Search

Graphical abstract, Orthogonal moments are used to represent digital images with minimum redundancy. Orthogonal moments with fractional-orders show better capabilities in digital image analysis than integer-order moments. In this work, the authors present new fractional-order shifted Gegenbauer polynomials. These new polynomials are used to define a novel set of orthogonal fractional-order shifted Gegenbauer moments (FrSGMs). The proposed method is applied in gray-scale image analysis and recognition. The invariances to rotation, scaling and translation (RST), are achieved using invariant fractional-order geometric moments. Experiments are conducted to evaluate the proposed FrSGMs and compare with the classical orthogonal integer-order Gegenbauer moments (GMs) and the existing orthogonal fractional-order moments. The new FrSGMs outperformed GMs and the existing orthogonal fractional-order moments in terms of image recognition and reconstruction, RST invariance, and robustness to noise.

The classical radial harmonic Fourier moments (RHFMs) and the quaternion radial harmonic Fourier moments (QRHFMs) are gray-scale and color image descriptors. The radial harmonic functions with integer orders are not able to extract fine features from the input images. In this paper, the authors derived novel fractional-order radial harmonic functions in polar coordinates. The obtained functions are used to defined novel multi-channel fractional-order radial harmonic moments (FrMRHFMs) for color image description and analysis. The invariants to geometric transformations for these new moments are derived. A theoretical comparison between FrMRHFMs and QRHFMs is performed from the aspects of kernel function and the spectrum analysis. Numerical simulation is carried out to test these new moments in terms of image reconstruction capabilities, invariance to the similarity transformations, color image recognition and the CPU computational times. The obtained theoretical and numerical results clearly show that the proposed FrMRHFMs is superior to the QRHFMs and the existing fractional-order orthogonal moments.

Pathologists need a lot of clinical experience and time to do the histopathological investigation. AI may play a significant role in supporting pathologists and resulting in more accurate and efficient histopathological diagnoses. Breast cancer is one of the most diagnosed cancers in women worldwide. Breast cancer may be detected and diagnosed using imaging methods such as histopathological images. Since various tissues make up the breast, there is a wide range of textural intensity, making abnormality detection difficult. As a result, there is an urgent need to improve computer-assisted systems (CAD) that can serve as a second opinion for radiologists when they use medical images. A self-training learning method employing deep learning neural network with residual learning is proposed to overcome the issue of needing a large number of labeled images to train deep learning models in breast cancer histopathology image classification. The suggested model is built from scratch and trained.

Computer-aided systems for skin lesion diagnosis is a growing area of research. Recently, researchers have shown an increasing interest in developing computer-aided diagnosis systems. This paper aims to review, synthesize and evaluate the quality of evidence for the diagnostic accuracy of computer-aided systems. This study discusses the papers published in the last five years in ScienceDirect, IEEE, and SpringerLink databases. It includes 53 articles using traditional machine learning methods and 49 articles using deep learning methods. The studies are compared based on their contributions, the methods used and the achieved results. The work identified the main challenges of evaluating skin lesion segmentation and classification methods such as small datasets, ad hoc image selection and racial bias.

Breast cancer is one of the most prevalent cancer types with a high mortality rate in women worldwide. This devastating cancer still represents a worldwide public health concern in terms of high morbidity and mortality rates. The diagnosis of breast abnormalities is challenging due to different types of tissues and textural variations in intensity. Hence, developing an accurate computer-aided system (CAD) is very important to distinguish normal from abnormal tissues and define the abnormal tissues as benign or malignant. The present study aims to enhance the accuracy of CAD systems and to reduce its computational complexity. This paper proposes a method for extracting a set of statistical features based on curvelet and wavelet sub-bands. Then the binary grey wolf optimizer (BGWO) is used as a feature selection technique aiming to choose the best set of features giving high performance. Using public dataset, Digital Database for Screening Mammography (DDSM), different experiments have been performed with and without using the BGWO algorithm. The random forest classifier with 10-fold cross-validation is used to achieve the classification task to evaluate the selected set of features&rsquo, capability. The obtained results showed that when the BGWO algorithm is used as a feature selection technique, only 30.7% of the total features can be used to detect whether a mammogram image is normal or abnormal with ROC area reaching 1.0 when the fusion of both curvelet and wavelet features were used. In addition, in case of diagnosing the mammogram images as benign or malignant, the results showed that using BGWO algorithm as a feature selection technique, only 38.5% of the total features can be used to do so with high ROC area result at 0.871.

Aim: We aimed to explore the circulating expression profile of nine lncRNAs (MALAT1, HOTAIR, PVT1, H19, ROR, GAS5, ANRIL, BANCR, MIAT) in breast cancer (BC) patients relative to normal and risky individuals. Methods: Serum relative expressions of the specified long non-coding RNAs were quantified in 155 consecutive women, using quantitative reverse-transcription PCR. Random Forest (RF) and decision tree were also applied. Results: Significant MALAT1 upregulation and GAS5 downregulation could discriminate risky women from healthy controls. Overexpression of the other genes showed good diagnostic performances. Lower GAS5 levels were associated with metastasis and recurrence. RF model revealed a better performance when combining gene expression patterns with risk factors. Conclusion: The studied panel could be utilized as diagnostic/prognostic biomarkers in BC, providing promising epigenetic-based therapeutic targets.

Accurate segregation of pectoral muscles is very crucial in breast cancer detection. Pectoral segmentation is a challenging task due to heterogeneous tissues densities, neighborhood complexities and breast shape variabilities. This paper presents an adaptive gamma correction method for pectoral suppression in mammograms. The proposed algorithm is adaptive to variations in shape, density of tissues and the curvature of pectoral boundary i.e. straight line or curved pectoral boundary. The method utilizes the morphological information of mammograms to discriminate the breast parenchyma from the rest of breast region. The adaptive gamma corrections enhance the mammograms according to tissues densities and provide a separation boundary between breast region and pectoral parenchymal. The method is tested on three types of tissues densities present in MIAS dataset i.e. Fatty, Fatty-glandular and Dense tissues. The goodness of segmentation is measured using jaccard similarity index between the ground truth and segmented regions. The proposed methods successfully detected 98.45 % of the pectoral regions and have an overall 92.79 % jaccard similarity index with the ground truth. Moreover, evaluation by experts also confirms good performance of the proposed method.

Breast cancer is one of the common cancer deaths in women worldwide. Early detection is the key to reduce the mortality rate. Clinical trials have shown that computer aided systems (CAD) have improved the accuracy of breast cancer detection. This paper proposed a highly accurate CAD system based on extracting highly significant features using exact Gaussian–Hermite moments. The obtained feature vector is presented to K-NN, random forests and AdaBoost classifiers. The proposed system is evaluated using two different datasets namely IRMA and MIAS. The evaluation metrics of accuracy, TP, FP and area under ROC curve using 10-fold cross-validation are calculated. The results indicate the usefulness of the proposed exact Gaussian–Hermite moments features for distinguishing between normal and abnormal lesions and the superiority of the moments features compared with the conventional methods.

This work introduces a computer-aided diagnosis (CAD) system for diagnosing liver cirrhosis in ultrasound (US) images. The proposed system uses a set of features obtained from different feature extraction methods. These features are the first order statistics (FOS), the fractal dimension (FD), the gray level co-occurrence matrix (GLCM), the Gabor filter (GF), the wavelet (WT) and the curvelet (CT) features. The measured features are presented in two different classifiers such as support vector machine (SVM) and k-nearest neighbors (K-NN). The proposed system is applied on dataset consists of 72 cirrhosis and 75 normal regions each of 128x128 pixels. The classification accuracy rates are calculated using a 10-fold cross validation. A correlation-based feature selection (CFS) is used resulting in better accuracy predictions. The results showed that SVM and K-NN classifiers achieved higher performance with the combination of the wavelet and curvelet feature vectors than other feature extraction methods.

microarray image processing becomes a viable branch of bioinformatics, its importance stems from the fact that it allows viewing and measuring tens of thousands of genes concurrently. Many techniques were introduced to develop and improve the mission of processing DNA microarray images. The aim of this study is to make a segmentation of the cDNA microarray images. The Marker Controlled Watershed technique is used to segment the DNA microarray spots. The proposed method starts with preprocessing step; i.e. denoising and histogram equalization. Then, the spots are segmented from its background. The used images in this paper were obtained from Stanford Microarray Database (SMD). The obtained results of the developed method are compared to the results of K-means clustering method and fuzzy c-means clustering method. We can conclude that the Marker Controlled Watershed technique is efficient for segmenting the cDNA microarray images.

Breast cancer is one of the leading causes of death in women worldwide. Early detection is the key to reduce the mortality rates. Mammography screening has proven to be one of the effective tools for diagnosis of breast cancer. Computer aided diagnosis (CAD) system is a fast, reliable, and cost-effective tool in assisting the radiologists/physicians for diagnosis of breast cancer. CAD systems play an increasingly important role in the clinics by providing a second opinion. Clinical trials have shown that CAD systems have improved the accuracy of breast cancer detection. A typical CAD system involves three major steps i.e. segmentation of suspected lesions, feature extraction and classification of these regions into normal or abnormal class and further into benign or malignant stages. The diagnostics ability of any CAD system is dependent on accurate segmentation, feature extraction techniques and most importantly classification tools that have ability to discriminate the normal tissues from the abnormal tissues. In this chapter we discuss the application of machine learning algorithms e.g. ANN, binary tree, SVM, etc. together with segmentation and feature extraction techniques in a CAD system development. Various methods used in the detection and diagnosis of breast lesions in mammography are reviewed. A brief introduction of machine learning tools, used in diagnosis and their classification performance on various segmentation and feature extraction techniques is presented.

This paper introduces a method for feature extraction from multiresolution representations (wavelet,curvelet) for classification of digital mammograms. The proposed method selects the fe atures according to its capability to distinguish between different classes. The method starts with both performing wavelet and curvelet transform over mammogram images. The resulting coefficients of each image are used to construct a matrix. Each row in the matrix corresponds to an image.The most significant features, in terms of capabilities of differentiating classes,are selected. The method uses threshold values to select the columns that will maximize the difference between the different classes'representa tives. The proposed method is applied to the mammographic image analysis society (MIAS) dataset. The results calculated using 2x5-folds cross validation show that the proposed method is able to find an appropriate feature set that lead to significant improvement in c lassification accuracy.The obtained results were satisfactory and the performances of both wavelet and curvelet are presented and compared.

This paper presents a method for breast cancer diagnosis in digital mammogram images. Multi-resolution representations, wavelet or curvelet, are used to transform the mammogram images into a long vector of coefficients. A matrix is constructed by putting wavelet or curvelet coefficients of each image in row vector, where the number of rows is the number of images, and the number of columns is the number of coefficients. A feature extraction method is developed based on the statistical t-test method. The method is ranking the features (columns) according to its capability to differentiate the classes. Then, a dynamic threshold is applied to optimize the number of features, which can achieve the maximum classification accuracy rate. The method depends on extracting the features that can maximize the ability to discriminate between different classes. Thus, the dimensionality of data features is reduced and the classification accuracy rate is improved. Support vector machine (SVM) is used to classify between the normal and abnormal tissues and to distinguish between benign and malignant tumors. The proposed method is validated using 5-fold cross validation. The obtained classification accuracy rates demonstrate that the proposed method could contribute to the successful detection of breast cancer.

This paper presents an approach for breast cancer diagnosis in digital mammogram using curvelet transform. After decomposing the mammogram images in curvelet basis, a special set of the biggest coefficients is extracted as feature vector. The Euclidean distance is then used to construct a supervised classifier. The experimental results gave a 98.59% classification accuracy rate, which indicate that curvelet transformation is a promising tool for analysis and classification of digital mammograms.

This paper presents a comparative study between wavelet and curvelet transform for breast cancer diagnosis in digital mammogram. Using multiresolution analysis, mammogram images are decomposed into different resolution levels, which are sensitive to different frequency bands. A set of the biggest coefficients from each decomposition level is extracted. Then a supervised classifier system based on Euclidian distance is constructed. The performance of the classifier is evaluated using a 2 x 5-fold cross validation followed by a statistical analysis. The experimental results suggest that curvelet transform outperforms wavelet transform and the difference is statistically significant.

This paper presents a method for classification of normal and abnormal tissues in mammograms using curvelet transform. The curvelet coefficients are represented into certain groups of coefficients, independently. Some statistical features are calculated for each group of coefficients. These statistical features are combined with features extracted from the mammogram image itself. To improve the classification rate, feature ranking method is applied to select the most significant features. The classification results of support vector machine (SVM) using 10-fold cross validation are presented. The classification results show that the ranked features improved the classification rate up to 85.48% with group of 200 coefficients.

Image texture analysis plays an important role in object detection and recognition in image processing. The texture analysis can be used for early detection of breast cancer by classifying the mammogram images into normal and abnormal classes. This study investigates breast cancer detection using texture features obtained from the grey level cooccurrence matrices (GLCM) of curvelet sub-band levels combined with texture feature obtained from the image itself. The GLCM were constructed for each sub-band of three curvelet decomposition levels. The obtained feature vector presented to the classifier to differentiate between normal and abnormal tissues. The proposed method is applied over 305 region of interest (ROI) cropped from MIAS dataset. The simple logistic classifier achieved 86.66% classification accuracy rate with sensitivity 76.53% and specificity 91.3%.

Early detection of breast cancer helps reducing the mortality rates. Mammography is very useful tool in breast cancer detection. But it is very difficult to separate different morphological features in mammographic images. In this study, Morphological Component Analysis (MCA) method is used to extract different morphological aspects of mammographic images by effectively preserving the morphological characteristics of regions. MCA decomposes the mammogram into piecewise smooth part and the texture part using the Local Discrete Cosine Transform (LDCT) and Curvelet Transform via wrapping (CURVwrap). In this study, simple comparison in performance has been done using some statistical features for the original image versus the piecewise smooth part obtained from the MCA decomposition. The results show that MCA suppresses the structural noises and blood vessels from the mammogram and enhances the performance for mass detection.

This paper proposes a method for breast cancer diagnosis in digital mammogram. The article focuses on using texture analysis based on curvelet transform for the classification of tissues. The most discriminative texture features of regions of interest are extracted. Then, a nearest neighbor classifier based on Euclidian distance is constructed. The obtained results calculated using 5-fold cross validation. The approach consists of two steps, detecting the abnormalities and then classifies the abnormalities into benign and malignant tumors.

The study examined the implementation of artificial neural network (ANN) for the prediction and simulation of antibiotic degradation in aqueous solution by the Fenton process. A three-layer backpropagation neural network was optimized to predict and simulate the degradation of amoxicillin, ampicillin and cloxacillin in aqueous solution in terms of COD removal. The configuration of the backpropagation neural network giving the smallest mean square error (MSE) was three-layer ANN with tangent sigmoid transfer function (tansig) at hidden layer with 14 neurons, linear transfer function (purelin) at output layer and Levenberg-Marquardt backpropagation training algorithm (LMA). ANN predicted results are very close to the experimental results with correlation coefficient (R(2)) of 0.997 and MSE 0.000376. The sensitivity analysis showed that all studied variables (reaction time, H(2)O(2)/COD molar ratio, H(2)O(2)/Fe(2+) molar ratio, pH and antibiotics concentration) have strong effect on antibiotic degradation in terms of COD removal. In addition, H(2)O(2)/Fe(2+) molar ratio is the most influential parameter with relative importance of 25.8%. The results showed that neural network modeling could effectively predict and simulate the behavior of the Fenton process.

This paper presents an approach for breast cancer diagnosis in digital mammogram using curvelet transform. The motivation of this approach is the desire of using the advantages of curvelet transform into mammogram analysis. Curvelet provide stable, efficient and near-optimal representation of otherwise smooth objects having discontinuities along smooth curves. Since medical images have several objects and curved shaped, it is expected that the curvelet transform would be better for classification of cancer classes in digital mammogram. To construct and evaluate a supervised classifier for this problem, by transforming the data of the images in curvelet basis and then using a special set of coefficients as the features tailored towards separating each of those classes. The experimental results indicate that using curvelet transform significantly improves the classification of cancer classes.

This paper introduces a new method of feature extraction from Wavelet coefficients for classification of digital mammograms. A matrix is constructed by putting Wavelet coefficients of each image of a building set as a row vector. The method consists then on selecting by threshold, the columns which will maximize the Euclidian distances between the different class representatives. The selected columns are then used as features for classification. The method is tested using a set of images provided by the Mammographic Image Analysis Society (MIAS) to classify between normal and abnormal and then between benign and malignant tissues. For both classifications, a high accuracy rate (98%) is achieved.

Whilst facial recognition systems are vulnerable to different acquisition conditions, most notably lighting effects and pose variations, their particular level of sensitivity to facial aging effects is yet to be researched. The face recognition vendor test (FRVT) 2012's annual statement estimated deterioration in the performance of face recognition systems due to facial aging. There was about 5% degradation in the accuracies of the face recognition systems for each single year age difference between a test image and a probe image. Consequently, developing an age-invariant platform continues to be a significant requirement for building an effective facial recognition system. The main objective of this work is to address the challenge of facial aging which affects the performance of facial recognition systems. Accordingly, this work presents a geometrical model that is based on extracting a number of triangular facial features. The proposed model comprises a total of six triangular areas connecting and surrounding the main facial features (i.e. eyes, nose and mouth). Furthermore, a set of thirty mathematical relationships are developed and used for building a feature vector for each sample image. The areas and perimeters of the extracted triangular areas are calculated and used as inputs for the developed mathematical relationships. The performance of the system is evaluated over the publicly available face and gesture recognition research network (FG-NET) face aging database. The performance of the system is compared with that of some of the state-of-the-art face recognition methods and state-of-the-art age-invariant face recognition systems. Our proposed system yielded a good performance in term of classification accuracy of more than 94%.