Search

Background: Wearable sensors offer the potential to bring new knowledge to inform interventions in patients affected by multiple sclerosis (MS) by thoroughly quantifying gait characteristics and gait deficits from prolonged daily living measurements. The aim of this study was to characterise gait in both laboratory and daily life conditions for a group of patients with moderate to severe ambulatory impairment due to MS. To this purpose, algorithms to detect and characterise gait from wearable inertial sensors data were also validated. Methods: Fourteen patients with MS were divided into two groups according to their disability level (EDSS 6.5–6.0 and EDSS 5.5–5.0, respectively). They performed both intermittent and continuous walking bouts (WBs) in a gait laboratory wearing waist and shank mounted inertial sensors. An algorithm (W-CWT) to estimate gait events and temporal parameters (mean and variability values) using data recorded from the waist mounted sensor (Dynaport, Mc Roberts) was tested against a reference algorithm (S-REF) based on the shank-worn sensors (OPAL, APDM). Subsequently, the accuracy of another algorithm (W-PAM) to detect and classify WBs was also tested. The validated algorithms were then used to quantify gait characteristics during short (sWB, 5–50 steps), intermediate (iWB, 51–100 steps) and long (lWB, >100 steps) daily living WBs and laboratory walking. Group means were compared using a two-way ANOVA. Results: W-CWT compared to S-REF showed good gait event accuracy (0.05–0.10 s absolute error) and was not influenced by disability level. It slightly overestimated stride time in intermittent walking (0.012 s) and overestimated highly variability of temporal parameters in both intermittent (17.5%–58.2%) and continuous walking (11.2%–76.7%). The accuracy of W-PAM was speed-dependent and decreased with increasing disability. The ANOVA analysis showed that patients walked at a slower pace in daily living than in the laboratory. In daily living gait, all mean temporal parameters decreased as the WB duration increased. In the sWB, the patients with a lower disability score showed, on average, lower values of the temporal parameters. Variability decreased as the WB duration increased. Conclusions: This study validated a method to quantify walking in real life in people with MS and showed how gait characteristics estimated from short walking bouts during daily living may be the most informative to quantify level of disability and effects of interventions in patients moderately affected by MS. The study provides a robust approach for the quantification of recognised clinically relevant outcomes and an innovative perspective in the study of real life walking. [ABSTRACT FROM AUTHOR]

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble’s output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) − k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer’s disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases. [ABSTRACT FROM AUTHOR]

Purpose: The aim of this study was to develop a robust post-processing workflow for motion-corrupted datasets in diffusion kurtosis imaging (DKI). Materials and methods: The proposed workflow consisted of brain extraction, rigid registration, distortion correction, artifacts rejection, spatial smoothing and tensor estimation. Rigid registration was utilized to correct misalignments. Motion artifacts were rejected by using local Pearson correlation coefficient (LPCC). The performance of LPCC in characterizing relative differences between artifacts and artifact-free images was compared with that of the conventional correlation coefficient in 10 randomly selected DKI datasets. The influence of rejected artifacts with information of gradient directions and b values for the parameter estimation was investigated by using mean square error (MSE). The variance of noise was used as the criterion for MSEs. The clinical practicality of the proposed workflow was evaluated by the image quality and measurements in regions of interest on 36 DKI datasets, including 18 artifact-free (18 pediatric subjects) and 18 motion-corrupted datasets (15 pediatric subjects and 3 essential tremor patients). Results: The relative difference between artifacts and artifact-free images calculated by LPCC was larger than that of the conventional correlation coefficient (p<0.05). It indicated that LPCC was more sensitive in detecting motion artifacts. MSEs of all derived parameters from the reserved data after the artifacts rejection were smaller than the variance of the noise. It suggested that influence of rejected artifacts was less than influence of noise on the precision of derived parameters. The proposed workflow improved the image quality and reduced the measurement biases significantly on motion-corrupted datasets (p<0.05). Conclusion: The proposed post-processing workflow was reliable to improve the image quality and the measurement precision of the derived parameters on motion-corrupted DKI datasets. The workflow provided an effective post-processing method for clinical applications of DKI in subjects with involuntary movements. [ABSTRACT FROM AUTHOR]

Diffusion kurtosis imaging (DKI) is a promising extension of diffusion tensor imaging, giving new insights into the white matter microstructure and providing new biomarkers. Given the rapidly increasing number of studies, DKI has a potential to establish itself as a valuable tool in brain diagnostics. However, to become a routine procedure, DKI still needs to be improved in terms of robustness, reliability, and reproducibility. As it requires acquisitions at higher diffusion weightings, results are more affected by noise than in diffusion tensor imaging. The lack of standard procedures for post-processing, especially for noise correction, might become a significant obstacle for the use of DKI in clinical routine limiting its application. We considered two noise correction schemes accounting for the noise properties of multichannel phased-array coils, in order to improve the data quality at signal-to-noise ratio (SNR) typical for DKI. The SNR dependence of estimated DKI metrics such as mean kurtosis (MK), mean diffusivity (MD) and fractional anisotropy (FA) is investigated for these noise correction approaches in Monte Carlo simulations and in in vivo human studies. The intra-subject reproducibility is investigated in a single subject study by varying the SNR level and SNR spatial distribution. Then the impact of the noise correction on inter-subject variability is evaluated in a homogeneous sample of 25 healthy volunteers. Results show a strong impact of noise correction on the MK estimate, while the estimation of FA and MD was affected to a lesser extent. Both intra- and inter-subject SNR-related variability of the MK estimate is considerably reduced after correction for the noise bias, providing more accurate and reproducible measures. In this work, we have proposed a straightforward method that improves accuracy of DKI metrics. This should contribute to standardization of DKI applications in clinical studies making valuable inferences in group analysis and longitudinal studies. [ABSTRACT FROM AUTHOR]

High quality segmentation of diffusion tensor images (DTI) is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework. [ABSTRACT FROM AUTHOR]