Cargando…

An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification

The most dangerous disease in recent decades is lung cancer. The most accurate method of cancer diagnosis, according to research, is through the use of histopathological images that are acquired by a biopsy. Deep learning techniques have achieved success in bioinformatics, particularly medical imagi...

Descripción completa

Detalles Bibliográficos
Autores principales: Hamed, Esraa A.-R., Salem, Mohammed A.-M., Badr, Nagwa L., Tolba, Mohamed F.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10416893/
https://www.ncbi.nlm.nih.gov/pubmed/37568831
http://dx.doi.org/10.3390/diagnostics13152469
_version_ 1785087886744354816
author Hamed, Esraa A.-R.
Salem, Mohammed A.-M.
Badr, Nagwa L.
Tolba, Mohamed F.
author_facet Hamed, Esraa A.-R.
Salem, Mohammed A.-M.
Badr, Nagwa L.
Tolba, Mohamed F.
author_sort Hamed, Esraa A.-R.
collection PubMed
description The most dangerous disease in recent decades is lung cancer. The most accurate method of cancer diagnosis, according to research, is through the use of histopathological images that are acquired by a biopsy. Deep learning techniques have achieved success in bioinformatics, particularly medical imaging. In this paper, we present an innovative method for rapidly identifying and classifying histopathology images of lung tissues by combining a newly proposed Convolutional Neural Networks (CNN) model with a few total parameters and the enhanced Light Gradient Boosting Model (LightGBM) classifier. After the images have been pre-processed in this study, the proposed CNN technique is provided for feature extraction. Then, the LightGBM model with multiple threads has been used for lung tissue classification. The simulation result, applied to the LC25000 dataset, demonstrated that the novel technique successfully classifies lung tissue with 99.6% accuracy and sensitivity. Furthermore, the proposed CNN model has achieved the lowest training parameters of only one million parameters, and it has also achieved the shortest processing time of just one second throughout the feature extraction process. When this result is compared with the most recent state-of-the-art approaches, the suggested approach has increased effectiveness in the areas of both disease classification accuracy and processing time.
format Online
Article
Text
id pubmed-10416893
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104168932023-08-12 An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification Hamed, Esraa A.-R. Salem, Mohammed A.-M. Badr, Nagwa L. Tolba, Mohamed F. Diagnostics (Basel) Article The most dangerous disease in recent decades is lung cancer. The most accurate method of cancer diagnosis, according to research, is through the use of histopathological images that are acquired by a biopsy. Deep learning techniques have achieved success in bioinformatics, particularly medical imaging. In this paper, we present an innovative method for rapidly identifying and classifying histopathology images of lung tissues by combining a newly proposed Convolutional Neural Networks (CNN) model with a few total parameters and the enhanced Light Gradient Boosting Model (LightGBM) classifier. After the images have been pre-processed in this study, the proposed CNN technique is provided for feature extraction. Then, the LightGBM model with multiple threads has been used for lung tissue classification. The simulation result, applied to the LC25000 dataset, demonstrated that the novel technique successfully classifies lung tissue with 99.6% accuracy and sensitivity. Furthermore, the proposed CNN model has achieved the lowest training parameters of only one million parameters, and it has also achieved the shortest processing time of just one second throughout the feature extraction process. When this result is compared with the most recent state-of-the-art approaches, the suggested approach has increased effectiveness in the areas of both disease classification accuracy and processing time. MDPI 2023-07-25 /pmc/articles/PMC10416893/ /pubmed/37568831 http://dx.doi.org/10.3390/diagnostics13152469 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
Hamed, Esraa A.-R.
Salem, Mohammed A.-M.
Badr, Nagwa L.
Tolba, Mohamed F.
An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification
title An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification
title_full An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification
title_fullStr An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification
title_full_unstemmed An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification
title_short An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification
title_sort efficient combination of convolutional neural network and lightgbm algorithm for lung cancer histopathology classification
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10416893/
https://www.ncbi.nlm.nih.gov/pubmed/37568831
http://dx.doi.org/10.3390/diagnostics13152469
work_keys_str_mv AT hamedesraaar anefficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification
AT salemmohammedam anefficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification
AT badrnagwal anefficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification
AT tolbamohamedf anefficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification
AT hamedesraaar efficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification
AT salemmohammedam efficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification
AT badrnagwal efficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification
AT tolbamohamedf efficientcombinationofconvolutionalneuralnetworkandlightgbmalgorithmforlungcancerhistopathologyclassification