scholarly journals An Effective and Efficient Feature Selection Method for Lung Cancer Detection

2015 ◽  
Vol 7 (4) ◽  
pp. 135-141 ◽  
Author(s):  
Kishore R
Keyword(s):  
Lung Cancer ◽  
Feature Selection ◽  
Cancer Detection ◽  
Feature Selection Method ◽  
Selection Method ◽  
Lung Cancer Detection

scholarly journals Predicting Lung Cancer Patients’ Survival Time via Logistic Regression-based Models in a Quantitative Radiomic Framework

2019 ◽  
Author(s):  
S P Shayesteh ◽  
I Shiri ◽  
A H Karami ◽  
R Hashemian ◽  
S Kooranifar ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Logistic Regression ◽  
Feature Selection ◽  
Mutual Information ◽  
Cancer Patients ◽  
Feature Selection Method ◽  
Selection Method ◽  
Classification Models ◽  
Lung Cancer Patients ◽  
Pre Treatment

Objectives: The aim of this study was to predict the survival time of lung cancer patients using the advantages of both radiomics and logistic regression-based classification models.Material and Methods: Fifty-nine patients with primary lung adenocarcinoma were included in this retrospective study and pre-treatment contrast-enhanced CT images were acquired. The patients lived more than 2 years were classified as the ‘Alive’ class and otherwise as the ‘Dead’ class. In our proposed quantitative radiomic framework, we first extracted the associated regions of each lung lesion from pre-treatment CT images for each patient via grow cut segmentation algorithm. Then, 40 radiomic features were extracted from the segmented lung lesions. In order to enhance the generalizability of the classification models, the mutual information-based feature selection method was applied to each feature vector. We investigated the performance of six logistic regression-based classification models with consider to acceptable evaluation measures such as F1 score and accuracy.Results: It was observed that the mutual information feature selection method can help the classifier to achieve better predictive results. In our study, the Logistic regression (LR) and Dual Coordinate Descent method for Logistic Regression (DCD-LR) models achieved the best results indicating that these classification models have strong potential for classifying the more important class (i.e., the ‘Alive’ class).Conclusion: The proposed quantitative radiomic framework yielded promising results, which can guide physicians to make better and more precise decisions and increase the chance of treatment success.

scholarly journals Lung Cancer Detection Using Chi-Square Feature Selection and Support Vector Machine Algorithm

2021 ◽  
Vol 10 (3) ◽  
pp. 2050-2060
Keyword(s):  
Lung Cancer ◽  
Feature Selection ◽  
Cancer Detection ◽  
Execution Time ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Chi Square ◽  
Cancer Dataset ◽  
Lung Cancer Detection

Lung Cancer is the most general type of disease in theworld ofcancer. It affects the lungs of the human body. So, the prediction of lung cancer at its earlier stage is difficult. It is the deadliest cause of death in both men and women. Its symptoms are harder to recognize in the initial stages.Machine learning algorithms have made the prediction and detection of lung cancereasier. Chi-square is used for feature selection to select the relevant features in the lung cancer dataset. Different Machine Learning algorithms are used to predict Lung Cancer.The algorithmsutilized in the proposed work are SVM and Random Forest. We have compared these algorithms with and without feature selection (Chi-square). SVM is identified as the best algorithm in the proposed work due to its accuracy and less execution time for detecting the model. The key objective of this paper is to enhance the accuracy and reduce the execution time of the classifier.

Classification of lung cancer using ensemble-based feature selection and machine learning methods

2015 ◽  
Vol 11 (3) ◽  
pp. 791-800 ◽  
Author(s):  
Zhihua Cai ◽  
Dong Xu ◽  
Qing Zhang ◽  
Jiexia Zhang ◽  
Sai-Ming Ngai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lung Cancer ◽  
Feature Selection ◽  
Feature Selection Method ◽  
Selection Method ◽  
Learning Methods ◽  
Machine Learning Methods

The ensemble-based feature selection method presents the merit of acquisition of more informative and compact features than those obtained by individual methods.

Sign in / Sign up

Export Citation Format

Share Document