Enhanced detonators detection in X-ray baggage inspection by image manipulation and deep convolutional neural networks.

Detecting detonators is a challenging task because they can be easily mis-classified as being a harmless organic mass, especially in high baggage throughput scenarios. Of particular interest is the focus on automated security X-ray analysis for detonators detection. The complex security scenarios require increasingly advanced combinations of computer-assisted vision. We propose an extensive set of experiments to evaluate the ability of Convolutional Neural Network (CNN) models to detect detonators, when the quality of the input images has been altered through manipulation. We leverage recent advances in the field of wavelet transforms and established CNN architectures-as both of these can be used for object detection. Various methods of image manipulation are used and further, the performance of detection is evaluated. Both raw X-ray images and manipulated images with the Contrast Limited Adaptive Histogram Equalization (CLAHE), wavelet transform-based methods and the mixed CLAHE RGB-wavelet method were analyzed. The results showed that a significant number of operations, such as: edges enhancements, altered color information or different frequency components provided by wavelet transforms, can be used to differentiate between almost similar features. It was found that the wavelet-based CNN achieved the higher detection performance. Overall, this performance illustrates the potential for a combined use of the manipulation methods and deep CNNs for airport security applications.

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.

Quiescent optical solitons with complex Ginzburg-Landau equation having a dozen forms of self-phase modulation.

The current study focuses on the recovery of quiescent optical solitons through the use of the complex Ginzburg-Landau equation when the chromatic dispersion is rendered to be nonlinear. A dozen forms of self-phase modulation structures are taken into consideration. The utilization of the enhanced Kudryashov's scheme has led to the emergence of singular, dark, and bright soliton solutions. The existence of such solitons is subject to certain parametric restrictions, which are also discussed in this paper.

Assessing and forecasting water quality in the Danube River by using neural network approaches.

The health and quality of the Danube River ecosystems is strongly affected by the nutrients loads (N and P), degree of contamination with hazardous substances or with oxygen depleting substances, microbiological contamination and changes in river flow patterns and sediment transport regimes. Water quality index (WQI) is an important dynamic attribute in the characterization of the Danube River ecosystems health and quality. The WQ index scores do not reflect the actual condition of water quality. We proposed a new forecast scheme for water quality based on the following qualitative classes very good (0-25), good (26-50), poor (51-75), very poor (76-100) and extremely polluted/non-potable (>100). Water quality forecasting by using Artificial Intelligence (AI) is a meaningful method of protecting public health because of its possibility to provide early warning regarding harmful water pollutants. The main objective of the present study is to forecast the WQI time series data based on water physical, chemical and flow status parameters and associated WQ index scores. The Cascade-forward network (CFN) models, along with the Radial Basis Function Network (RBF) as a benchmark model, were developed using data from 2011 to 2017 and WQI forecasts were produced for the period 2018-2019 at all sites. The nineteen input water quality features represent the initial dataset. Moreover, the Random Forest (RF) algorithm refines the initial dataset by selecting eight features considered the most relevant. Both datasets are employed for constructing the predictive models. According to the results of appraisal, the CFN models produced better outcomes (MSE = 0.083/0,319 and R-value 0.940/0.911 in quarter I/quarter IV) than the RBF models. In addition, results show that both the CFN and RBF models could be effective for predicting time series data for water quality when the eight most relevant features are used as input variables. Also, the CFNs provide the most accurate short-term forecasting curves which reproduce the WQI for the first and fourth quarters (the cold season). The second and third quarters presented a slightly lower accuracy. The reported results clearly demonstrate that CFNs successfully forecast the short-term WQI as they may learn historic patterns and determine the nonlinear relationships between the input and output variables.

Dispersive optical solitons and conservation laws of Radhakrishnan-Kundu-Lakshmanan equation with dual-power law nonlinearity.

The current paper implements three elegant approaches to recover a complete spectrum of optical solitons to the Radhakrishnan-Kundu-Lakshmanan equation with dual-power law of nonlinear refractive index. The conservation laws are also recovered by the usage of multipliers approach. The parameter constraints for the existence of such solitons are also enumerated. The numerical simulations of the recovered soliton solutions are also presented.

A Robust Machine Learning Model for Diabetic Retinopathy Classification.

Ensemble learning is a process that belongs to the artificial intelligence (AI) field. It helps to choose a robust machine learning (ML) model, usually used for data classification. AI has a large connection with image processing and feature classification, and it can also be successfully applied to analyzing fundus eye images. Diabetic retinopathy (DR) is a disease that can cause vision loss and blindness, which, from an imaging point of view, can be shown when screening the eyes. Image processing tools can analyze and extract the features from fundus eye images, and these corroborate with ML classifiers that can perform their classification among different disease classes. The outcomes integrated into automated diagnostic systems can be a real success for physicians and patients. In this study, in the form image processing area, the manipulation of the contrast with the gamma correction parameter was applied because DR affects the blood vessels, and the structure of the eyes becomes disorderly. Therefore, the analysis of the texture with two types of entropies was necessary. Shannon and fuzzy entropies and contrast manipulation led to ten original features used in the classification process. The machine learning library PyCaret performs complex tasks, and the empirical process shows that of the fifteen classifiers, the gradient boosting classifier (GBC) provides the best results. Indeed, the proposed model can classify the DR degrees as normal or severe, achieving an accuracy of 0.929, an F1 score of 0.902, and an area under the curve (AUC) of 0.941. The validation of the selected model with a bootstrap statistical technique was performed. The novelty of the study consists of the extraction of features from preprocessed fundus eye images, their classification, and the manipulation of the contrast in a controlled way.

A New Approach in Detectability of Microcalcifications in the Placenta during Pregnancy Using Textural Features and K-Nearest Neighbors Algorithm.

(1) Background: Ultrasonography is the main method used during pregnancy to assess the fetal growth, amniotic fluid, umbilical cord and placenta. The placenta's structure suffers dynamic modifications throughout the whole pregnancy and many of these changes, in which placental microcalcifications are by far the most prominent, are related to the process of aging and maturation and have no effect on fetal wellbeing. However, when placental microcalcifications are noticed earlier during pregnancy, they could suggest a major placental dysfunction with serious consequences for the fetus and mother. For better detectability of microcalcifications, we propose a new approach based on improving the clarity of details and the analysis of the placental structure using first and second order statistics, and fractal dimension. (2) Methods: The methodology is based on four stages: (i) cropping the region of interest and preprocessing steps; (ii) feature extraction, first order-standard deviation (SD), skewness (SK) and kurtosis (KR)-and second order-contrast (C), homogeneity (H), correlation (CR), energy (E) and entropy (EN)-are computed from a gray level co-occurrence matrix (GLCM) and fractal dimension (FD); (iii) statistical analysis (t-test); (iv) classification with the K-Nearest Neighbors algorithm (K-NN algorithm) and performance comparison with results from the support vector machine algorithm (SVM algorithm). (3) Results: Experimental results obtained from real clinical data show an improvement in the detectability and visibility of placental microcalcifications.

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.

Combining Sparse and Dense Features to Improve Multi-Modal Registration for Brain DTI Images.

A new solution to overcome the constraints of multimodality medical intra-subject image registration is proposed, using the mutual information (MI) of image histogram-oriented gradients as a new matching criterion. We present a rigid, multi-modal image registration algorithm based on linear transformation and oriented gradients for the alignment of T2-weighted (T2w) images (as a fixed reference) and diffusion tensor imaging (DTI) (b-values of 500 and 1250 s/mm2) as floating images of three patients to compensate for the motion during the acquisition process. Diffusion MRI is very sensitive to motion, especially when the intensity and duration of the gradient pulses (characterized by the b-value) increases. The proposed method relies on the whole brain surface and addresses the variability of anatomical features into an image stack. The sparse features refer to corners detected using the Harris corner detector operator, while dense features use all image pixels through the image histogram of oriented gradients (HOG) as a measure of the degree of statistical dependence between a pair of registered images. HOG as a dense feature is focused on the structure and extracts the oriented gradient image in the x and y directions. MI is used as an objective function for the optimization process. The entropy functions and joint entropy function are determined using the HOGs data. To determine the best image transformation, the fiducial registration error (FRE) measure is used. We compare the results against the MI-based intensities results computed using a statistical intensity relationship between corresponding pixels in source and target images. Our approach, which is devoted to the whole brain, shows improved registration accuracy, robustness, and computational cost compared with the registration algorithms, which use anatomical features or regions of interest areas with specific neuroanatomy. Despite the supplementary HOG computation task, the computation time is comparable for MI-based intensities and MI-based HOG methods.

Gaussian mixture model for texture characterization with application to brain DTI images.

A Gaussian mixture model (GMM)-based classification technique is employed for a quantitative global assessment of brain tissue changes by using pixel intensities and contrast generated by b-values in diffusion tensor imaging (DTI). A hemisphere approach is also proposed. A GMM identifies the variability in the main brain tissues at a macroscopic scale rather than searching for tumours or affected areas. The asymmetries of the mixture distributions between the hemispheres could be used as a sensitive, faster tool for early diagnosis. The k-means algorithm optimizes the parameters of the mixture distributions and ensures that the global maxima of the likelihood functions are determined. This method has been illustrated using 18 sub-classes of DTI data grouped into six levels of diffusion weighting (b = 0; 250; 500; 750; 1000 and 1250 s/mm2) and three main brain tissues. These tissues belong to three subjects, i.e., healthy, multiple haemorrhage areas in the left temporal lobe and ischaemic stroke. The mixing probabilities or weights at the class level are estimated based on the sub-class-level mixing probability estimation. Furthermore, weighted Euclidean distance and multiple correlation analysis are applied to analyse the dissimilarity of mixing probabilities between hemispheres and subjects. The silhouette data evaluate the objective quality of the clustering. By using a GMM in the present study, we establish an important variability in the mixing probability associated with white matter and grey matter between the left and right hemispheres.

Texture analysis of parasitological liver fibrosis images.

Liver fibrosis accurate staging is vital to define the state of the Schistosomiasis disease for further treatment. The present work analyzed the microscopic liver images to identify and to differentiate between healthy, cellular, fibrocellular, and fibrous liver pathologies by proposing a fast, robust, and highly discriminative method based on texture analysis. The multiclass classification based on the "one-versus- all" method that built a voting rule approach to classify the liver images based on the liver state. Specifically, quantitative parameters, such as the anisotropy and laminarity are proposed based on the relative orientation of the pixel pairs in a global and local coherence of gradient vectors approach. Analysis of the tissue texture data using both gradient vector and gradient angle co-occurrence matrix approaches facilitated more definitive identification of the abnormal tissue. The experimental results established that the local anisotropy based texture measures are appropriated for the microtexture analysis in order to discriminate between pathologies. Macrotexture description using the global features provided only integral anisotropy coefficient that has a confidence level similar to those provided by the local feature.

Robust Skull-Stripping Segmentation Based on Irrational Mask for Magnetic Resonance Brain Images.

This paper proposes a new method for simple, efficient, and robust removal of the non-brain tissues in MR images based on an irrational mask for filtration within a binary morphological operation framework. The proposed skull-stripping segmentation is based on two irrational 3 × 3 and 5 × 5 masks, having the sum of its weights equal to the transcendental number π value provided by the Gregory-Leibniz infinite series. It allows maintaining a lower rate of useful pixel loss. The proposed method has been tested in two ways. First, it has been validated as a binary method by comparing and contrasting with Otsu's, Sauvola's, Niblack's, and Bernsen's binary methods. Secondly, its accuracy has been verified against three state-of-the-art skull-stripping methods: the graph cuts method, the method based on Chan-Vese active contour model, and the simplex mesh and histogram analysis skull stripping. The performance of the proposed method has been assessed using the Dice scores, overlap and extra fractions, and sensitivity and specificity as statistical methods. The gold standard has been provided by two neurologist experts. The proposed method has been tested and validated on 26 image series which contain 216 images from two publicly available databases: the Whole Brain Atlas and the Internet Brain Segmentation Repository that include a highly variable sample population (with reference to age, sex, healthy/diseased). The approach performs accurately on both standardized databases. The main advantage of the proposed method is its robustness and speed.

Optimization of breast lesion segmentation in texture feature space approach.

This paper develops a method for semi-automatic detection of breast lesion boundaries by combining the snake evolution techniques with statistical texture information of images. We propose an efficient image energy function in segmentation based on image features, first-order textural features and four n×n masks. The segmentation results were evaluated by using area error rate. The image features were evaluated qualitatively by using the contrast-to-noise ratio and fractal dimension analysis. In our study, standard deviation, skewness and entropy are indicated as being the most relevant image features.

Comparative study on the performance of textural image features for active contour segmentation.

We present a computerized method for the semi-automatic detection of contours in ultrasound images. The novelty of our study is the introduction of a fast and efficient image function relating to parametric active contour models. This new function is a combination of the gray-level information and first-order statistical features, called standard deviation parameters. In a comprehensive study, the developed algorithm and the efficiency of segmentation were first tested for synthetic images. Tests were also performed on breast and liver ultrasound images. The proposed method was compared with the watershed approach to show its efficiency. The performance of the segmentation was estimated using the area error rate. Using the standard deviation textural feature and a 5×5 kernel, our curve evolution was able to produce results close to the minimal area error rate (namely 8.88% for breast images and 10.82% for liver images). The image resolution was evaluated using the contrast-to-gradient method. The experiments showed promising segmentation results.