Refining skin lesions classification performance using geometric features of superpixels.

This paper introduces superpixels to enhance the detection of skin lesions and to discriminate between melanoma and nevi without false negatives, in dermoscopy images. An improved Simple Linear Iterative Clustering (iSLIC) superpixels algorithm for image segmentation in digital image processing is proposed. The local graph cut method to identify the region of interest (i.e., either the nevi or melanoma lesions) has been adopted. The iSLIC algorithm is then exploited to segment sSPs. iSLIC discards all the SPs belonging to image background based on assigned labels and preserves the segmented skin lesions. A shape and geometric feature extraction task is performed for each segmented SP. The extracted features are fed into six machine learning algorithms such as: random forest, support vector machines, AdaBoost, k-nearest neighbor, decision trees (DT), Gaussian Naïve Bayes and three neural networks. These include Pattern recognition neural network, Feed forward neural network, and 1D Convolutional Neural Network for classification. The method is evaluated on the 7-Point MED-NODE and PAD-UFES-20 datasets and the results have been compared to the state-of-art findings. Extensive experiments show that the proposed method outperforms the compared existing methods in terms of accuracy.

Skin Lesion Classification Based on Surface Fractal Dimensions and Statistical Color Cluster Features Using an Ensemble of Machine Learning Techniques.

(1) Background: An approach for skin cancer recognition and classification by implementation of a novel combination of features and two classifiers, as an auxiliary diagnostic method, is proposed. (2) Methods: The predictions are made by k-nearest neighbor with a 5-fold cross validation algorithm and a neural network model to assist dermatologists in the diagnosis of cancerous skin lesions. As a main contribution, this work proposes a descriptor that combines skin surface fractal dimension and relevant color area features for skin lesion classification purposes. The surface fractal dimension is computed using a 2D generalization of Higuchi's method. A clustering method allows for the selection of the relevant color distribution in skin lesion images by determining the average percentage of color areas within the nevi and melanoma lesion areas. In a classification stage, the Higuchi fractal dimensions (HFDs) and the color features are classified, separately, using a kNN-CV algorithm. In addition, these features are prototypes for a Radial basis function neural network (RBFNN) classifier. The efficiency of our algorithms was verified by utilizing images belonging to the 7-Point, Med-Node, and PH2 databases; (3) Results: Experimental results show that the accuracy of the proposed RBFNN model in skin cancer classification is 95.42% for 7-Point, 94.71% for Med-Node, and 94.88% for PH2, which are all significantly better than that of the kNN algorithm. (4) Conclusions: 2D Higuchi's surface fractal features have not been previously used for skin lesion classification purpose. We used fractal features further correlated to color features to create a RBFNN classifier that provides high accuracies of classification.

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks.

In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape asymmetry for an optimal structural design that includes both the hidden neuron number and the input data selection. The reason for the choice of shape asymmetry was based on the 5-10% disagreement between dermatologists regarding the efficacy of asymmetry in the diagnosis of malignant melanoma. Asymmetry is quantified based on lesion shape (contour), moment of inertia of the lesion shape and histograms. The FFBPN has a high architecture flexibility, which indicates it as a favorable tool to avoid the over-parameterization of the ANN and, equally, to discard those redundant input datasets that usually result in poor test performance. The FFBPN was tested on four public image datasets containing melanoma, dysplastic nevus and nevus images. Experimental results on multiple benchmark data sets demonstrate that asymmetry A2 is a meaningful feature for skin lesion classification, and FFBPN with 16 neurons in the hidden layer can model the data without compromising prediction accuracy.

A novel method for the measurement of elemental selenium produced by bacterial reduction of selenite.

The measurement of elemental selenium (Se(0)) is needed to assess the rate and magnitude of bacteria reduction of selenite or selenate. We have developed a spectrophotometric method for the measurement Se(0) that is rapid and can be employed to measure the quantity of Se(0) produced by bacterial cultures. This method employs the use of 1M Na(2)S to convert the insoluble elemental selenium to a red-brown solution and with this method there is a direct correlation between concentration of elemental selenium and the absorption at 500nm. To demonstrate the utility of this assay, we have followed the reduction of selenite to Se(0) by Moraxella bovis, and by bacterial consortia in soil and water samples.

An exact solution for the modified nonlinear Schrödinger's equation for Davydov solitons in alpha-helix proteins.

The solitons in alpha-helix proteins that are governed by the nonlinear Schrödinger's equation is investigated in presence of perturbation terms in this paper. The integration of this perturbed nonlinear Schrödinger's equation is carried out. The solitary wave ansatz is used to carry out the integration and the parameter domain is identified.

Hydrolysis and photolysis of oxytetracycline in aqueous solution.

Oxytetracycline ((2Z,4S,4aR,5S,5aR,6S,12aS)-2-(amino-hydroxy-methylidene)-4-dimethylamino-5,6,10,11,12a-pentahydroxy-6-methyl-4,4a,5,5a-tetrahydrotetracene-1,3,12-trione) is a member of tetracycline antibiotics family and is widely administered to farm animals for the purpose of therapeutical treatment and health protection. Increasing attention has been paid to the environmental fate of oxytetracycline and other veterinary antibiotics with the occurrence of these antibiotics in the environment. The hydrolysis and photolysis degradation of oxytetracycline was investigated in this study. Oxytetracycline hydrolysis was found to obey the first-order model and similar rate constant values ranging from 0.094 +/- 0.001 to 0.106 +/- 0.003 day(-1) were obtained at different initial concentration ranging from 10 to 230 microM. Solution pH and temperature were shown to have remarked effects on oxytetracycline hydrolysis. The hydrolysis in pH neutral solution appeared to be much faster than in both acidic and alkaline solutions. Oxytetracycline half-life decreased from 1.2 x 10(2) to 0.15 day with the increasing temperature from 4 +/- 0.8 to 60 +/- 1 degrees C. The presence of Ca(2+) made oxytetracycline hydrolytic degradation kinetics deviate from the simple first-order model to the availability-adjusted first-order model and greatly slowed down the hydrolysis. Oxytetracycline photolysis was found to be very fast with a degradation rate constant at 3.61 +/- 0.06 day(-1), which is comparable to that of hydrolysis at 60 degrees C. The presence of Ca(2+) accelerated oxytetracycline photolysis, implying that oxytetracycline become more vulnerable to sunlight irradiation after chelating with Ca(2+). The photolysis may be the dominant degradation pathway of oxytetracycline in shallow transparent water environment.

Reduction of molybdate by sulfate-reducing bacteria.

Molybdate is an essential trace element required by biological systems including the anaerobic sulfate-reducing bacteria (SRB); however, detrimental consequences may occur if molybdate is present in high concentrations in the environment. While molybdate is a structural analog of sulfate and inhibits sulfate respiration of SRB, little information is available concerning the effect of molybdate on pure cultures. We followed the growth of Desulfovibrio gigas ATCC 19364, Desulfovibrio vulgaris Hildenborough, Desulfovibrio desulfuricans DSM 642, and D. desulfuricans DSM 27774 in media containing sub-lethal levels of molybdate and observed a red-brown color in the culture fluid. Spectral analysis of the culture fluid revealed absorption peaks at 467, 395 and 314 nm and this color is proposed to be a molybdate-sulfide complex. Reduction of molybdate with the formation of molybdate disulfide occurs in the periplasm D. gigas and D. desulfuricans DSM 642. From these results we suggest that the occurrence of poorly crystalline Mo-sulfides in black shale may be a result from SRB reduction and selective enrichment of Mo in paleo-seawater.