Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation.

There are various distributions of image histograms where regions form symmetrically or asymmetrically based on the frequency of the intensity levels inside the image. In pure image processing, the process of optimal thresholding tends to accurately separate each region in the image histogram to obtain the segmented image. Otsu's method is the most used technique in image segmentation. Otsu algorithm performs automatic image thresholding and returns the optimal threshold by maximizing between-class variance using the sum of Gaussian distribution for the intensity level in the histogram. There are various types of images where an intensity level has right-skewed histograms and does not fit with the between-class variance of the original Otsu algorithm. In this paper, we proposed an improvement of the between-class variance based on lognormal distribution, using the mean and the variance of the lognormal. The proposed model aims to handle the drawbacks of asymmetric distribution, especially for images with right-skewed intensity levels. Several images were tested for segmentation in the proposed model in parallel with the original Otsu method and the relevant work, including simulated images and Medical Resonance Imaging (MRI) of brain tumors. Two types of evaluation measures were used in this work based on unsupervised and supervised metrics. The proposed model showed superior results, and the segmented images indicated better threshold estimation against the original Otsu method and the related improvement.

Improving Minimum Cross-Entropy Thresholding for Segmentation of Infected Foregrounds in Medical Images Based on Mean Filters Approaches.

Mean-based thresholding methods are among the most popular techniques that are used for images segmentation. Thresholding is a fundamental process for many applications since it provides a good degree of intensity separation of given images. Minimum cross-entropy thresholding (MCET) is one of the widely used mean-based methods for images segmentation; it is based on a classical mean that remains steady and limited value. In this paper, to improve the efficiency of MCET, dedicated mean estimation approaches are proposed to be used with MCET, instead of using the classical mean. The proposed mean estimation approaches, for example, alpha trim, harmonic, contraharmonic, and geometric, tend to exclude the negative impact of the undesired parts from the mean computation process, such as noises, local outliers, and gray intensity levels, and then provide an improvement for the thresholding process that can reflect good segmentation results. The proposed technique adds a profound impact on accurate images segmentation. It can be extended to other applications in object detection. Three data sets of medical images were applied for segmentation in this paper, including magnetic resonance imaging (MRI) Alzheimer's, MRI brain tumor, and skin lesion. The unsupervised and supervised evaluations were used to conduct the efficiency of the proposed method.

A Boosted Minimum Cross Entropy Thresholding for Medical Images Segmentation Based on Heterogeneous Mean Filters Approaches.

Computer vision plays an important role in the accurate foreground detection of medical images. Diagnosing diseases in their early stages has effective life-saving potential, and this is every physician's goal. There is a positive relationship between improving image segmentation methods and precise diagnosis in medical images. This relation provides a profound indication for feature extraction in a segmented image, such that an accurate separation occurs between the foreground and the background. There are many thresholding-based segmentation methods found under the pure image processing approach. Minimum cross entropy thresholding (MCET) is one of the frequently used mean-based thresholding methods for medical image segmentation. In this paper, the aim was to boost the efficiency of MCET, based on heterogeneous mean filter approaches. The proposed model estimates an optimized mean by excluding the negative influence of noise, local outliers, and gray intensity levels; thus, obtaining new mean values for the MCET's objective function. The proposed model was examined compared to the original and related methods, using three types of medical image dataset. It was able to show accurate results based on the performance measures, using the benchmark of unsupervised and supervised evaluation.

An Optimized Approach for Prostate Image Segmentation Using K-Means Clustering Algorithm with Elbow Method.

Prostate cancer disease is one of the common types that cause men's prostate damage all over the world. Prostate-specific membrane antigen (PSMA) expressed by type-II is an extremely attractive style for imaging-based diagnosis of prostate cancer. Clinically, photodynamic therapy (PDT) is used as noninvasive therapy in treatment of several cancers and some other diseases. This paper aims to segment or cluster and analyze pixels of histological and near-infrared (NIR) prostate cancer images acquired by PSMA-targeting PDT low weight molecular agents. Such agents can provide image guidance to resection of the prostate tumors and permit for the subsequent PDT in order to remove remaining or noneradicable cancer cells. The color prostate image segmentation is accomplished using an optimized image segmentation approach. The optimized approach combines the k-means clustering algorithm with elbow method that can give better clustering of pixels through automatically determining the best number of clusters. Clusters' statistics and ratio results of pixels in the segmented images show the applicability of the proposed approach for giving the optimum number of clusters for prostate cancer analysis and diagnosis.

Feature selection with ensemble learning for prostate cancer diagnosis from microarray gene expression.

Cancer diagnosis using machine learning algorithms is one of the main topics of research in computer-based medical science. Prostate cancer is considered one of the reasons that are leading to deaths worldwide. Data analysis of gene expression from microarray using machine learning and soft computing algorithms is a useful tool for detecting prostate cancer in medical diagnosis. Even though traditional machine learning methods have been successfully applied for detecting prostate cancer, the large number of attributes with a small sample size of microarray data is still a challenge that limits their ability for effective medical diagnosis. Selecting a subset of relevant features from all features and choosing an appropriate machine learning method can exploit the information of microarray data to improve the accuracy rate of detection. In this paper, we propose to use a correlation feature selection (CFS) method with random committee (RC) ensemble learning to detect prostate cancer from microarray data of gene expression. A set of experiments are conducted on a public benchmark dataset using 10-fold cross-validation technique to evaluate the proposed approach. The experimental results revealed that the proposed approach attains 95.098% accuracy, which is higher than related work methods on the same dataset.

Expectation-maximization technique for fibro-glandular discs detection in mammography images.

Breast cancer is among the leading causes of death in women worldwide. Mammography is the most effective imaging method for detecting no-palpable early-stage breast cancer. Understanding the nature of data in mammography images is very important for developing a model that fits well the data. Statistical distributions are widely used on the modelling of the data. Gamma distribution is more suitable than Gaussian distribution for modelling the data in mammography images. In this paper, we will use Gamma distribution to model the data in mammography images. The histogram of images can be seen as a mixture of Gamma distributions. Thresholds are selected at the valleys of a multi-modal histogram. The estimation of thresholds is based on the statistical parameters of the histogram. The expectation-maximization technique with gamma distribution (EMTG) is therefore developed to estimate the statistical histogram parameters. The experimental results on mammography images using this technique showed improvement in the accuracy in detection of the fibro-glandular discs.