An evaluation and ranking of evolutionary algorithms in segmenting abnormal masses in digital mammograms

Breast cancer is the most common cancer in women worldwide and the second main cause of cancer mortality after lung cancer. Up to now, there still no prevention nor early symptoms of breast cancer. Early detection can decrease significantly the mortality rate as the disease can be treated at an early stage. X-Ray is the current screening method that helps in detecting the most two common abnormalities of the breast, masses and micro-calcifications. However, interpreting mammograms is challenging in dense breasts as the abnormal masses and the normal glandular tissue of the breast have similar characteristics. Recently, the evolutionary algorithms have been widely used in image segmentation. In this paper, we evaluate and compare the performance of six most used evolutionary algorithms, invasive weed optimization (IWO), genetic algorithm (GA), particle swarm optimization (PSO), electromagnetism-like optimization (EMO), ant colony optimization (ACO), and artificial bee colony (ABC) in terms of clustering abnormal masses in the breast, particularly dense and extremely dense breasts. This evaluation is conducted based on quantitative metrics including Cohen’s Kappa, correlation, and false positive and false negative rates. The evolutionary algorithms are then ranked based on two multi-criteria decision analysis methods, the Preference Ranking Organization Method for the Enrichment of Evaluations (PROMETHEE) and the Graphical Analysis for Interactive Aid (GAIA).

     

On the potential of polyetheretherketone matrix composites reinforced with ternary nanolaminates for tribological and biomedical applications

We report the synthesis and characterization of PEEK-MAX (Ti₃SiC₂, Ti₃AlC₂, and Cr₂AlC), and PEEK-MoAlB composites by hot-pressing. Detailed microstructure analysis by scanning electron microscopy showed that Ti₃SiC₂ particles are well dispersed in the PEEK matrix after the addition of 5 vol% Ti₃SiC₂ but at higher concentration (≥10 vol%), the Ti₃SiC₂ particles segregated at the phase boundaries and formed interpenetrating micro-networks. PEEK-Ti₃AlC₂ and PEEK-MoAlB composites also showed similar structuring at the microstructural level. PEEK-Cr₂AlC composites showed a different behavior where Cr₂AlC particles were well dispersed in the PEEK matrix. All the three PEEK-MAX composites have lower hardness than PEEK-MoAlB composites as MoAlB particulates are appreciably harder than MAX phases but were harder than PEEK. Due to heterogenous nucleation, the addition of MAX phases or MoAlB reduced the crystallization temperature (T_c) by a few ^oC. The formation of imperfect crystals also resulted in the lowering of melting point (T_m) of these composites. PEEK reinforced with 10 vol% Ti₃SiC₂, Ti₃AlC₂ and MoAlB showed plastic failure, and had higher strength than PEEK. Comparatively, PEEK reinforced with 10 vol% Cr₂AlC did not show any enhancement. All the PEEK-MAX and PEEK-MoAlB composites showed triboactive behavior and enhanced wear resistance.     

A performance comparison of measurement matrices in compressive sensing

Compressive sensing involves 3 main processes: signal sparse representation, linear encoding or measurement collection, and nonlinear decoding or sparse recovery. In the measurement process, a measurement matrix is used to sample only the components that best represent the signal. The choice of the measurement matrix has an important impact on the accuracy and the processing time of the sparse recovery process. Hence, the design of accurate measurement matrices is of vital importance in compressive sensing. Over the last decade, a number of measurement matrices have been proposed. Therefore, a detailed review of these measurement matrices and a comparison of their performances are strongly needed. This paper explains the foundation of compressive sensing and highlights the process of measurement by reviewing the existing measurement matrices. It provides a 3‐level classification and compares the performance of 8 measurement matrices belonging to 4 different types using 5 evaluation metrics: the recovery error, processing time, recovery time, covariance, and phase transition diagram. The theoretical performance comparison is validated with experimental results, and the results show that the Circulant, Toeplitz, and Hadamard matrices outperform the other measurement matrices.