Physiological model using diffuse reflectance spectroscopy for nonmelanoma skin cancer diagnosis

Diffuse reflectance spectroscopy (DRS) is a noninvasive, fast, and low‐cost technology with potential to assist cancer diagnosis. The goal of this study was to test the capability of our physiological model, a computational Monte Carlo lookup table inverse model, for nonmelanoma skin cancer diagnosis. We applied this model on a clinical DRS dataset to extract scattering parameters, blood volume fraction, oxygen saturation and vessel radius. We found that the model was able to capture physiological information relevant to skin cancer. We used the extracted parameters to classify (basal cell carcinoma [BCC], squamous cell carcinoma [SCC]) vs actinic keratosis (AK) and (BCC, SCC, AK) vs normal. The area under the receiver operating characteristic curve achieved by the classifiers trained on the parameters extracted using the physiological model is comparable to that of classifiers trained on features extracted via Principal Component Analysis. Our findings suggest that DRS can reveal physiologic characteristics of skin and this physiologic model offers greater flexibility for diagnosing skin cancer than a pure statistical analysis. Physiological parameters extracted from diffuse reflectance spectra data for nonmelanoma skin cancer diagnosis.     

Identification of gravid mosquitoes from changes in spectral and polarimetric backscatter cross sections

Improving the survey of mosquito populations is of the utmost importance to further enhance mitigation techniques that protect human populations from mosquito‐borne diseases. While mosquito populations are generally studied using physical traps, stand‐off optical sensors allow to study insect ecosystems with potentially better spatial and temporal resolution. This can be greatly beneficial to eco‐epidemiological models and various mosquito control programs. In this contribution, we demonstrate that the gravidity of female mosquitoes can be identified from changes in their spectral and polarimetric backscatter cross sections. Among other predictive variables, the wing beat frequency and the depolarization ratio of the mosquito body allows for the identification of gravid females with a precision and recall of 86% and 87%, respectively. Since female mosquitoes need a blood meal to become gravid, statistics on gravidity is of prime importance as only females that have been gravid might carry infectious diseases. In addition, it allows to detect possible breeding habitat, predict a potential increase in the mosquito population and provide a better overall understanding of the ecosystem dynamics. As a result, targeted and localized mitigation techniques can be used, reducing the cost and improving the efficiency of mosquito population control.     

A biogeographical analysis of Muhlenbergia (Poaceae: Chloridoideae: Cynodonteae: Muhlenbergiinae)

A phylogeny based on the analysis of six DNA sequence markers (ITS, ndhA intron, rpl32-trnL, rps3, rps16 intron, and rps16-trnK) is used to infer ancestral areas and divergence times, and reconstruct the biogeographical history and evolution of 150 of the 183 (82%) species of Muhlenbergia. Our results suggest that the genus originated 9.3 mya in the Sierra Madre (Occidental and Oriental) in Mexico, splitting into six lineages: M. ramulosa diverging 8.2 mya, M. subg. Muhlenbergia at 5.9 mya, M. subg. Pseudosporobolus at 5.9 mya, M. subg. Clomena at 5.4 mya, M. subg. Bealia at 4.3 mya, and M. subg. Trichochloa at 1 mya, each of these with a high probability of Sierra Madrean origin. Our results further suggest that founder-event speciation from Sierra Madre to South America occurred independently multiple times in all five subgenera during the Pleistocene and late Pliocene. One long-distance dispersal event most likely originating from Central or Eastern North America to East and Central Asia occurred 1.6–1 mya in M. subg. Muhlenbergia. In our cladogram, members of M. subg. Trichochloa show little genetic resolution, suggesting very low levels of divergence among the species, and this may be a consequence of rapid radiation.     

VPMCD: variable interaction modeling approach for class discrimination in biological systems

Data classification algorithms applied for class prediction in computational biology literature are data specific and have shown varying degrees of performance. Different classes cannot be distinguished solely based on interclass distances or decision boundaries. We propose that inter-relations among the features be exploited for separating observations into specific classes. A new variable predictive model based class discrimination (VPMCD) method is described here. Three well established and proven data sets of varying statistical and biological significance are utilized as benchmark. The performance of the new method is compared with advanced classification algorithms. The new method performs better during different tests and shows higher stability and robustness. The VPMCD is observed to be a potentially strong classification approach and can be effectively extended to other data mining applications involving biological systems.     

Selection of relevant features for EEG signal classification of schizophrenic patients

In this paper, EEG signals of 20 schizophrenic patients and 20 age-matched control participants are analyzed with the objective of determining the more informative channels and finally distinguishing the two groups. For each case, 22 channels of EEG were recorded. A two-stage feature selection algorithm is designed, such that, the more informative channels are first selected to enhance the discriminative information. Two methods, bidirectional search and plus-L minus-R (LRS) techniques are employed to select these informative channels. The interesting point is that most of selected channels are located in the temporal lobes (containing the limbic system) that confirm the neuro-phychological differences in these areas between the schizophrenic and normal participants. After channel selection, genetic algorithm (GA) is employed to select the best features from the selected channels. In this case, in addition to elimination of the less informative channels, the redundant and less discriminant features are also eliminated. A computationally fast algorithm with excellent classification results is obtained. Implementation of this efficient approach involves several features including autoregressive (AR) model parameters, band power, fractal dimension and wavelet energy. To test the performance of the final subset of features, classifiers including linear discriminant analysis (LDA) and support vector machine (SVM) are employed to classify the reduced feature set of the two groups. Using the bidirectional search for channel selection, a classification accuracy of 84.62% and 99.38% is obtained for LDA and SVM, respectively. Using the LRS technique for channel selection, a classification accuracy of 88.23% and 99.54% is also obtained for LDA and SVM, respectively. Finally, the results are compared and contrasted with two well-known methods namely, the single-stage feature selection (evolutionary feature selection) and principal component analysis (PCA)-based feature selection. The results show improved accuracy of classification in relatively low computational time with the two-stage feature selection.     

Seeking causes: Classifying and evaluating congenital heart defects in etiologic studies

BACKGROUND: Classification and analysis of congenital heart defects (CHD) in etiologic studies is particularly challenging because of diversity of cardiac phenotypes and underlying developmental mechanisms. We describe an approach to classification for risk assessment of CHD based on developmental and epidemiologic considerations, and apply it to data from the National Birth Defect Prevention Study (NBDPS). METHODS: The classification system incorporated the three dimensions of cardiac phenotype, cardiac complexity, and extracardiac anomalies. The system was designed to facilitate the assessment of simple isolated defects and common associations. A team with cardiologic expertise applied the system to a large sample from the NBDPS. RESULTS: Of the 4,703 cases of CHDs in the NBDPS with birth years 1997 through 2002, 63.6% were simple, isolated cases. Specific associations of CHDs represented the majority of the remainder. The mapping strategy generated relatively large samples for most cardiac phenotypes and provided enough detail to isolate important subgroups of CHDs that may differ by etiology or mechanism. CONCLUSIONS: Classification of CHDs that considers cardiac and extracardiac phenotypes is practically feasible, and yields manageable groups of well-characterized phenotypes. Although best suited for large studies, this approach to classification and analysis can be a flexible and powerful tool in many types of etiologic studies of heart defects.     

Pollen morphology of Trigonostemon and its relatives (Euphorbiaceae)

The pollen of Trigonostemon and the related genera Dimorphocalyx, Ostodes, Tritaxis and Jatropha (outgroup) has been studied with light microscopy, and scanning and transmission electron microscopy. The two major pollen types within Trigonostemon correlate well with macromorphological characters. Species belonging to the Trigonostemon reidioides type have pollen with ‘croton pattern’ ornamentation, a pistil with deeply divided stigmas (to at least half the length of the stigma arm) and stamens with a protruding appendage on the connective, while species of the Trigonostemon verrucosus type have verrucate (to almost gemmate) pollen, stigmas that are shortly cleft and stamens without an appendage on the connective. Dimorphocalyx, Ostodes, Tritaxis and Jatropha (outgroup) have similar pollen morphology, while Trigonostemon deviates from these genera in the absence of the ‘vertically’ striate ornamentation on the subunits. Therefore, when compared with an existing phylogeny of the Euphorbiaceae, the pollen characters of Trigonostemon appear to be derived. Moreover, because the ‘croton pattern’ ornamentation itself is widely shared by the ‘inaperturate crotonoids’, the loss of that structure in the Trigonostemon verrucosus type pollen is considered a further apomorphy.     

Giant clams discriminate threats along a risk gradient and display varying habituation rates to different stimuli

It is often beneficial for animals to discriminate between different threats and to habituate to repeated exposures of benign stimuli. While much is known about risk perception in vertebrates and some invertebrates, risk perception in marine invertebrates is less extensively studied. One method to study risk perception is to habituate animals to a series of exposures to one stimulus, and then present a novel stimulus to test if it transfers habituation. Transfer of habituation is seen as a continued decrease in response while lack of transfer is seen either by having a similar or greater magnitude response. We asked whether giant clams (Tridacna maxima) discriminate between biologically relevant types of threats along a risk gradient. Giant clams retract their mantle and close their shell upon detecting a threat. While closed, they neither feed nor photosynthesize, and prior work has shown that the cost of being closed increases as the duration of their response increases. We recorded a clam's latency to emerge after simulated threats chosen to represent a risk gradient: exposure to a small shading event, a medium shading event, a large shading event (chosen to simulate fish swimming above them), tapping on their shell and touching their mantle (chosen to simulate different degrees of direct attack). Although these stimuli are initially perceived as threatening, we expected clams to habituate to them because they are ultimately non‐damaging and it would be costly for clams to remain closed for extended periods of time when there is no threat present. Clams had different initial latencies to emerge and different habituation rates to these treatments, and they did not transfer habituation to higher risk stimuli and to some lower risk stimuli. These results suggest that clams discriminated between these stimuli along a risk gradient and the lack of habituation transfer shows that the new stimulus was perceived as a potential threat. This study demonstrates that sessile bivalves can discern between levels of predatory threat. These photosynthetic clams may benefit from being able to categorize predator cues for efficient energy allocation.