An investigation of machine learning methods in delta-radiomics feature analysis.
PURPOSE:This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delt...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2019-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0226348 |
| _version_ | 1818824311916462080 |
|---|---|
| author | Yushi Chang Kyle Lafata Wenzheng Sun Chunhao Wang Zheng Chang John P Kirkpatrick Fang-Fang Yin |
| author_facet | Yushi Chang Kyle Lafata Wenzheng Sun Chunhao Wang Zheng Chang John P Kirkpatrick Fang-Fang Yin |
| author_sort | Yushi Chang |
| collection | DOAJ |
| description | PURPOSE:This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS:The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS:For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS:The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification. |
| first_indexed | 2024-12-18T23:53:52Z |
| format | Article |
| id | doaj.art-a3226a2590534699be3d5b7a5ed0d6be |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-18T23:53:52Z |
| publishDate | 2019-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-a3226a2590534699be3d5b7a5ed0d6be2022-12-21T20:46:48ZengPublic Library of Science (PLoS)PLoS ONE1932-62032019-01-011412e022634810.1371/journal.pone.0226348An investigation of machine learning methods in delta-radiomics feature analysis.Yushi ChangKyle LafataWenzheng SunChunhao WangZheng ChangJohn P KirkpatrickFang-Fang YinPURPOSE:This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS:The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS:For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS:The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.https://doi.org/10.1371/journal.pone.0226348 |
| spellingShingle | Yushi Chang Kyle Lafata Wenzheng Sun Chunhao Wang Zheng Chang John P Kirkpatrick Fang-Fang Yin An investigation of machine learning methods in delta-radiomics feature analysis. PLoS ONE |
| title | An investigation of machine learning methods in delta-radiomics feature analysis. |
| title_full | An investigation of machine learning methods in delta-radiomics feature analysis. |
| title_fullStr | An investigation of machine learning methods in delta-radiomics feature analysis. |
| title_full_unstemmed | An investigation of machine learning methods in delta-radiomics feature analysis. |
| title_short | An investigation of machine learning methods in delta-radiomics feature analysis. |
| title_sort | investigation of machine learning methods in delta radiomics feature analysis |
| url | https://doi.org/10.1371/journal.pone.0226348 |
| work_keys_str_mv | AT yushichang aninvestigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT kylelafata aninvestigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT wenzhengsun aninvestigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT chunhaowang aninvestigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT zhengchang aninvestigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT johnpkirkpatrick aninvestigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT fangfangyin aninvestigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT yushichang investigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT kylelafata investigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT wenzhengsun investigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT chunhaowang investigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT zhengchang investigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT johnpkirkpatrick investigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis AT fangfangyin investigationofmachinelearningmethodsindeltaradiomicsfeatureanalysis |