Mohammad Sadegh Helfroush

TL;DR: The proposed robust segmentation technique was designed based on the fact that if background and erythrocytes could be removed from the blood microscopic image, the remainder area will indicate leukocyte candidate regions and performs better than other available methods in terms of robustness and accuracy.

TL;DR: A new hybrid algorithm is proposed to identify the most relevant genes involved in breast cancer development using a combination of the teaching learning-based optimization (TLBO) algorithm and the proposed mutated fuzzy adaptive particle swarm optimization (PSO) algorithm.

TL;DR: A CAD for automatic analysis of breast cancer histopathological Images to count mitosis as an important criteria for the breast cancer grading is proposed and performs better than other methods proposed by other participants at ICPR2012.

TL;DR: The proposed single-channel method can be used for robust and reliable sleep stage scoring with high accuracy and relatively low complexity required for real time applications.

TL;DR: Three types of features with more flexibility and less complexity are employed in the proposed automatic mitosis detection method, and employing both a nonlinear radial basis function (RBF) kernel for support vector machine (SVM) and also random forest classifiers, leads to the best efficiencies among the other competitive methods.