Biomedical Engineering: Applications, Basis and Communications

Active contour model (ACM) algorithm is an effective and accurate method to segment out the regions of interest (ROIs) and has been widely used in many clinical imaging systems. In addition to segmenting out the lesion contour, how to accurately quantify the area/volume of the lesion is also important and challenging. Some quantification methods performed manually are time-consuming. To increase the accuracy and efficiency in quantifying the ACM segmented regions, a simple, straightforward, accurate and efficient automatic region quantification method with edge-linking and region-filling algorithm (ERA) for the ACM segmented regions was developed. Three types of computer simulated images, namely closed contour simulated images (CCSIs), discrete contour simulated images (DCSIs) and intact region simulated images (IRSIs) were created to evaluate the accuracy of the region-filling process, edge-linking process and ERA after ACM image segmentation process, respectively. Furthermore, the results of ERA were compared with those of the direct subtraction method (DSM). The ERA was also applied to quantify the area/volume of an irregularly-shaped lymphoma in a MR brain image. The results showed that the average percentage errors on the region-filling process, edge-linking process and ERA (0%, 0.03% and 7.52%, respectively) were significantly lower than those of DSM (15.85%, 15.08% and 20.36%, respectively) in quantifying the ROIs. The application of ERA to quantify the area/volume of an irregularly-shaped lymphoma in a MR brain image was successfully demonstrated. In conclusions, ERA outperforms the DSM in quantifying the area/volume of ACM segmented regions and might increase the efficiency and accuracy in clinical diagnosis and treatment.

Physiological reflection of emotions can be tracked by autonomic signals. Several studies have been conducted using autonomic signal processing to examine men and women differences during the exposure of affective stimuli. Emotional pictures and music are two commonly used methods to induce affects in an experimental setup. The biological changes have been commonly monitored during a certain emotional inducement protocol, solely. This study was aimed to examine two induction paradigms involved auditory and visual cues using nonlinear dynamical approaches. To this end, various nonlinear parameters of galvanic skin response (GSR) and pulse signals of men and women were examined. The nonlinear analysis was performed using lagged Poincare parameters, detrended fluctuation indices (DFAs), Lyapunov exponents (LEs), some entropy measures, and recurrence quantification analysis (RQA). The Wilcoxon rank sum test was used to show significant differences between the groups. The results indicate that besides the type of affect induction, physiological differences of men and women are notable in negative emotions (sadness and fear). Regardless to the inducements, lagged Poincare parameters of the pulse signals and DFA indices of the GSR have shown significant differences in gender affective responses. However, applying pictorial stimuli, LEs are appropriate indicators for gender discrimination. It is also concluded that GSR dynamics are intensely affected by the kind of stimuli; while this is not validated for the pulse. These findings suggest that different emotional inductions evoked different autonomic responses in men and women, which can be appropriately monitored using nonlinear signal processing approaches.

Image segmentation is often required as a fundamental stage in medical image processing, particularly during the clinical analysis of magnetic resonance (MR) brain images. Fuzzy c-means (FCM) clustering algorithm is one of the best known and widely used segmentation methods, but this algorithm has some problem for segmenting simulated MRI images to high number of clusters with different noise levels and real images because of spatial complexities. Anatomical segmentation usually requires information derived from the manual segmentations done by experts, prior knowledge can be useful to modify image segmentation methods. In this paper, we propose some methods to modify FCM algorithm using expert manual segmentation as prior knowledge. We developed combination of FCM algorithm and prior knowledge in three ways, in order to improve segmentation of brain MR images with high noise level and spatial complexity. In real images, we had a considerable improvement in similarity index of three classes (white matter, gray matter, CSF) and in simulated images with different noise levels evaluation criteria of white matter and gray matter has improved.

Deep brain stimulation (DBS) is one of the most effective neurosurgical procedures to reduce Parkinsons tremor. The conventional method of DBS is open loop stimulation of one area of basal ganglia (BG). On the other hand, existing feedback causes the reduction of additional stimulatory signal delivered to the brain which results in the reduction of the side effects caused by the excessive stimulation intensity. Actually, the stimulatory intensity of the controllers is reduced proportionally by the reduction of hands tremor, which is in fact the intended rehabilitation of the disease. The meaningful objective of this study is to design an architecture of controllers to decrease three criteria. The first one is the hand’s tremor, the second one is the level of delivered stimulation signal to brain in disease condition and the third one is the ratio of the level of delivered stimulation signal in health condition to disease condition. In order to achieve these objectives, a new architecture of a closed loop control system to stimulate two areas of BG at the same time is presented. One area (STN: subthalamic nucleus) is stimulated with a state feedback (SF) controller (pole placement method) and the other area (GPi: globus pallidus internal) is stimulated with a partial state feedback controller (PSFC). Considering these criteria, the results illustrate that stimulating two areas leads to a suitable performance. Simulation results show that the PSF and SF controllers are robust enough to the variations of the system parameters. Moreover, we are able to estimate the parameters of BG model in real time; it is a valuable method to update the time variable parameters of this model.

To explore the genetic complexity of disease, this paper focuses on the prioritization of susceptibility genes by re-ranking. This approach prioritizes disease-related genes based on the prior ranking. The genes in prior ranking are divided into seeds and candidates. And then these seed genes are used to prioritize candidates based on association rules. Experimental results show the approach is promising for finding new disease-related genes.

Three dimensional (3D) voxel phantoms are numerical representations of human bodies, used by physicians in very different contexts. In the controlled context of hospitals, where from 2 to 10 subjects may arrive per day, phantoms are used to verify computations before therapeutic exposure to radiation of cancerous tumors. In addition, 3D phantoms are used to diagnose the gravity of accidental exposure to radiation. In such cases, there may be from 10 to more than 1000 subjects to be diagnosed simultaneously. In all of these cases, computation accuracy depends on a single such representation. In this paper, we present EquiVox which is a tool composed of several distributed functions and enables to create, as quickly and as accurately as possible, 3D numerical phantoms that fit anyone, whatever the context. It is based on a multi-agent system. Agents are convenient for this kind of structure, they can interact together and they may have individual capacities. In EquiVox, the phantoms adaptation is a key phase based on artificial neural network (ANN) interpolations. Thus, ANNs must be trained regularly in order to take into account newly capitalized subjects and to increase interpolation accuracy. However, ANN training is a time-consuming process. Consequently, we have built Equivox to optimize this process. Thus, in this paper, we present our architecture, based on agents and ANN, and we put the stress on the adaptation module. We propose, next, some experimentations in order to show the efficiency of the EquiVox architecture.

Wireless capsule endoscopy (WCE) has been proven to be a robust technology which is able to ease diagnosing the GI tract diseases. It can be seen that a better computational algorithm is needed to analyze WCE images. Ulcer is one of the several diseases which are diagnosed using these images. Non-uniform lighting can complicate the detection process because it can change the color of tissue and make it seem darker or lighter than usual. This change of color makes the detection harder as the main feature of detecting ulcer as the color of the tissue. In this research work, adapted bit-planes are used to detect useful areas in images and then two sets of features, bit-plane probability and wavelet-based features, were extracted from the detected areas and used to classify them. Experimental results demonstrate a promising ground for further analysis of the channel-based bit-plane data and wavelet-based features.

In this research, classification of the 18 reaching movements was done in 3D space using the elbow flexion/extension angle and the upper arm acceleration. For this, a hierarchical structure was proposed where the approximate region of the movements was determined at high level and then, motion types were recognized exactly at low level. To evaluate this hierarchical structure, the flat classifiers were implemented with the same features. The hierarchical classifier improves the formation of the decision boundaries better than the flat classifiers due to its proper structure. It improves the discrimination of the within-group members by applying an algorithm to increase the ratio of the between-class covariance matrix trace to the within-class covariance matrix trace. It also benefits from low dimensional feature space. Recognition accuracy was higher than the flat classifiers. In other evaluation metrics (Recall, Precision and F-score), this structure indicated better performance, especially in those classes with the least recognition percentage.