Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning Method
PurposeThe current study proposed a model to predict the response of brain metastases (BMs) treated by Gamma knife radiosurgery (GKRS) using a machine learning (ML) method with radiomics features. The model can be used as a decision tool by clinicians for the most desirable treatment outcome.Methods...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2020.569461/full |
| _version_ | 1818951819435442176 |
|---|---|
| author | Daisuke Kawahara Xueyan Tang Chung K. Lee Yasushi Nagata Yoichi Watanabe |
| author_facet | Daisuke Kawahara Xueyan Tang Chung K. Lee Yasushi Nagata Yoichi Watanabe |
| author_sort | Daisuke Kawahara |
| collection | DOAJ |
| description | PurposeThe current study proposed a model to predict the response of brain metastases (BMs) treated by Gamma knife radiosurgery (GKRS) using a machine learning (ML) method with radiomics features. The model can be used as a decision tool by clinicians for the most desirable treatment outcome.Methods and MaterialUsing MR image data taken by a FLASH (3D fast, low-angle shot) scanning protocol with gadolinium (Gd) contrast-enhanced T1-weighting, the local response (LR) of 157 metastatic brain tumors was categorized into two groups (Group I: responder and Group II: non-responder). We performed a radiomics analysis of those tumors, resulting in more than 700 features. To build a machine learning model, first, we used the least absolute shrinkage and selection operator (LASSO) regression to reduce the number of radiomics features to the minimum number of features useful for the prediction. Then, a prediction model was constructed by using a neural network (NN) classifier with 10 hidden layers and rectified linear unit activation. The training model was evaluated with five-fold cross-validation. For the final evaluation, the NN model was applied to a set of data not used for model creation. The accuracy and sensitivity and the area under the receiver operating characteristic curve (AUC) of the prediction model of LR were analyzed. The performance of the ML model was compared with a visual evaluation method, for which the LR of tumors was predicted by examining the image enhancement pattern of the tumor on MR images.ResultsBy the LASSO analysis of the training data, we found seven radiomics features useful for the classification. The accuracy and sensitivity of the visual evaluation method were 44 and 54%. On the other hand, the accuracy and sensitivity of the proposed NN model were 78 and 87%, and the AUC was 0.87.ConclusionsThe proposed NN model using the radiomics features can help physicians to gain a more realistic expectation of the treatment outcome than the traditional method. |
| first_indexed | 2024-12-20T09:40:32Z |
| format | Article |
| id | doaj.art-866bf8ddeb1d4d5aa452a7c54595ca76 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-20T09:40:32Z |
| publishDate | 2021-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-866bf8ddeb1d4d5aa452a7c54595ca762022-12-21T19:44:53ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-01-011010.3389/fonc.2020.569461569461Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning MethodDaisuke Kawahara0Xueyan Tang1Chung K. Lee2Yasushi Nagata3Yoichi Watanabe4Department of Radiation Oncology, Institute of Biomedical & Health Sciences, Hiroshima University, Hiroshima, JapanDepartment of Radiation Oncology, University of Minnesota-Twin Cities, Minneapolis, MN, United StatesDepartment of Radiation Oncology, University of Minnesota-Twin Cities, Minneapolis, MN, United StatesDepartment of Radiation Oncology, Institute of Biomedical & Health Sciences, Hiroshima University, Hiroshima, JapanDepartment of Radiation Oncology, University of Minnesota-Twin Cities, Minneapolis, MN, United StatesPurposeThe current study proposed a model to predict the response of brain metastases (BMs) treated by Gamma knife radiosurgery (GKRS) using a machine learning (ML) method with radiomics features. The model can be used as a decision tool by clinicians for the most desirable treatment outcome.Methods and MaterialUsing MR image data taken by a FLASH (3D fast, low-angle shot) scanning protocol with gadolinium (Gd) contrast-enhanced T1-weighting, the local response (LR) of 157 metastatic brain tumors was categorized into two groups (Group I: responder and Group II: non-responder). We performed a radiomics analysis of those tumors, resulting in more than 700 features. To build a machine learning model, first, we used the least absolute shrinkage and selection operator (LASSO) regression to reduce the number of radiomics features to the minimum number of features useful for the prediction. Then, a prediction model was constructed by using a neural network (NN) classifier with 10 hidden layers and rectified linear unit activation. The training model was evaluated with five-fold cross-validation. For the final evaluation, the NN model was applied to a set of data not used for model creation. The accuracy and sensitivity and the area under the receiver operating characteristic curve (AUC) of the prediction model of LR were analyzed. The performance of the ML model was compared with a visual evaluation method, for which the LR of tumors was predicted by examining the image enhancement pattern of the tumor on MR images.ResultsBy the LASSO analysis of the training data, we found seven radiomics features useful for the classification. The accuracy and sensitivity of the visual evaluation method were 44 and 54%. On the other hand, the accuracy and sensitivity of the proposed NN model were 78 and 87%, and the AUC was 0.87.ConclusionsThe proposed NN model using the radiomics features can help physicians to gain a more realistic expectation of the treatment outcome than the traditional method.https://www.frontiersin.org/articles/10.3389/fonc.2020.569461/fullradiomicsmachine learningbrain metastasesgamma kniferadiosurgerylocal control |
| spellingShingle | Daisuke Kawahara Xueyan Tang Chung K. Lee Yasushi Nagata Yoichi Watanabe Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning Method Frontiers in Oncology radiomics machine learning brain metastases gamma knife radiosurgery local control |
| title | Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning Method |
| title_full | Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning Method |
| title_fullStr | Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning Method |
| title_full_unstemmed | Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning Method |
| title_short | Predicting the Local Response of Metastatic Brain Tumor to Gamma Knife Radiosurgery by Radiomics With a Machine Learning Method |
| title_sort | predicting the local response of metastatic brain tumor to gamma knife radiosurgery by radiomics with a machine learning method |
| topic | radiomics machine learning brain metastases gamma knife radiosurgery local control |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2020.569461/full |
| work_keys_str_mv | AT daisukekawahara predictingthelocalresponseofmetastaticbraintumortogammakniferadiosurgerybyradiomicswithamachinelearningmethod AT xueyantang predictingthelocalresponseofmetastaticbraintumortogammakniferadiosurgerybyradiomicswithamachinelearningmethod AT chungklee predictingthelocalresponseofmetastaticbraintumortogammakniferadiosurgerybyradiomicswithamachinelearningmethod AT yasushinagata predictingthelocalresponseofmetastaticbraintumortogammakniferadiosurgerybyradiomicswithamachinelearningmethod AT yoichiwatanabe predictingthelocalresponseofmetastaticbraintumortogammakniferadiosurgerybyradiomicswithamachinelearningmethod |