBFNNcc stage provides an initial contour to the CSAC; the initial contour is optimally sampled with respect to its curvature variations; multispectral information and a restriction term are included into the CSAC energy equation. Segmentations were compared to a reference stack, indicating high-quality performance as measured by Tanimoto indexes of 0.74/spl plusmn/0.08.

Reported studies describing normal and abnormal aging based on anatomical MRI analysis do not consider morphological brain changes, but only volumetric measures to distinguish among these processes. This work presents a classification scheme, based both on size and shape features extracted from brain volumes, to determine different aging stages: healthy control (HC) adults, mild cognitive impairment (MCI), and Alzheimer's disease (AD). Three support vector machines were optimized and validated for the pair-wise separation of these three classes, using selected features from a set of 3D discrete compactness measures and normalized volumes of several global and local anatomical structures. Our analysis show classification rates of up to 98.3% between HC and AD; of 85% between HC and MCI and of 93.3% for MCI and AD separation. These results outperform those reported in the literature and demonstrate the viability of the proposed morphological indexes to classify different aging stages.

Previous work has shown that the segmentation of anatomical structures on 3D ultrasound data sets provides an important tool for the assessment of the fetal health. In this work, we present an algorithm based on a 3D statistical shape model to segment the fetal cerebellum on 3D ultrasound volumes. This model is adjusted using an ad hoc objective function which is in turn optimized using the Nelder–Mead simplex algorithm. Our algorithm was tested on ultrasound volumes of the fetal brain taken from 20 pregnant women, between 18 and 24 gestational weeks. An intraclass correlation coefficient of 0.8528 and a mean Dice coefficient of 0.8 between cerebellar volumes measured using manual techniques and the volumes calculated using our algorithm were obtained. As far as we know, this is the first effort to automatically segment fetal intracranial structures on 3D ultrasound data.

Brain computer interfaces (BCIs) translate brain activity into computer commands. To enhance the performance of a BCI, it is necessary to improve the feature extraction techniques being applied to decode the users' intentions. Objective comparison methods are needed to analyze different feature extraction techniques. One possibility is to use the classifier performance as a comparative measure. In this paper, we study the behavior of linear discriminant analysis (LDA) when used to distinguish between electroencephalographic (EEG) signals with and without the presence of event related potentials (ERPs).

"La imagenología por resonancia magnética (IRM) se ha convertido en una de las modalidades de imágenes médicas más importantes para el diagnóstico, prevención y monitoreo de desórdenes neurológicos. En particular, la imagenología ponderada de difusión de RM (DWI, Diffusion-Weighted Image) es altamente sensible para lograr una detección temprana de los cambios isquémicos en la fase aguda de un infarto cerebral. En este trabajo se presenta la aplicación y comparación de un método de segmentación adaptativo desarrollado y validado previamente, utilizando una técnica de estimación no paramétrica que incluye anchos de banda o radios de intensidad variables, con el objetivo de cuantificar la región de la lesión isquémica cerebral causada por un infarto sólo a partir de la información contenida en las imágenes DWI. El método fue aplicado a imágenes reales, manteniendo el conjunto de parámetros constantes durante el proceso de segmentación para toda la base de datos. La comparación de la técnica de segmentación adaptativa, en relación con una técnica de estimación no paramétrica de radio fijo, demostró además de ser una técnica automática y robusta de segmentación de lesiones isquémicas cerebrales en fase aguda a partir de imágenes DWI, que la utilización del método adaptativo arroja mejores resultados debido a que fue sensible a volúmenes de infartos pequeños (< 1 cm3). En comparación con la segmentación control de referencia de las lesiones cerebrales, las técnicas de segmentación evaluadas en este trabajo presentaron una correlación significativa para ambos métodos validados de radio fijo y radio variable (r = 0.8863 y r = 0.9693, respectivamente), observándose mejores resultados al utilizar el método adaptativo. Así mismo el índice de Tanimoto promedio obtenido fue superior para el caso del método de segmentación adaptativo que el de radio fijo, 0.729 y 0.638 respectivamente."

To delineate arbitrarily shaped clusters in a complex multimodal feature space, such as the brain MRI intensity space, often requires kernel estimation techniques with locally adaptive bandwidths, such as the adaptive mean shift procedure. Proper selection of the kernel bandwidth is a critical step for a better quality in the clustering. This paper presents a solution for the bandwidth selection, which is completely nonparametric and is based on the sample point estimator to yield a spatial pattern of local bandwidths. The method was applied to synthetic brain images, showing a high performance even in the presence of varying noise level and bias.

Equilibrium radionuclide angiography (ERNA) imaging of the heart is used to visualize and quantify the cardiac function. Phase image analysis has been used for the localization of several conduction and contraction abnormalities and has been proposed to evaluate cardiac resynchronization therapy. The ventricular contraction has been described with indices like mean, standard deviation, mode, synchrony and entropy with Fourier phase imaging (FoPI). Factorial phase imaging (FaPI) has been used for wall motion abnormalities analysis and on a cardiac phantom, but not for synchrony quantification. In this paper a comparison of several indices obtained with FoPI and FaPI for a normal population is presented. These indices were computed inside regions corresponding to left ventricle, right ventricle and the total ventricular area. A set of ERNA images from 23 normal volunteers was analyzed. The comparison of indices was carried out by paired Student's t test with a significance level of (p

The most frequently used imaging procedure for the diagnosis of diverse neurological illnesses is magnetic resonance. Improved benefits have been obtained from multi-spectral information under this imaging modality. Both supervised and unsupervised segmentation procedures have been reported for this kind of images, many of which require a preprocessing stage for contrast adjustment within the intensity space. This paper presents a fully automatic procedure for intensity space normalization of multi-spectral magnetic resonance image stacks based on the combination of the Karhunen-Loeve transformation and a maximum likelihood adjustment of the basis vectors' orientation as related to an underlying mixture model available for supervised segmentation. Results on three different test cases are presented, together with the Tanimoto indexes computed for segmented sets of images from each case. The average indexes obtained qualify the normalization procedure as an adequate alternative for multi-spectral magnetic resonance image preprocessing.

We present a discrete compactness (DC) index, together with a classification scheme, based both on the size and shape features extracted from brain volumes, to determine different aging stages: healthy controls (HC), mild cognitive impairment (MCI), and Alzheimer's disease (AD). A set of 30 brain magnetic resonance imaging (MRI) volumes for each group was segmented and two indices were measured for several structures: three-dimensional DC and normalized volumes (NVs). The discrimination power of these indices was determined by means of the area under the curve (AUC) of the receiver operating characteristic, where the proposed compactness index showed an average AUC of 0.7 for HC versus MCI comparison, 0.9 for HC versus AD separation, and 0.75 for MCI versus AD groups. In all cases, this index outperformed the discrimination capability of the NV. Using selected features from the set of DC and NV measures, three support vector machines were optimized and validated for the pairwise separation of the three classes. Our analysis shows classification rates of up to 98.3% between HC and AD, 85% between HC and MCI, and 93.3% for MCI and AD separation. These results outperform those reported in the literature and demonstrate the viability of the proposed morphological indices to classify different aging stages.

Brain computer interfaces (BCIs) translate brain activity into computer commands. To enhance the performance of a BCI, it is necessary to improve the feature extraction techniques being applied to decode the users' intentions. Objective comparison methods are needed to analyze different feature extraction techniques. One possibility is to use the classifier performance as a comparative measure. In this work the effect of several variables that affect the behaviour of linear discriminant analysis (LDA) has been studied when used to distinguish between electroencephalographic signals with and without the presence of event related potentials (ERPs). The error rate (ER) and the area under the receiver operating characteristic curve (AUC) were used as performance estimators of LDA. The results show that the number of characteristics, the degree of balance of the training patterns set and the number of averaged trials affect the classifier's performance and therefore, must be considered in the design of the integrated system.

Magnetic Resonance Imaging (MRI) is increasingly used for the diagnosis and monitoring of neurological disorders. In particular Diffusion-Weighted MRI (DWI) is highly sensitive in detecting early cerebral ischemic changes in acute stroke. Cerebral infarction lesion segmentation from DWI is accomplished in this work by applying nonparametric density estimation. The quality of the class boundaries is improved by including an edge confidence map, that is the confidence of truly being in the presence of a border between adjacent regions. The adjacency graph, that is constructed with the label regions, is analyzed and pruned to merge adjacent regions. The method was applied to real images, keeping all parameters constant throughout the process for each data set. The combination of region segmentation and edge detection proved to be a robust automatic technique of segmentation from DWI images of cerebral infarction regions in acute ischemic stroke. In a comparison with the reference infarct lesions segmentation, the automatic segmentation presented a significant correlation (r = 0.935), and an average Tanimoto index of 0.538.