Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer Fusion
A novel technique of automatically selecting the best pairs of features and sampling techniques to predict the stage of prostate cancer is proposed in this study. The problem of class imbalance, which is prominent in most medical data sets is also addressed here. Three feature subsets obtained by th...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SAGE Publishing
2009-01-01
|
Series: | Cancer Informatics |
Subjects: | |
Online Access: | http://www.la-press.com/staging-of-prostate-cancer-using-automatic-feature-selection-sampling--a1305 |
id |
doaj-30e7892545e04bf4863e0f9d635dd8aa |
---|---|
record_format |
Article |
spelling |
doaj-30e7892545e04bf4863e0f9d635dd8aa2020-11-25T02:46:19ZengSAGE PublishingCancer Informatics1176-93512009-01-0175773Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer FusionSandeep ChandanaHenry LeungKiril TrpkovA novel technique of automatically selecting the best pairs of features and sampling techniques to predict the stage of prostate cancer is proposed in this study. The problem of class imbalance, which is prominent in most medical data sets is also addressed here. Three feature subsets obtained by the use of principal components analysis (PCA), genetic algorithm (GA) and rough sets (RS) based approaches were also used in the study. The performance of under-sampling, synthetic minority over-sampling technique (SMOTE) and a combination of the two were also investigated and the performance of the obtained models was compared. To combine the classifier outputs, we used the Dempster-Shafer (DS) theory, whereas the actual choice of combined models was made using a GA. We found that the best performance for the overall system resulted from the use of under sampled data combined with rough sets based features modeled as a support vector machine (SVM).http://www.la-press.com/staging-of-prostate-cancer-using-automatic-feature-selection-sampling--a1305prostate cancerstagingclassifier fusion |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sandeep Chandana Henry Leung Kiril Trpkov |
spellingShingle |
Sandeep Chandana Henry Leung Kiril Trpkov Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer Fusion Cancer Informatics prostate cancer staging classifier fusion |
author_facet |
Sandeep Chandana Henry Leung Kiril Trpkov |
author_sort |
Sandeep Chandana |
title |
Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer Fusion |
title_short |
Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer Fusion |
title_full |
Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer Fusion |
title_fullStr |
Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer Fusion |
title_full_unstemmed |
Staging of Prostate Cancer Using Automatic Feature Selection, Sampling and Dempster-Shafer Fusion |
title_sort |
staging of prostate cancer using automatic feature selection, sampling and dempster-shafer fusion |
publisher |
SAGE Publishing |
series |
Cancer Informatics |
issn |
1176-9351 |
publishDate |
2009-01-01 |
description |
A novel technique of automatically selecting the best pairs of features and sampling techniques to predict the stage of prostate cancer is proposed in this study. The problem of class imbalance, which is prominent in most medical data sets is also addressed here. Three feature subsets obtained by the use of principal components analysis (PCA), genetic algorithm (GA) and rough sets (RS) based approaches were also used in the study. The performance of under-sampling, synthetic minority over-sampling technique (SMOTE) and a combination of the two were also investigated and the performance of the obtained models was compared. To combine the classifier outputs, we used the Dempster-Shafer (DS) theory, whereas the actual choice of combined models was made using a GA. We found that the best performance for the overall system resulted from the use of under sampled data combined with rough sets based features modeled as a support vector machine (SVM). |
topic |
prostate cancer staging classifier fusion |
url |
http://www.la-press.com/staging-of-prostate-cancer-using-automatic-feature-selection-sampling--a1305 |
work_keys_str_mv |
AT sandeepchandana stagingofprostatecancerusingautomaticfeatureselectionsamplinganddempstershaferfusion AT henryleung stagingofprostatecancerusingautomaticfeatureselectionsamplinganddempstershaferfusion AT kiriltrpkov stagingofprostatecancerusingautomaticfeatureselectionsamplinganddempstershaferfusion |
_version_ |
1724759216269295616 |