Acute lymphoblastic leukemia (ALL) is a cancer that starts from the early version of white blood cells called lymphocytes in the bone marrow. It can spread to different parts of the body rapidly and if not treated, would probably be deadly within a couple of months. Leukemia cells are categorized into three types of L1, L2, and L3. The cancer is detected through screening of blood and bone marrow smears by pathologists. But manual examination of blood samples is a time-consuming and boring procedure as well as limited by human error risks. So to overcome these limitations a computer-aided detection system, capable of discriminating cancer from noncancer cases and identifying the cancerous cell subtypes, seems to be necessary. In this article an automatic detection method is proposed; first cell nucleus is segmented by fuzzy c-means clustering algorithm. Then a rich set of features including geometric, first- and second-order statistical features are obtained from the nucleus. A principal component analysis is used to reduce feature matrix dimensionality. Finally, an ensemble of SVM classifiers with different kernels and parameters is applied to classify cells into four groups, that is noncancerous, L1, L2, and L3. Results show that the proposed method can be used as an assistive diagnostic tool in laboratories.

Background:Tinnitus known as a central nervous system disorder is correlated with specific oscillatory activities within auditory and non-auditory brain areas. Several studies in the past few years have revealed that in the most tinnitus cases, the response pattern of neurons in auditory system is changed due to auditory deafferentation, which leads to variation and disruption of the brain networks.Objective: In this paper, we introduce an approach to automatically distinguish tinnitus individuals from healthy controls based on whole-brain functional connectivity and network analysis. Material and Methods:The functional connectivity analysis was applied to the resting state electroencephalographic (EEG) data of both groups using Weighted Phase Lag Index (WPLI) for various frequency bands in 2-44 Hz frequency range. In this case-control study, the classification was performed on graph theoretical measures using support vector machine (SVM) as a robust classification method.Results: Experimental results showed promising classification performance with a high accuracy, sensitivity, and specificity in all frequency bands, specifically in the beta2 frequency band. Conclusion:The current study provides substantial evidence that tinnitus network can be successfully detected by consistent measures of the brain networks based on EEG functional connectivity.

No abstract

Sparse component analysis (SCA) is a popular method for addressing underdetermined blind source separation (UBSS) in array signal processing applications. We are motivated by problems that arise in the applications where the sources are densely sparse (i.e. only a limited number of sources are inactive at each time instant). The separation performance of current underdetermined source recovery (USR) solutions, including the relaxation and greedy families, reduces with decreasing the mixing system dimension and increasing the sparsity level (k). In this paper, we present a k-SCA based algorithm that is suitable for USR in low dimensional mixing systems. Assuming the sources are at most (m − 1)-sparse where m is the number of mixtures, the proposed method is capable of recovering the sources from the mixtures given the mixing matrix using a subspace detection framework. Simulation results show that the proposed algorithm achieves better separation performance in k-SCA conditions compared with state of the art USR algorithms such as basis pursuit (BP), minimizing L1-norm (ML1), smoothed L0 (SL0), focal underdetermined system solve (FOCUSS) and orthogonal matching pursuit (OMP).

Event-Related Potentials (ERPs) have been used in addiction studies to evaluate cognitive performance and craving in individuals with Substance Use Dependence (SUD). This paper reviews studies that used ERPs to investigate cue reactivity, inhibitory control and error processing in SUDs. Five abused substances are included in the investigation, i.e. alcohol, nicotine, cannabis, cocaine, and methamphetamine. For each substance, the main recent findings related to the ERPs are specifically discussed, according to the latency of ERPs. The results show that individuals with SUDs allocate more attention resources to the cognitive processing of substance-related cues, indexed by increased amplitude of middle and late latency ERPs. Laboratory observations also show amplitude enlargement for early latency ERPs. SUDs reveal a deficiency in the inhibitory control and conscious error processing, indexed by attenuated N2 and Pe amplitude. The cognitive and motor inhibitory component (P3) changes show a controversial result. This study expands the findings of previous related reviews implying that substance abusers allocate more attentional resources to drug cues indexed by enlarged P3 and LPP amplitude. Regarding P3 elicited in inhibitory control tasks, there is not still convergent results, while N2 and Pe become attenuated as reported in previous reviews. The outcomes also show that the chance of relapse to substance abuse could be predicted by recording ERPs reflecting inhibitory control and error processing.