Survival Analysis in Cognitively Normal Subjects and in Patients with Mild Cognitive Impairment Using a Proportional Hazards Model with Extreme Gradient Boosting Regression.

BACKGROUND: Evaluating the risk of Alzheimer's disease (AD) in cognitively normal (CN) and patients with mild cognitive impairment (MCI) is extremely important. While MCI-to-AD progression risk has been studied extensively, few studies estimate CN-to-MCI conversion risk. The Cox proportional hazards (PH), a widely used survival analysis model, assumes a linear predictor-risk relationship. Generalizing the PH model to more complex predictor-risk relationships may increase risk estimation accuracy. OBJECTIVE: The aim of this study was to develop a PH model using an Xgboost regressor, based on demographic, genetic, neuropsychiatric, and neuroimaging predictors to estimate risk of AD in patients with MCI, and the risk of MCI in CN subjects. METHODS: We replaced the Cox PH linear model with an Xgboost regressor to capture complex interactions between predictors, and non-linear predictor-risk associations. We endeavored to limit model inputs to noninvasive and more widely available predictors in order to facilitate future applicability in a wider setting. RESULTS: In MCI-to-AD (n = 882), the Xgboost model achieved a concordance index (C-index) of 84.5%. When the model was used for MCI risk prediction in CN (n = 100) individuals, the C-index was 73.3%. In both applications, the C-index was statistically significantly higher in the Xgboost in comparison to the Cox PH model. CONCLUSION: Using non-linear regressors such as Xgboost improves AD dementia risk assessment in CN and MCI. It is possible to achieve reasonable risk stratification using predictors that are relatively low-cost in terms of time, invasiveness, and availability. Future strategies for improving AD dementia risk estimation are discussed.

Multiple-target tracking in human and machine vision.

Humans are able to track multiple objects at any given time in their daily activities-for example, we can drive a car while monitoring obstacles, pedestrians, and other vehicles. Several past studies have examined how humans track targets simultaneously and what underlying behavioral and neural mechanisms they use. At the same time, computer-vision researchers have proposed different algorithms to track multiple targets automatically. These algorithms are useful for video surveillance, team-sport analysis, video analysis, video summarization, and human-computer interaction. Although there are several efficient biologically inspired algorithms in artificial intelligence, the human multiple-target tracking (MTT) ability is rarely imitated in computer-vision algorithms. In this paper, we review MTT studies in neuroscience and biologically inspired MTT methods in computer vision and discuss the ways in which they can be seen as complementary.

Early Visual Processing of Feature Saliency Tasks: A Review of Psychophysical Experiments.

The visual system is constantly bombarded with information originating from the outside world, but it is unable to process all the received information at any given time. In fact, the most salient parts of the visual scene are chosen to be processed involuntarily and immediately after the first glance along with endogenous signals in the brain. Vision scientists have shown that the early visual system, from retina to lateral geniculate nucleus (LGN) and then primary visual cortex, selectively processes the low-level features of the visual scene. Everything we perceive from the visual scene is based on these feature properties and their subsequent combination in higher visual areas. Different experiments have been designed to investigate the impact of these features on saliency and understand the relative visual mechanisms. In this paper, we review the psychophysical experiments which have been published in the last decades to indicate how the low-level salient features are processed in the early visual cortex and extract the most important and basic information of the visual scene. Important and open questions are discussed in this review as well and one might pursue these questions to investigate the impact of higher level features on saliency in complex scenes or natural images.

A unified methodology based on sparse field level sets and boosting algorithms for false positives reduction in lung nodules detection.

PURPOSE: This work aims to develop a unified methodology for the false positives reduction in lung nodules computer-aided detection schemes. METHODS: The 3D region of each detected nodule candidate is first reconstructed using the sparse field method for accurately segmenting the objects. This technique enhances the level set modeling by restricting the computations to a narrow band near the evolving curve. Then, a set of 2D and 3D relevant features are extracted for each segmented candidate. Subsequently, a hybrid undersampling/boosting algorithm called RUSBoost is applied to analyze the features and discriminate real nodules from non-nodules. RESULTS: The performance of the proposed scheme was evaluated by using 70 CT images, randomly selected from the Lung Image Database Consortium and containing 198 nodules. Applying RUSBoost classifier exhibited a better performance than some commonly used classifiers. It effectively reduced the average number of FPs to only 3.9 per scan based on a fivefold cross-validation. CONCLUSION: The practical implementation, applicability for different nodule types and adaptability in handling the imbalanced data classification insure the improvement in lung nodules detection by utilizing this new approach.

Temporal resolvability analysis of macroscopic morphological development in neonatal cerebral magnetic resonance images.

OBJECTIVES: Reliable gradation of neonatal brain development is important for clinical investigation of neurological disorders. A prerequisite for such quantification of development is knowledge about temporal resolvability. METHODS: We hypothesized 2-week interval as the temporal resolvability of age-related templates to study macroscopic morphological brain development in the early weeks after birth. Therefore, we constructed two templates for the gestational age (GA) ranges of 39 to 40 and 41 to 42 weeks using T1-weighted magnetic resonance (MR) images. Then, we compared the spatial variation of anatomical landmarks and the average and the maximal length of spatial deformation in 30 subjects normalized to the two templates along x, y, and z directions. RESULTS: Multivariate analysis of variance (MANOVA) revealed significant difference between spatial variations of the above macroscopic features in the two age ranges. Furthermore, quantitative analysis of feature scattering yielded the same result even in features for which the null hypothesis was not rejected by MANOVA. Moreover, the same procedure was reiterated on two sets of subjects with the closer age range of 1 week (40 and 41 week's GA) and no significant difference could be detected. CONCLUSIONS: The results strengthen the hypothesis that 2-week is the temporal resolvability of age-related templates for macroscopic morphological studies of the developing brain in the early weeks after birth.

Experimental investigation of NIRS spatial sensitivity.

Near infrared spectroscopy (NIRS) is regarded as a potential medical diagnostic technique for investigation of hemodynamic changes. However, uncertainties pertaining to the origin of NIRS signals have hampered its clinical interpretation. The uncertainities in NIRS measurements especially in case of living tissues are due to lack of rigorous combined theoretical-experimental studies resulting in clear understanding of the origin of NIRS signals. For their reliable interpretation it is important to understand the relationship between spatial changes in optical properties and corresponding changes in the NIRS signal. We investigated spatial sensitivity of near infrared optical measurements using an experimental approach. It uses a liquid optical phantom as tissue equivalent, which is explored under robot-control by a small, approximately point like perturbation of desired optical properties, and a NIRS instrument for trans-illumination/reflection measurements. The experimentally obtained sensitivity has been analyzed and compared with numerical simulations. In preliminary experiments we investigated the influence of various optical properties of the medium and of source/detector distances on the spatial sensitivity distribution. The acquired sensitivity maps can be used to define characteristic parameters. As an example, we used a 25% threshold to define a penetration depth measure which provides values in good accordance with published ones. To the best of our knowledge this is the first experimental study of NIRS spatial sensitivity. The presented method will allow in depth experimental investigation of the influence of various conditions pertaining to medium such as optical properties of tissue (scattering and absorption) and of the source/detector configuration.

Design and construction of a brain phantom to simulate neonatal MR images.

This paper presents the design and construction of a 3D digital neonatal neurocranial phantom and its application for the simulation of brain magnetic resonance (MR) images. Commonly used digital brain phantoms (e.g. BrainWeb) are based on the adult brain. With the growing interest in computer-aided methods for neonatal MR image processing, there is a growing demand a digital phantom and brain MR image simulator especially for the neonatal brains. This is due to the pronounced differences between adult and neonatal brains not only in terms of size but also, more importantly, in terms of geometrical proportions and the need to subdivide white matter into two different tissue types in neonates. Therefore the neonatal brain phantom created in the here presented work consists of 9 different tissue types: skin, fat, muscle, skull, dura mater, gray matter, myelinated white matter, nonmyelinated white matter and cerebrospinal fluid. Each voxel has a vector consisting of 9 components, one for each of these nine tissue types. This digital phantom can be used to map simulated magnetic resonance signal intensities resulting in simulated MR images of the newborns head. These images with controlled degradation of the image data present a representative, reproducible data set ideal for development and evaluation of neonatal MRI analysis methods, e.g. segmentation and registration algorithms.

Detection of EEG transients in neonates and older children using a system based on dynamic time-warping template matching and spatial dipole clustering.

We present a novel system for detecting electroencephalographic transient events in neonates and older children. The detection system consists of three major elements: (i) a preprocessing stage for filtering EEG and detecting artifacts, (ii) a hierarchical course-to-fine temporal event detection stage and (iii) a hierarchical course-to-fine spatial event selection stage to incorporate spatial contextual information for rejection of spurious events. The output consists of homogeneous EEG events and their corresponding dipole clusters. The system was evaluated on EEG signals recorded in four neonates and six older children. There was a high degree of correlation between system-detected and expert-marked events for all patients. Mean sensitivities of 84.9% and 91.9% and mean selectivities of 86.3% and 90.6% were obtained for the neonates and the older children, respectively. This tool is appropriate for the detection and selection of homogeneous EEG events prior to source localization. Quantitative spatial analysis of dipoles may facilitate the physician's assessment of patients' brain dysfunction.

A novel constructive-optimizer neural network for the traveling salesman problem.

In this paper, a novel constructive-optimizer neural network (CONN) is proposed for the traveling salesman problem (TSP). CONN uses a feedback structure similar to Hopfield-type neural networks and a competitive training algorithm similar to the Kohonen-type self-organizing maps (K-SOMs). Consequently, CONN is composed of a constructive part, which grows the tour and an optimizer part to optimize it. In the training algorithm, an initial tour is created first and introduced to CONN. Then, it is trained in the constructive phase for adding a number of cities to the tour. Next, the training algorithm switches to the optimizer phase for optimizing the current tour by displacing the tour cities. After convergence in this phase, the training algorithm switches to the constructive phase anew and is continued until all cities are added to the tour. Furthermore, we investigate a relationship between the number of TSP cities and the number of cities to be added in each constructive phase. CONN was tested on nine sets of benchmark TSPs from TSPLIB to demonstrate its performance and efficiency. It performed better than several typical Neural networks (NNs), including KNIES_TSP_Local, KNIES_TSP_Global, Budinich's SOM, Co-Adaptive Net, and multivalued Hopfield network as wall as computationally comparable variants of the simulated annealing algorithm, in terms of both CPU time and accuracy. Furthermore, CONN converged considerably faster than expanding SOM and evolved integrated SOM and generated shorter tours compared to KNIES_DECOMPOSE. Although CONN is not yet comparable in terms of accuracy with some sophisticated computationally intensive algorithms, it converges significantly faster than they do. Generally speaking, CONN provides the best compromise between CPU time and accuracy among currently reported NNs for TSP.

A neonatal atlas template for spatial normalization of whole-brain magnetic resonance images of newborns: preliminary results.

Commonly used brain templates are based on adults' or children's brains. In this study, we create a neonatal brain template. This becomes necessary because of the pronounced differences not only in size but even more importantly in geometrical proportions of the brains of adults and children as compared to the ones of newborns. The template is created based on high resolution T1 magnetic resonance images of 7 individuals with gestational ages between 39 and 42 weeks at the dates of examination. As usual, the created template presents two characteristics in a single image: an average intensity and an average shape. The normalization process to map subjects to the same space is done using SPM2 (Statistical Parametric Mapping) and its deformation toolbox. It consists of two steps: an affine and a nonlinear registration for global and local alignments, respectively. The template was evaluated by (i) study of anatomical local deviations and (ii) amount of local deformations of brain tissues in normalized neonatal images. The extracted results were compared with the ones obtained by normalization using adult and pediatric templates. It was shown that the application of our neonatal brain template for alignment of neonatal images results in a pronounced increase in performance of the normalization procedure as indicated by reduction of deviation of anatomical equivalent structures. The neonatal atlas template is freely downloadable from http://www.u-picardie.fr/labo/GRAMFC.

A novel evolutionary approach for optimizing content-based image indexing algorithms.

Optimization of content-based image indexing and retrieval (CBIR) algorithms is a complicated and time-consuming task since each time a parameter of the indexing algorithm is changed, all images in the database should be indexed again. In this paper, a novel evolutionary method called evolutionary group algorithm (EGA) is proposed for complicated time-consuming optimization problems such as finding optimal parameters of content-based image indexing algorithms. In the new evolutionary algorithm, the image database is partitioned into several smaller subsets, and each subset is used by an updating process as training patterns for each chromosome during evolution. This is in contrast to genetic algorithms that use the whole database as training patterns for evolution. Additionally, for each chromosome, a parameter called age is defined that implies the progress of the updating process. Similarly, the genes of the proposed chromosomes are divided into two categories: evolutionary genes that participate to evolution and history genes that save previous states of the updating process. Furthermore, a new fitness function is defined which evaluates the fitness of the chromosomes of the current population with different ages in each generation. We used EGA to optimize the quantization thresholds of the wavelet-correlogram algorithm for CBIR. The optimal quantization thresholds computed by EGA improved significantly all the evaluation measures including average precision, average weighted precision, average recall, and average rank for the wavelet-correlogram method.