Showing papers in "Computers in Biology and Medicine in 2007"

TL;DR: The matched filter response to the detection of blood vessels is increased by proposing better filter parameters found by using an optimization procedure on 20 retina images of the DRIVE database.

TL;DR: An automatic technique for wheeze detection and monitoring using spectral analysis and the experimental and testing results justified the efficient performance and high noise robustness of the TF-WD.

TL;DR: In this study, a new approach based on an adaptive neuro-fuzzy inference system (ANFIS) was presented for epileptic seizure detection and a comparative analysis suggests that the proposed modeling approach outperforms ANN model in terms of training performances and classification accuracies.

TL;DR: The results imply that two combinations of all HRV measures, both of which include wavelet entropy measures, have the highest discrimination power in terms of sensitivity and specificity values.

TL;DR: This study aims at diagnosing breast cancer with a new hybrid machine learning method by hybridizing a fuzzy-artificial immune system with k-nearest neighbour algorithm and obtained a classification accuracy of 99.14%, which is the highest one reached so far.

TL;DR: Tests indicate that using curvelet-based texture features significantly improves the classification of normal tissues in CT scans, and the algorithms are extensively tested and results are compared with standard texture classification algorithms.

TL;DR: A decision support system that classifies the Doppler signals of the heart valve to two classes (normal and abnormal) is presented to support the cardiologist using least-squares support vector machine (LS-SVM) classifier instead of ANN.

TL;DR: The proposed algorithm for detection of suspicious masses from mammographic images was tested on a database of 61 mammograms on which masses had previously been marked by experienced radiologists and showed a sensitivity of 95.91%.

TL;DR: An integrated gene-search algorithm for genetic expression data analysis involves a genetic algorithm and correlation-based heuristics for data preprocessing and data mining for data mining and decision tree and support vector machines algorithms for making predictions.

TL;DR: Hptic functions that are added to a volume based surgical simulator to simulate the drilling process compute drilling forces and torques based on reliable metal removing theorem and can be obtained to provide effective surgery training and rehearsal.

TL;DR: Results suggest that the proposed method could help radiologists as a second reader in mammographic screening with a sensitivity of 88% and 94% at 1.02 false positives per image for lesion-based and case-based evaluation, respectively.

TL;DR: The between-subject agreement is sufficient to make the approach practical and male and older subjects were more likely to look in the same place than female and younger subjects, respectively.

TL;DR: This work describes a novel algorithm to identify laryngeal pathologies, by the digital analysis of the voice, based on Daubechies' discrete wavelet transform, linear prediction coefficients, and least squares support vector machines.

TL;DR: It is concluded that single ECG lead methods for estimating the respiratory signal are well correlated with inductance plethysmographs and single lead respiratory estimates can classify epochs of sleep disordered respiration with approximately 82% accuracy.

TL;DR: A computer-aided method for the quantitative and qualitative 3D analysis has been developed and applied and factors influencing the obtainable precision in the application of CAD/CAM techniques were taken into consideration.

TL;DR: It is suggested that observers see different things when looking at the samples in the microscope; a situation that significantly diminishes the performance of these classifiers in diagnosing such a disease.

TL;DR: This paper presents a wavelet-based cascaded adaptive filter (CAF) to remove the baseline wander of pulse waveform and demonstrates the power of CAF filter both in removing baseline wander and in preserving the diagnostic information of pulseWaveform.

TL;DR: The concepts for selecting a suitable wavelet basis and scales used in the process are developed and the analysis via the selected basis is without suffering time shift for decomposition and detection/elimination procedures after wavelet transformation.

TL;DR: From the results, it became clear that the size and location of cartilage defects drastically affect to those variables, which has important clinical implications regarding the long-term integrity of the cartilage adjacent to osteochondral defects.

TL;DR: Mass of experiments showed that the multispectral imaging techniques with spectral calibration method was proposed to acquire device-independent images, which is almost impossible in conventional color imaging method.

TL;DR: Embedded entropy feature, in comparison with energy, demonstrates a more efficient description of such pathological voices and provides a valuable tool for clinical diagnosis of unilateral laryngeal paralysis.

TL;DR: The proposed method automatically decomposes MUAPs and classifies them into normal, neuropathic or myopathic using a two-stage feature-based classifier using Radial Basis Function Artificial Neural Networks and decision trees.

TL;DR: Efference copy is a viable explanation of static position perception and sensorimotor interaction, but the rich, stable visual world is an illusion.

TL;DR: A feature selection procedure has been carried out on the basis of the feature discriminating power and of the linear correlations interplaying among them, and the comparison of the areas under the ROC curves obtained by varying the number of features to be classified has shown that 12 selected features are powerful enough to achieve the best classifier performances.

TL;DR: A fully automated approach for lumen and media-adventitia border detection is presented based on an active contour model, the initialization of which is performed via an analysis mechanism that takes advantage of the inherent morphologic characteristics of IVUS images.

TL;DR: Wavelet-based approaches for single-trial evoked potential estimation based on intracortical recordings outperform several existing methods including the Wiener filter, least mean square (LMS), and recursive least squares (RLS), and that the TI wavelet- based estimates have higher SNR and lower RMSE than the conventional wavelets.

TL;DR: A new fitting method for the additive model is outlined, which solves the problem of dependency of the parameter estimation on the assumption about the baseline excess hazard, and is directed to the R package relsurv that provides functions for easy and flexible fitting of all the commonly used relative survival regression models.

TL;DR: Surprising yet promising outcomes indicate that ERPs in response to novel sounds of oddball paradigm may be more reliable as a biomarker than the more commonly used responses to target sounds.

TL;DR: This study compares different systems based on the fuzzy C-means clustering algorithm for the detection of epileptic spikes in electroencephalogram (EEG) records and suggests that an FCM based two-stage system should be preferred as the spike detection system.

TL;DR: The proposed analysis scheme combines flexible long-term graphical representation tools, while maintaining the ability of quick browsing via visualization and auralization of the detected short-term events, allowing for enhanced content manipulation and analysis.