Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics
This study aimed to investigate the feasibility of predicting oxygen 6-methylguanine-DNA methyltransferase (MGMT) promoter methylation in diffuse gliomas by developing a deep learning approach using MRI radiomics. A total of 111 patients with diffuse gliomas participated in the retrospective study (...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/11/12/3445 |
| _version_ | 1797485993842966528 |
|---|---|
| author | Sixuan Chen Yue Xu Meiping Ye Yang Li Yu Sun Jiawei Liang Jiaming Lu Zhengge Wang Zhengyang Zhu Xin Zhang Bing Zhang |
| author_facet | Sixuan Chen Yue Xu Meiping Ye Yang Li Yu Sun Jiawei Liang Jiaming Lu Zhengge Wang Zhengyang Zhu Xin Zhang Bing Zhang |
| author_sort | Sixuan Chen |
| collection | DOAJ |
| description | This study aimed to investigate the feasibility of predicting oxygen 6-methylguanine-DNA methyltransferase (MGMT) promoter methylation in diffuse gliomas by developing a deep learning approach using MRI radiomics. A total of 111 patients with diffuse gliomas participated in the retrospective study (56 patients with MGMT promoter methylation and 55 patients with MGMT promoter unmethylation). The radiomics features of the two regions of interest (ROI) (the whole tumor area and the tumor core area) for four sequences, including T1 weighted image (T1WI), T2 weighted image (T2WI), apparent diffusion coefficient (ADC) maps, and T1 contrast-enhanced (T1CE) MR images were extracted and jointly fed into the residual network. Then the deep learning method was developed and evaluated with a five-fold cross-validation, where in each fold, the dataset was randomly divided into training (80%) and validation (20%) cohorts. We compared the performance of all models using area under the curve (AUC) and average accuracy of validation cohorts and calculated the 10 most important features of the best model via a class activation map. Based on the ROI of the whole tumor, the predictive capacity of the T1CE and ADC model achieved the highest AUC value of 0.85. Based on the ROI of the tumor core, the T1CE and ADC model achieved the highest AUC value of 0.90. After comparison, the T1CE combined with the ADC model based on the ROI of the tumor core exhibited the best performance, with the highest average accuracy (0.91) and AUC (0.90) among all models. The deep learning method using MRI radiomics has excellent diagnostic performance with a high accuracy in predicting MGMT promoter methylation in diffuse gliomas. |
| first_indexed | 2024-03-09T23:27:47Z |
| format | Article |
| id | doaj.art-e8a9bacd33ba4cc0862ab3a37bc11a6e |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-09T23:27:47Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-e8a9bacd33ba4cc0862ab3a37bc11a6e2023-11-23T17:16:05ZengMDPI AGJournal of Clinical Medicine2077-03832022-06-011112344510.3390/jcm11123445Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with RadiomicsSixuan Chen0Yue Xu1Meiping Ye2Yang Li3Yu Sun4Jiawei Liang5Jiaming Lu6Zhengge Wang7Zhengyang Zhu8Xin Zhang9Bing Zhang10Department of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaNational Institute of Healthcare Data Science, Nanjing University, Nanjing 210023, ChinaDepartment of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaDepartment of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaSchool of Biological Science and Medical Engineering, Southeast University, Nanjing 211189, ChinaSchool of Biological Science and Medical Engineering, Southeast University, Nanjing 211189, ChinaDepartment of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaDepartment of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaDepartment of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaDepartment of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaDepartment of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, ChinaThis study aimed to investigate the feasibility of predicting oxygen 6-methylguanine-DNA methyltransferase (MGMT) promoter methylation in diffuse gliomas by developing a deep learning approach using MRI radiomics. A total of 111 patients with diffuse gliomas participated in the retrospective study (56 patients with MGMT promoter methylation and 55 patients with MGMT promoter unmethylation). The radiomics features of the two regions of interest (ROI) (the whole tumor area and the tumor core area) for four sequences, including T1 weighted image (T1WI), T2 weighted image (T2WI), apparent diffusion coefficient (ADC) maps, and T1 contrast-enhanced (T1CE) MR images were extracted and jointly fed into the residual network. Then the deep learning method was developed and evaluated with a five-fold cross-validation, where in each fold, the dataset was randomly divided into training (80%) and validation (20%) cohorts. We compared the performance of all models using area under the curve (AUC) and average accuracy of validation cohorts and calculated the 10 most important features of the best model via a class activation map. Based on the ROI of the whole tumor, the predictive capacity of the T1CE and ADC model achieved the highest AUC value of 0.85. Based on the ROI of the tumor core, the T1CE and ADC model achieved the highest AUC value of 0.90. After comparison, the T1CE combined with the ADC model based on the ROI of the tumor core exhibited the best performance, with the highest average accuracy (0.91) and AUC (0.90) among all models. The deep learning method using MRI radiomics has excellent diagnostic performance with a high accuracy in predicting MGMT promoter methylation in diffuse gliomas.https://www.mdpi.com/2077-0383/11/12/3445MGMT promoter methylationgliomadeep learningradiomic |
| spellingShingle | Sixuan Chen Yue Xu Meiping Ye Yang Li Yu Sun Jiawei Liang Jiaming Lu Zhengge Wang Zhengyang Zhu Xin Zhang Bing Zhang Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics Journal of Clinical Medicine MGMT promoter methylation glioma deep learning radiomic |
| title | Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics |
| title_full | Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics |
| title_fullStr | Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics |
| title_full_unstemmed | Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics |
| title_short | Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics |
| title_sort | predicting mgmt promoter methylation in diffuse gliomas using deep learning with radiomics |
| topic | MGMT promoter methylation glioma deep learning radiomic |
| url | https://www.mdpi.com/2077-0383/11/12/3445 |
| work_keys_str_mv | AT sixuanchen predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT yuexu predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT meipingye predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT yangli predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT yusun predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT jiaweiliang predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT jiaminglu predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT zhenggewang predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT zhengyangzhu predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT xinzhang predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics AT bingzhang predictingmgmtpromotermethylationindiffusegliomasusingdeeplearningwithradiomics |