Genetic algorithm-based initial contour optimization for skin lesion border detection

Multimedia Tools and Applications - Automated segmentation has an essential role in detecting several diseases, such as skin lesions. In segmentation, the active contour (AC) is an efficient method...     

Clump splitting via bottleneck detection and shape classification

Under-segmentation of an image with multiple objects is a common problem in image segmentation algorithms. This paper presents a novel approach for splitting clumps formed by multiple objects due to under-segmentation. The proposed algorithm includes three steps: (1) decide whether to split a candidate connected component by application-specific shape classification; (2) find a pair of points for clump splitting and (3) join the pair of selected points. In the first step, a shape classifier is applied to determine whether a connected component should be split. In the second step, a pair of points for splitting is detected using a bottleneck rule, under the assumption that the desired objects have roughly a convex shape. In the third step, the selected splitting points from step two are joined by finding the optimal splitting line between them, based on minimizing an image energy. The shape classifier is built offline via various shape features and a support vector machine. Steps two and three are application-independent. The performance of this method is evaluated using images from various applications. Experimental results show that the proposed approach outperforms the state-of-the-art algorithms for the clump splitting problem.     

Morphological segmenting and neighborhood pixel-based locality preserving projection on brain fMRI dataset for semantic feature extraction: an affective computing study

Two specific chemical receptive fields of brain, namely the amygdala and the orbital-frontal cortex, are related to valence and arousal in medical experiments. Functional magnetic resonance imaging (fMRI), which is a noninvasive, repeatable, and atomical tool for medical imaging in clinic system, was widely used in affective computing; however, it faces its dataset processing difficulty for dimensional reduction as well as for decreasing the computational complexity. In addition, features extraction from those de-dimensionality datasets is a challenging issue. The current work solved the de-dimensionality issue by using some preprocessing algorithms including clustering, morphological segmenting, and locality preserving projection. In order to keep useful information in fMRI dataset for reduction process, improved neighborhood pixel-based locality preserving projection (NP-LPP) algorithm was addressed and continuously for feature extraction operating using Otsu weighted sum of histogram. Furthermore, a modified covariance power spectral density (MC-PSD) separately in an fMRI Valence–Arousal experiments was measured. The results were analyzed and compared with affective norms English words system. The experiments established that the proposed methods of NP-LPP effectively simplified high complexity of fMRI, and Otsu weighted sum of histogram exhibited superior performance for features extraction compared to the MC-PSD through the calculation root mean standard error. The current proposed method provided a potential application and promising research direction on human semantic retrieval through medical imaging dataset.

     

Bisnaphthalimidopropyl Derivatives as Inhibitors of Leishmania SIR2 Related Protein 1

The NAD⁺‐dependent deacetylases, namely sirtuins, are involved in the regulation of a variety of biological processes such as gene silencing, DNA repair, longevity, metabolism, apoptosis, and development. An enzyme from the parasite Leishmania infantum that belongs to this family, LiSIR2RP1, is a NAD⁺‐dependent tubulin deacetylase and an ADP‐ribosyltransferase. This enzyme's involvement in L. infantum virulence and survival underscores its potential as a drug target. Our search for selective inhibitors of LiSIR2RP1 has led, for the first time, to the identification of the antiparasitic and anticancer bisnaphthalimidopropyl (BNIP) alkyl di‐ and triamines (IC₅₀ values in the single‐digit micromolar range for the most potent compounds). Structure–activity studies were conducted with 12 BNIP derivatives that differ in the length of the central alkyl chain, which links the two naphthalimidopropyl moieties. The most active and selective compound is the BNIP diaminononane (BNIPDanon), with IC₅₀ values of 5.7 and 97.4 μM against the parasite and human forms (SIRT1) of the enzyme, respectively. Furthermore, this compound is an NAD⁺‐competitive inhibitor that interacts differently with the parasite and human enzymes, as determined by docking analysis, which might explain its selectivity toward the parasitic enzyme.     

Effects of Lewis number on flame surface density transport in turbulent premixed combustion

The transport of flame surface density (FSD) in turbulent premixed flames has been studied using a database obtained from Direct Numerical Simulation (DNS). Three-dimensional freely propagating developing statistically planar turbulent premixed flames have been examined over a range of global Lewis numbers from 0.6 to 1.2. Simplified chemistry has been used and the emphasis is on the effects of Lewis number on FSD transport in the context of Reynolds-averaged closure modelling. Under the same initial conditions of turbulence, flames with low Lewis numbers are found to exhibit counter-gradient transport of FSD, whereas flames with higher Lewis numbers tend to exhibit gradient transport of FSD. Stronger heat release effects for lower Lewis number flames are found to lead to an increase in the positive (negative) value of the dilatation rate (normal strain rate) term in the FSD transport equation with decreasing Lewis number. The contribution of flame curvature to FSD transport is found to be influenced significantly by the effects of Lewis number on the curvature dependence of the magnitude of the reaction progress variable gradient, and on the combined reaction and normal diffusion components of displacement speed. The modelling of the various terms of the FSD transport equation has been analysed in detail and the performance of existing models is assessed with respect to the terms assembled from corresponding quantities extracted from DNS data. Based on this assessment, suitable models are identified which are able to address the effects of non-unity Lewis number on FSD transport, and new or modified models are suggested wherever necessary.     

Motion gradient vector flow: an external force for tracking rolling leukocytes with shape and size constrained active contours

Recording rolling leukocyte velocities from intravital microscopic video imagery is a critical task in inflammation research and drug validation. Since manual tracking is excessively time consuming, an automated method is desired. This paper illustrates an active contour based automated tracking method, where we propose a novel external force to guide the active contour that takes the hemodynamic flow direction into account. The construction of the proposed force field, referred to as motion gradient vector flow (MGVF), is accomplished by minimizing an energy functional involving the motion direction, and the image gradient magnitude. The tracking experiments demonstrate that MGVF can be used to track both slow- and fast-rolling leukocytes, thus extending the capture range of previously designed cell tracking techniques.     

Exploiting wheel slips of mobile robots to improve navigation performance

Improving navigation performance of autonomous wheeled mobile robot (WMR) in a dynamic unstructured environment requires improved maneuverability. In such cases, the dynamics of wheel slip may violate the ideal no-slip kinematic constraints generally used to model nonholonomic WMR. In this paper, a new method is proposed to tackle the modeling inadequacy that arises when slip is neglected by including both longitudinal and lateral slip dynamics into the overall dynamics of the WMR. This new model of the WMR provides a realistic simulation environment that can be utilized to develop model-based controllers to improve WMR navigation. In this paper, a dynamic planner with a path-following controller is designed to allow the WMR to navigate efficiently by autonomously regulating the generated traction force due to wheel slip. Extensive simulation results demonstrate the importance of the proposed modeling technique to capture slip phenomenon and the efficacy of the presented control technique to exploit such slip for better navigation performance.     

Texture anisotropy technique in brain degenerative diseases

Structural alterations anisotropy-based measured for different areas for the most common types of dementia diseases could be a biomarker of brain impairment. The current work aims to assess whether texture anisotropy can discriminate both healthy versus Alzheimer’s and Pick’s patients based on regional evaluation while maintaining high predictive power. The investigated area is reduced from the whole-brain surface to three major lobes (i.e., frontal, temporal and parietal). A predictive model was proposed to associate a disease with a specific area in the brain based on the anisotropy values. Simultaneous analysis of 1680 measurements from 105 brain magnetic resonance images acquired as T2w and PD sequences was performed to establish the significance of the model. The cerebral calcinosis disease has been used as artificial ground truth. The association based on textural anisotropy between targeted diseases and control patients was performed by using Pearson’s correlation coefficients. A new proposed consistency index investigated the texture anisotropy relevance for all image’s types and all analyzed classes and regions. The validation study is based on area under the receiver-operating characteristic curve that depicted the overall diagnostic performance of the texture anisotropy in each region. The proposed model demonstrated that texture anisotropy is accurate solution in diagnosis of Alzheimer’s and Pick’s diseases when the investigated area is reduced to major lobes, with sensitivity >90% and specificity >80%.