Methods Used in Computer-Aided Diagnosis for Breast Cancer Detection Using Mammograms: A Review

According to the American Cancer Society's forecasts for 2019, there will be about 268,600 new cases in the United States with invasive breast cancer in women, about 62,930 new noninvasive cases, and about 41,760 death cases from breast cancer. As a result, there is a high demand for breast imaging specialists as indicated in a recent report for the Institute of Medicine and National Research Council. One way to meet this demand is through developing Computer-Aided Diagnosis (CAD) systems for breast cancer detection and diagnosis using mammograms. This study aims to review recent advancements and developments in CAD systems for breast cancer detection and diagnosis using mammograms and to give an overview of the methods used in its steps starting from preprocessing and enhancement step and ending in classification step. The current level of performance for the CAD systems is encouraging but not enough to make CAD systems standalone detection and diagnose clinical systems. Unless the performance of CAD systems enhanced dramatically from its current level by enhancing the existing methods, exploiting new promising methods in pattern recognition like data augmentation in deep learning and exploiting the advances in computational power of computers, CAD systems will continue to be a second opinion clinical procedure.

Remote Sensing Image Change Detection Based on NSCT-HMT Model and Its Application

Traditional image change detection based on a non-subsampled contourlet transform always ignores the neighborhood information’s relationship to the non-subsampled contourlet coefficients, and the detection results are susceptible to noise interference. To address these disadvantages, we propose a denoising method based on the non-subsampled contourlet transform domain that uses the Hidden Markov Tree model (NSCT-HMT) for change detection of remote sensing images. First, the ENVI software is used to calibrate the original remote sensing images. After that, the mean-ratio operation is adopted to obtain the difference image that will be denoised by the NSCT-HMT model. Then, using the Fuzzy Local Information C-means (FLICM) algorithm, the difference image is divided into the change area and unchanged area. The proposed algorithm is applied to a real remote sensing data set. The application results show that the proposed algorithm can effectively suppress clutter noise, and retain more detailed information from the original images. The proposed algorithm has higher detection accuracy than the Markov Random Field-Fuzzy C-means (MRF-FCM), the non-subsampled contourlet transform-Fuzzy C-means clustering (NSCT-FCM), the pointwise approach and graph theory (PA-GT), and the Principal Component Analysis-Nonlocal Means (PCA-NLM) denosing algorithm. Finally, the five algorithms are used to detect the southern boundary of the Gurbantunggut Desert in Xinjiang Uygur Autonomous Region of China, and the results show that the proposed algorithm has the best effect on real remote sensing image change detection.

Wavelet modeling using finite mixtures of generalized gaussian distributions: application to texture discrimination and retrieval

This paper addresses statistical-based texture modeling using wavelets. We propose a new approach to represent the marginal distribution of the wavelet coefficients using finite mixtures of generalized Gaussian (MoGG) distributions. The MoGG captures a wide range of histogram shapes, which provides better description and discrimination of texture than using single probability density functions (pdf's), as proposed by recent state-of-the-art approaches. Moreover, we propose a model similarity measure based on Kullback-Leibler divergence (KLD) approximation using Monte Carlo sampling methods. Through experiments on two popular texture data sets, we show that our approach yields significant performance improvements for texture discrimination and retrieval, as compared with recent methods of statistical-based wavelet modeling.

Artificial Neural Network-Based System for PET Volume Segmentation

Tumour detection, classification, and quantification in positron emission tomography (PET) imaging at early stage of disease are important issues for clinical diagnosis, assessment of response to treatment, and radiotherapy planning. Many techniques have been proposed for segmenting medical imaging data; however, some of the approaches have poor performance, large inaccuracy, and require substantial computation time for analysing large medical volumes. Artificial intelligence (AI) approaches can provide improved accuracy and save decent amount of time. Artificial neural networks (ANNs), as one of the best AI techniques, have the capability to classify and quantify precisely lesions and model the clinical evaluation for a specific problem. This paper presents a novel application of ANNs in the wavelet domain for PET volume segmentation. ANN performance evaluation using different training algorithms in both spatial and wavelet domains with a different number of neurons in the hidden layer is also presented. The best number of neurons in the hidden layer is determined according to the experimental results, which is also stated Levenberg-Marquardt backpropagation training algorithm as the best training approach for the proposed application. The proposed intelligent system results are compared with those obtained using conventional techniques including thresholding and clustering based approaches. Experimental and Monte Carlo simulated PET phantom data sets and clinical PET volumes of nonsmall cell lung cancer patients were utilised to validate the proposed algorithm which has demonstrated promising results.

A fast nonparametric noncausal MRF-based texture synthesis scheme using a novel FKDE algorithm

In this paper, a new algorithm is proposed for fast kernel density estimation (FKDE), based on principal direction divisive partitioning (PDDP) of the data space. A new framework is also developed to apply FKDE algorithms (both proposed and existing), within nonparametric noncausal Markov random field (NNMRF) based texture synthesis algorithm. The goal of the proposed FKDE algorithm is to use the finite support property of kernels for fast estimation of density. It has been shown that hyperplane boundaries for partitioning the data space and principal component vectors of the data space are two requirements for efficient FKDE. The proposed algorithm is compared with the earlier algorithms, with a number of high-dimensional data sets. The error and time complexity analysis, proves the efficiency of the proposed FKDE algorithm compared to the earlier algorithms. Due to the local simulated annealing, direct incorporation of the FKDE algorithms within the NNMRF-based texture synthesis algorithm, is not possible. This work proposes a new methodology to incorporate the effect of local simulated annealing within the FKDE framework. Afterward, the developed texture synthesis algorithms have been tested with a number of different natural textures, taken from a standard database. The comparison in terms of visual similarity and time complexity, between the proposed FKDE based texture synthesis algorithm with the earlier algorithms, show the efficiency.

Automatic image segmentation by dynamic region growth and multiresolution merging

Image segmentation is a fundamental task in many computer vision applications. In this paper, we propose a new unsupervised color image segmentation algorithm, which exploits the information obtained from detecting edges in color images in the CIE L *a *b * color space. To this effect, by using a color gradient detection technique, pixels without edges are clustered and labeled individually to identify some initial portion of the input image content. Elements that contain higher gradient densities are included by the dynamic generation of clusters as the algorithm progresses. Texture modeling is performed by color quantization and local entropy computation of the quantized image. The obtained texture and color information along with a region growth map consisting of all fully grown regions are used to perform a unique multiresolution merging procedure to blend regions with similar characteristics. Experimental results obtained in comparison to published segmentation techniques demonstrate the performance advantages of the proposed method.

Hierarchical multiple Markov chain model for unsupervised texture segmentation

In this paper, we present a novel multiscale texture model and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled, in turn, by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The "fragmentation" step allows one to find the elementary textures of the model, while the "reconstruction" step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural and remote sensing images.

Wavelet feature selection for image classification

Energy distribution over wavelet subbands is a widely used feature for wavelet packet based texture classification. Due to the overcomplete nature of the wavelet packet decomposition, feature selection is usually applied for a better classification accuracy and a compact feature representation. The majority of wavelet feature selection algorithms conduct feature selection based on the evaluation of each subband separately, which implicitly assumes that the wavelet features from different subbands are independent. In this paper, the dependence between features from different subbands is investigated theoretically and simulated for a given image model. Based on the analysis and simulation, a wavelet feature selection algorithm based on statistical dependence is proposed. This algorithm is further improved by combining the dependence between wavelet feature and the evaluation of individual feature component. Experimental results show the effectiveness of the proposed algorithms in incorporating dependence into wavelet feature selection.

Biofilm structure differentiation based on multi-resolution analysis

Quantitative parameters for describing the morphology of biofilms are crucial towards establishing the influence of growing conditions on biofilm structure. Parameters used in earlier studies generally fail to differentiate complex three-dimensional structures. This article presents a novel approach of defining a parameter vector based on the energy signature of multi-resolution analysis, which was applied to differentiating biofilm structures from confocal laser scanning microscopy (CLSM) biofilm images. The parameter vector distinguished differences in the spatial arrangements of synthetic images. For real CLSM images, this parameter vector detected subtle differences in biofilm structure for three sample cases: (1) two adjacent images of a CLSM stack; (2) two partial stacks from the same CLSM stack with equal numbers of images but spatially offset by one image; and (3) three complete CLSM stacks from different bacterial strains. It was also observed that filtering the noise in CLSM images enhanced the sensitivity of the differentiation using our parameter vector.

SVD-based modeling for image texture classification using wavelet transformation

This paper introduces a new model for image texture classification based on wavelet transformation and singular value decomposition. The probability density function of the singular values of wavelet transformation coefficients of image textures is modeled as an exponential function. The model parameter of the exponential function is estimated using maximum likelihood estimation technique. Truncation of lower singular values is employed to classify textures in the presence of noise. Kullback-Leibler distance (KLD) between estimated model parameters of image textures is used as a similarity metric to perform the classification using minimum distance classifier. The exponential function permits us to have closed-form expressions for the estimate of the model parameter and computation of the KLD. These closed-form expressions reduce the computational complexity of the proposed approach. Experimental results are presented to demonstrate the effectiveness of this approach on the entire 111 textures from Brodatz database. The experimental results demonstrate that the proposed approach improves recognition rates using a lower number of parameters on large databases. The proposed approach achieves higher recognition rates compared to the traditional sub-band energy-based approach, the hybrid IMM/SVM approach, and the GGD-based approach.

Directional multiscale modeling of images using the contourlet transform

The contourlet transform is a new two-dimensional extension of the wavelet transform using multiscale and directional filter banks. The contourlet expansion is composed of basis images oriented at various directions in multiple scales, with flexible aspect ratios. Given this rich set of basis images, the contourlet transform effectively captures smooth contours that are the dominant feature in natural images. We begin with a detailed study on the statistics of the contourlet coefficients of natural images: using histograms to estimate the marginal and joint distributions and mutual information to measure the dependencies between coefficients. This study reveals the highly non-Gaussian marginal statistics and strong interlocation, interscale, and interdirection dependencies of contourlet coefficients. We also find that conditioned on the magnitudes of their generalized neighborhood coefficients, contourlet coefficients can be approximately modeled as Gaussian random variables. Based on these findings, we model contourlet coefficients using a hidden Markov tree (HMT) model with Gaussian mixtures that can capture all interscale, interdirection, and interlocation dependencies. We present experimental results using this model in image denoising and texture retrieval applications. In denoising, the contourlet HMT outperforms other wavelet methods in terms of visual quality, especially around edges. In texture retrieval, it shows improvements in performance for various oriented textures.

A new texture generation method based on pseudo-DCT coefficients

In this paper, a new method for generating different texture images is presented. This method involves a simple transform from a certain one-dimensional (1-D) signal to an expected two-dimensional (2-D) image. Unlike traditional methods, the input signal is generated by a simple 1-D function in our work instead of a sample texture. We first transform the 1-D input signal into frequency domain using fast Fourier transform. Based on the sufficient analysis in 2-D discrete cosine transform (DCT) domain, where each of the coefficients expresses a texture feature in a certain direction, the 2-D pseudo-DCT coefficients are then constructed by appropriately rearranging the Fourier coefficients in terms of their frequency components. Finally, the corresponding texture image can be produced by 2-D inverse DCT algorithm. We applied the proposed method to generate several stochastic textures (i.e., cloud, illumination, and sand), and several structural texture images. Experimental results indicate the good performance of the proposed method.

Varying complexity in tree-structured image distribution models

Probabilistic models of image statistics underlie many approaches in image analysis and processing. An important class of such models have variables whose dependency graph is a tree. If the hidden variables take values on a finite set, most computations with the model can be performed exactly, including the likelihood calculation, training with the EM algorithm, etc. Crouse et al. developed one such model, the hidden Markov tree (HMT). They took particular care to limit the complexity of their model. We argue that it is beneficial to allow more complex tree-structured models, describe the use of information theoretic penalties to choose the model complexity, and present experimental results to support these proposals. For these experiments, we use what we call the hierarchical image probability (HIP) model. The differences between the HIP and the HMT models include the use of multivariate Gaussians to model the distributions of local vectors of wavelet coefficients and the use of different numbers of hidden states at each resolution. We demonstrate the broad utility of image distributions by applying the HIP model to classification, synthesis, and compression, across a variety of image types, namely, electrooptical, synthetic aperture radar, and mammograms (digitized X-rays). In all cases, we compare with the HMT.

Adaptive scale fixing for multiscale texture segmentation

This paper addresses two challenging issues in unsupervised multiscale texture segmentation: determining adequate spatial and feature resolutions for different regions of the image, and utilizing information across different scales/resolutions. The center of a homogeneous texture is analyzed using coarse spatial resolution, and its border is detected using fine spatial resolution so as to locate the boundary accurately. The extraction of texture features is achieved via a multiresolution pyramid. The feature values are integrated across scales/resolutions adaptively. The number of textures is determined automatically using the variance ratio criterion. Experimental results on synthetic and real images demonstrate the improvement in performance of the proposed multiscale scheme over single scale approaches.

Using wavelets to analyze AFM images of thin films: surface micelles and supported lipid bilayers

This paper presents micro- and nanoanalysis of thin films based on images obtained by atomic force microscopy (AFM). The analysis exploits the discrete wavelet transform and the resulting wavelet spectrum to study surface features. It is demonstrated that the wavelet technique can characterize micro- and nanosurface features and distinguish between similar surface structures. The use of a feature extraction method is shown. The method involves the separation of certain frequency content from the original AFM images and analyzing the data independently to gain quantitative information about the images. By using the feature extraction method, soft surfaces in water are analyzed and nanofeatures are measured. The packing of surface micelles of sodium dodecyl sulfate on a self-assembled monolayer is analyzed. The characteristics of pore formation, due to penetration of the antibacterial peptide protegrin, into a solid-supported lipid bilayer are quantified. The sizes of the pores are obtained, and it is observed that the line tension of the pores reduces the fluctuations of the lipid bilayer.