Multi Texture Analysis of Colorectal Cancer Continuum Using Multispectral Imagery

Purpose

This paper proposes to characterize the continuum of colorectal cancer (CRC) using multiple texture features extracted from multispectral optical microscopy images. Three types of pathological tissues (PT) are considered: benign hyperplasia, intraepithelial neoplasia and carcinoma.

Materials and Methods

In the proposed approach, the region of interest containing PT is first extracted from multispectral images using active contour segmentation. This region is then encoded using texture features based on the Laplacian-of-Gaussian (LoG) filter, discrete wavelets (DW) and gray level co-occurrence matrices (GLCM). To assess the significance of textural differences between PT types, a statistical analysis based on the Kruskal-Wallis test is performed. The usefulness of texture features is then evaluated quantitatively in terms of their ability to predict PT types using various classifier models.

Results

Preliminary results show significant texture differences between PT types, for all texture features (p-value < 0.01). Individually, GLCM texture features outperform LoG and DW features in terms of PT type prediction. However, a higher performance can be achieved by combining all texture features, resulting in a mean classification accuracy of 98.92%, sensitivity of 98.12%, and specificity of 99.67%.

Conclusions

These results demonstrate the efficiency and effectiveness of combining multiple texture features for characterizing the continuum of CRC and discriminating between pathological tissues in multispectral images.     

Inertia weight control strategies for particle swarm optimization

Particle swarm optimization (PSO) is a population-based, stochastic optimization technique inspired by the social dynamics of birds. The PSO algorithm is rather sensitive to the control parameters, and thus, there has been a significant amount of research effort devoted to the dynamic adaptation of these parameters. The focus of the adaptive approaches has largely revolved around adapting the inertia weight as it exhibits the clearest relationship with the exploration/exploitation balance of the PSO algorithm. However, despite the significant amount of research efforts, many inertia weight control strategies have not been thoroughly examined analytically nor empirically. Thus, there are a plethora of choices when selecting an inertia weight control strategy, but no study has been comprehensive enough to definitively guide the selection. This paper addresses these issues by first providing an overview of 18 inertia weight control strategies. Secondly, conditions required for the strategies to exhibit convergent behaviour are derived. Finally, the inertia weight control strategies are empirically examined on a suite of 60 benchmark problems. Results of the empirical investigation show that none of the examined strategies, with the exception of a randomly selected inertia weight, even perform on par with a constant inertia weight.     

Turing learning: a metric-free approach to inferring behavior and its application to swarms

We propose Turing Learning, a novel system identification method for inferring the behavior of natural or artificial systems. Turing Learning simultaneously optimizes two populations of computer programs, one representing models of the behavior of the system under investigation, and the other representing classifiers. By observing the behavior of the system as well as the behaviors produced by the models, two sets of data samples are obtained. The classifiers are rewarded for discriminating between these two sets, that is, for correctly categorizing data samples as either genuine or counterfeit. Conversely, the models are rewarded for ‘tricking’ the classifiers into categorizing their data samples as genuine. Unlike other methods for system identification, Turing Learning does not require predefined metrics to quantify the difference between the system and its models. We present two case studies with swarms of simulated robots and prove that the underlying behaviors cannot be inferred by a metric-based system identification method. By contrast, Turing Learning infers the behaviors with high accuracy. It also produces a useful by-product—the classifiers—that can be used to detect abnormal behavior in the swarm. Moreover, we show that Turing Learning also successfully infers the behavior of physical robot swarms. The results show that collective behaviors can be directly inferred from motion trajectories of individuals in the swarm, which may have significant implications for the study of animal collectives. Furthermore, Turing Learning could prove useful whenever a behavior is not easily characterizable using metrics, making it suitable for a wide range of applications.     

A taxonomic revision of <Emphasis Type="Italic">Bursera</Emphasis> subgen. <Emphasis Type="Italic">Bursera</Emphasis> in the Greater Antilles and the Bahamas,including a new species from Cuba

A revision of Bursera in the Greater Antilles and the Bahamas has confirmed that Commiphora does not occur in the region and that all but one species in the region belong to Bursera subgen. Bursera. Here we describe a new species, Bursera yaterensis; B. nashii is synonymized with B. glauca and B. ovata is synonymized with B. trinitensis; and we return five species from Commiphora to Bursera. A dichotomous key is provided using mostly vegetative characters due to the frequent lack of adequate reproductive material and the relative uniformity of most floral and fruit characters.     

Scale-dependent bi-trophic interactions in a semi-arid savanna: how herbivores eliminate benefits of nutrient patchiness to plants

The scale of resource heterogeneity may influence how resources are locally partitioned between co-existing large and small organisms such as trees and grasses in savannas. Scale-related plant responses may, in turn, influence herbivore use of the vegetation. To examine these scale-dependent bi-trophic interactions, we varied fertilizer [(nitrogen (N)/phosphorus (P)/potassium (K)] applications to patches to create different scales of nutrient patchiness (patch size 2 × 2 m, 10 × 10 m, or whole-plot 50 × 50 m) in a large field experiment in intact African savanna. Within-patch fertilizer concentration and the total fertilizer load per plot were independently varied. We found that fertilization increased the leaf N and P concentrations of trees and grasses, resulting in elevated utilization by browsers and grazers. Herbivory off-take was particularly considerable at higher nutrient concentrations. Scale-dependent effects were weak. The net effect of fertilization and herbivory was that plants in fertilized areas tended to grow less and develop smaller rather than larger standing biomass compared to plants growing in areas that remained unfertilized. When all of these effects were considered together at the community (plot) level, herbivory completely eliminated the positive effects of fertilization on the plant community. While this was true for all scales of fertilization, grasses tended to profit more from coarse-grained fertilization and trees from fine-grained fertilization. We conclude that in herbivore-dominated communities, such as the African savanna, nutrient patchiness results in the herbivore community profiting rather more than the plant community, irrespective of the scale of patchiness. At the community level, the allometric scaling theory’s prediction of plant—and probably also animal—production does not hold or may even be reversed as a result of complex bi-trophic interactions.