Year-end Sale % OFF 
Abstract
In this research, we propose an intelligent decision support system for acute lymphoblastic leukaemia (ALL) diagnosis using microscopic images. Two Bare-bones Particle Swarm Optimization (BBPSO) algorithms are proposed to identify the most significant discriminative characteristics of healthy and blast cells to enable efficient ALL classification. The first BBPSO variant incorporates accelerated chaotic search mechanisms of food chasing and enemy avoidance to diversify the search and mitigate the premature convergence of the original BBPSO algorithm. The second BBPSO variant exhibits both of the abovementioned new search mechanisms in a subswarm-based search. Evaluated with the ALL-IDB2 database, both proposed algorithms achieve superior geometric mean performances of 94.94% and 96.25%, respectively, and outperform other metaheuristic search and related methods significantly for ALL classification.
Highlights
Leukaemia is a type of cancer pertaining to white blood cells (WBCs), in which abnormal and immature WBCs are produced by the bone marrow and enter the bloodstream
Since identifying the most discriminative characteristics of normal and abnormal lymphocytic cells and removing the redundant features have a great impact in boosting classification accuracy, in this research, we propose two modified Bare-bones Particle Swarm Optimization (BBPSO) algorithms to identify significant discriminative feature subsets of healthy and blast cells from the 80 raw features to benefit subsequent robust acute lymphoblastic leukaemia (ALL) classification
The trained 1NN and Radial Basis Function (RBF)-based Support Vector Machine (SVM) models with hold-out validation have been employed for evaluation of all methods
Summary
Leukaemia is a type of cancer pertaining to white blood cells (WBCs), in which abnormal and immature WBCs are produced by the bone marrow and enter the bloodstream. In order to achieve robust and efficient computerized diagnosis, identifying the characteristics of healthy and blast cells is a crucial factor. Many studies on the separation and retrieval of the nucleus and cytoplasm or purely nuclei of the cells using segmentation techniques are available, limited investigations have been conducted on the selection of significant discriminative character-. This research aims to deal with the aforementioned challenges by proposing an intelligent decision support system with evolutionary feature optimization for robust ALL classification. We propose two Bare-bones Particle Swarm Optimization (BBPSO) algorithms to extract the most significant discriminative characteristics of normal and abnormal lymphocytic cells for ALL classification. The proposed BBPSO variants incorporate accelerated search mechanisms of attraction to the food source and avoidance of enemies to diversify the search and overcome premature convergence of the original BBPSO algorithm
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
