Cargando…
Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection
SIMPLE SUMMARY: In this work, an improved pipeline for Leukocytes subtype classification is proposed which uses transfer learning for deep feature extraction and a quantum inspired evolutionary algorithm for feature selection. The proposed system achieves a high accuracy with smaller number of featu...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10177199/ https://www.ncbi.nlm.nih.gov/pubmed/37173974 http://dx.doi.org/10.3390/cancers15092507 |
_version_ | 1785040581593923584 |
---|---|
author | Ahmad, Riaz Awais, Muhammad Kausar, Nabeela Tariq, Usman Cha, Jae-Hyuk Balili, Jamel |
author_facet | Ahmad, Riaz Awais, Muhammad Kausar, Nabeela Tariq, Usman Cha, Jae-Hyuk Balili, Jamel |
author_sort | Ahmad, Riaz |
collection | PubMed |
description | SIMPLE SUMMARY: In this work, an improved pipeline for Leukocytes subtype classification is proposed which uses transfer learning for deep feature extraction and a quantum inspired evolutionary algorithm for feature selection. The proposed system achieves a high accuracy with smaller number of features as compared to the classical methods. ABSTRACT: Leukocytes, also referred to as white blood cells (WBCs), are a crucial component of the human immune system. Abnormal proliferation of leukocytes in the bone marrow leads to leukemia, a fatal blood cancer. Classification of various subtypes of WBCs is an important step in the diagnosis of leukemia. The method of automated classification of WBCs using deep convolutional neural networks is promising to achieve a significant level of accuracy, but suffers from high computational costs due to very large feature sets. Dimensionality reduction through intelligent feature selection is essential to improve the model performance with reduced computational complexity. This work proposed an improved pipeline for subtype classification of WBCs that relies on transfer learning for feature extraction using deep neural networks, followed by a wrapper feature selection approach based on a customized quantum-inspired evolutionary algorithm (QIEA). This algorithm, inspired by the principles of quantum physics, outperforms classical evolutionary algorithms in the exploration of search space. The reduced feature vector obtained from QIEA was then classified with multiple baseline classifiers. In order to validate the proposed methodology, a public dataset of 5000 images of five subtypes of WBCs was used. The proposed system achieves a classification accuracy of about 99% with a reduction of 90% in the size of the feature vector. The proposed feature selection method also shows a better convergence performance as compared to the classical genetic algorithm and a comparable performance to several existing works. |
format | Online Article Text |
id | pubmed-10177199 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-101771992023-05-13 Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection Ahmad, Riaz Awais, Muhammad Kausar, Nabeela Tariq, Usman Cha, Jae-Hyuk Balili, Jamel Cancers (Basel) Article SIMPLE SUMMARY: In this work, an improved pipeline for Leukocytes subtype classification is proposed which uses transfer learning for deep feature extraction and a quantum inspired evolutionary algorithm for feature selection. The proposed system achieves a high accuracy with smaller number of features as compared to the classical methods. ABSTRACT: Leukocytes, also referred to as white blood cells (WBCs), are a crucial component of the human immune system. Abnormal proliferation of leukocytes in the bone marrow leads to leukemia, a fatal blood cancer. Classification of various subtypes of WBCs is an important step in the diagnosis of leukemia. The method of automated classification of WBCs using deep convolutional neural networks is promising to achieve a significant level of accuracy, but suffers from high computational costs due to very large feature sets. Dimensionality reduction through intelligent feature selection is essential to improve the model performance with reduced computational complexity. This work proposed an improved pipeline for subtype classification of WBCs that relies on transfer learning for feature extraction using deep neural networks, followed by a wrapper feature selection approach based on a customized quantum-inspired evolutionary algorithm (QIEA). This algorithm, inspired by the principles of quantum physics, outperforms classical evolutionary algorithms in the exploration of search space. The reduced feature vector obtained from QIEA was then classified with multiple baseline classifiers. In order to validate the proposed methodology, a public dataset of 5000 images of five subtypes of WBCs was used. The proposed system achieves a classification accuracy of about 99% with a reduction of 90% in the size of the feature vector. The proposed feature selection method also shows a better convergence performance as compared to the classical genetic algorithm and a comparable performance to several existing works. MDPI 2023-04-27 /pmc/articles/PMC10177199/ /pubmed/37173974 http://dx.doi.org/10.3390/cancers15092507 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Ahmad, Riaz Awais, Muhammad Kausar, Nabeela Tariq, Usman Cha, Jae-Hyuk Balili, Jamel Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection |
title | Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection |
title_full | Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection |
title_fullStr | Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection |
title_full_unstemmed | Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection |
title_short | Leukocytes Classification for Leukemia Detection Using Quantum Inspired Deep Feature Selection |
title_sort | leukocytes classification for leukemia detection using quantum inspired deep feature selection |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10177199/ https://www.ncbi.nlm.nih.gov/pubmed/37173974 http://dx.doi.org/10.3390/cancers15092507 |
work_keys_str_mv | AT ahmadriaz leukocytesclassificationforleukemiadetectionusingquantuminspireddeepfeatureselection AT awaismuhammad leukocytesclassificationforleukemiadetectionusingquantuminspireddeepfeatureselection AT kausarnabeela leukocytesclassificationforleukemiadetectionusingquantuminspireddeepfeatureselection AT tariqusman leukocytesclassificationforleukemiadetectionusingquantuminspireddeepfeatureselection AT chajaehyuk leukocytesclassificationforleukemiadetectionusingquantuminspireddeepfeatureselection AT balilijamel leukocytesclassificationforleukemiadetectionusingquantuminspireddeepfeatureselection |