Authors :
D. Kalaivani; Dr.G.Dheepa
Volume/Issue :
Volume 8 - 2023, Issue 5 - May
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://tinyurl.com/4vjswmv8
DOI :
https://doi.org/10.5281/zenodo.8041458
Abstract :
According to the estimated reports of World
Health Organization, with over 2.6 million new cases
captured and diagnosed each year, lung cancer is the
most prevalent cause of cancer-related deaths
worldwide. Early detection and classification of LC is
needed for effective analysis & treatments for better
patient outcomes. Lung cancer prediction and
classification at an early stage have shown significant
potential for advanced ML algorithms, particularly DL
models. Early detection of lung cancer facilitates
patients to undergo timely and effective treatment,
considerably improving their chances of survival. The
purpose of this research is to put forward an ISBSSA
(Improved Selection Based Squirrel Search Algorithm)-
based machine learning approach for LC prediction and
classification employing CT-SCAN illustrations. The
suggested method makes use of a deep learning model
called ISBSSA that has been trained on a substantial
dataset of computed tomography (CT) images in order
to accurately identify and classify lung cancer cells. For
the experimental study, a Large-Scale CT and PET/CT
Dataset for Lung Cancer Diagnosis took from Cancer
Imaging Archive (CIA) serves as the data source. The
LC-CIA dataset which includes CT and PET-CT
DICOM pictures of lung cancer patients as well as
individuals who are healthy. The model is trained using
appropriate machine learning algorithms along with
ISBSSA such Naive Bayes Algorithm (NBA),
Convolutional Neural Networks (CNNs), Support Vector
Machines (SVMs), K-Nearest Neighbour (KNN) and
Random Forests (RFs), to predict the presence and type
of lung cancer cells in the CT & PET-CT DICOM
images which was extracted. The findings of this study
show that the proposed approach is successful in
effectively predicting and classifying lung cancer cells in
CT scans, which might have significant implications for
the early detection and treatment of the disease.the
HD in an effective manner, which is the advantage of
employing ML and DL approaches.
Keywords :
Lung Cancer Prediction, Classification, Machine Learning, Deep Learning, Feature Selection, Data Mining, Image Processing.
According to the estimated reports of World
Health Organization, with over 2.6 million new cases
captured and diagnosed each year, lung cancer is the
most prevalent cause of cancer-related deaths
worldwide. Early detection and classification of LC is
needed for effective analysis & treatments for better
patient outcomes. Lung cancer prediction and
classification at an early stage have shown significant
potential for advanced ML algorithms, particularly DL
models. Early detection of lung cancer facilitates
patients to undergo timely and effective treatment,
considerably improving their chances of survival. The
purpose of this research is to put forward an ISBSSA
(Improved Selection Based Squirrel Search Algorithm)-
based machine learning approach for LC prediction and
classification employing CT-SCAN illustrations. The
suggested method makes use of a deep learning model
called ISBSSA that has been trained on a substantial
dataset of computed tomography (CT) images in order
to accurately identify and classify lung cancer cells. For
the experimental study, a Large-Scale CT and PET/CT
Dataset for Lung Cancer Diagnosis took from Cancer
Imaging Archive (CIA) serves as the data source. The
LC-CIA dataset which includes CT and PET-CT
DICOM pictures of lung cancer patients as well as
individuals who are healthy. The model is trained using
appropriate machine learning algorithms along with
ISBSSA such Naive Bayes Algorithm (NBA),
Convolutional Neural Networks (CNNs), Support Vector
Machines (SVMs), K-Nearest Neighbour (KNN) and
Random Forests (RFs), to predict the presence and type
of lung cancer cells in the CT & PET-CT DICOM
images which was extracted. The findings of this study
show that the proposed approach is successful in
effectively predicting and classifying lung cancer cells in
CT scans, which might have significant implications for
the early detection and treatment of the disease.the
HD in an effective manner, which is the advantage of
employing ML and DL approaches.
Keywords :
Lung Cancer Prediction, Classification, Machine Learning, Deep Learning, Feature Selection, Data Mining, Image Processing.