Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla
Background and goalNoninvasive prediction of isocitrate dehydrogenase (IDH) mutation status in glioma guides surgical strategies and individualized management. We explored the capability on preoperatively identifying IDH status of combining a convolutional neural network (CNN) and a novel imaging mo...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.1134626/full |
| _version_ | 1797831662900346880 |
|---|---|
| author | Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yang Yu Yang Yu Yang Yu Yang Yu Jun Chang Jun Chang Jun Chang Jun Chang Jun Chang Ying-Hua Chu Wenwen Yu Yi-Cheng Hsu Liebig Alexander Patrick Mianxin Liu Qi Yue Qi Yue Qi Yue Qi Yue Qi Yue Qi Yue |
| author_facet | Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yang Yu Yang Yu Yang Yu Yang Yu Jun Chang Jun Chang Jun Chang Jun Chang Jun Chang Ying-Hua Chu Wenwen Yu Yi-Cheng Hsu Liebig Alexander Patrick Mianxin Liu Qi Yue Qi Yue Qi Yue Qi Yue Qi Yue Qi Yue |
| author_sort | Yifan Yuan |
| collection | DOAJ |
| description | Background and goalNoninvasive prediction of isocitrate dehydrogenase (IDH) mutation status in glioma guides surgical strategies and individualized management. We explored the capability on preoperatively identifying IDH status of combining a convolutional neural network (CNN) and a novel imaging modality, ultra-high field 7.0 Tesla (T) chemical exchange saturation transfer (CEST) imaging.MethodWe enrolled 84 glioma patients of different tumor grades in this retrospective study. Amide proton transfer CEST and structural Magnetic Resonance (MR) imaging at 7T were performed preoperatively, and the tumor regions are manually segmented, leading to the “annotation” maps that offers the location and shape information of the tumors. The tumor region slices in CEST and T1 images were further cropped out as samples and combined with the annotation maps, which were inputted to a 2D CNN model for generating IDH predictions. Further comparison analysis to radiomics-based prediction methods was performed to demonstrate the crucial role of CNN for predicting IDH based on CEST and T1 images.ResultsA fivefold cross-validation was performed on the 84 patients and 4090 slices. We observed a model based on only CEST achieved accuracy of 74.01% ± 1.15%, and the area under the curve (AUC) of 0.8022 ± 0.0147. When using T1 image only, the prediction performances dropped to accuracy of 72.52% ± 1.12% and AUC of 0.7904 ± 0.0214, which indicates no superiority of CEST over T1. However, when we combined CEST and T1 together with the annotation maps, the performances of the CNN model were further boosted to accuracy of 82.94% ± 1.23% and AUC of 0.8868 ± 0.0055, suggesting the importance of a joint analysis of CEST and T1. Finally, using the same inputs, the CNN-based predictions achieved significantly improved performances above those from radiomics-based predictions (logistic regression and support vector machine) by 10% to 20% in all metrics.Conclusion7T CEST and structural MRI jointly offer improved sensitivity and specificity of preoperative non-invasive imaging for the diagnosis of IDH mutation status. As the first study of CNN model on imaging acquired at ultra-high field MR, our results could demonstrate the potential of combining ultra-high-field CEST and CNN for facilitating decision-making in clinical practice. However, due to the limited cases and B1 inhomogeneities, the accuracy of this model will be improved in our further study. |
| first_indexed | 2024-04-09T13:56:17Z |
| format | Article |
| id | doaj.art-165d9ea4d189421e93e693f736f4e40e |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-09T13:56:17Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-165d9ea4d189421e93e693f736f4e40e2023-05-08T04:49:11ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-05-011310.3389/fonc.2023.11346261134626Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 TeslaYifan Yuan0Yifan Yuan1Yifan Yuan2Yifan Yuan3Yifan Yuan4Yifan Yuan5Yang Yu6Yang Yu7Yang Yu8Yang Yu9Jun Chang10Jun Chang11Jun Chang12Jun Chang13Jun Chang14Ying-Hua Chu15Wenwen Yu16Yi-Cheng Hsu17Liebig Alexander Patrick18Mianxin Liu19Qi Yue20Qi Yue21Qi Yue22Qi Yue23Qi Yue24Qi Yue25Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, ChinaNational Center for Neurological Disorders, Shanghai, ChinaNeurosurgical Institute of Fudan University, Shanghai, ChinaShanghai Clinical Medical Center of Neurosurgery, Shanghai, ChinaShanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, ChinaResearch Units of New Technologies of Micro-Endoscopy Combination in Skull Base Surgery (2018RU008), Chinese Academy of Medical Sciences (CAMS), Shanghai, ChinaNational Center for Neurological Disorders, Shanghai, ChinaShanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, ChinaResearch Units of New Technologies of Micro-Endoscopy Combination in Skull Base Surgery (2018RU008), Chinese Academy of Medical Sciences (CAMS), Shanghai, ChinaDepartment of Radiology, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, ChinaDepartment of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, ChinaNational Center for Neurological Disorders, Shanghai, ChinaNeurosurgical Institute of Fudan University, Shanghai, ChinaShanghai Clinical Medical Center of Neurosurgery, Shanghai, ChinaShanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, ChinaMagnetic Resonance (MR) Collaboration, Siemens Healthineers Ltd., Shanghai, ChinaInstitute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, ChinaMagnetic Resonance (MR) Collaboration, Siemens Healthineers Ltd., Shanghai, China0Siemens Healthcare GmbH, Erlangen, Germany1Shanghai Artificial Intelligence Laboratory, Shanghai, ChinaDepartment of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, ChinaNational Center for Neurological Disorders, Shanghai, ChinaNeurosurgical Institute of Fudan University, Shanghai, ChinaShanghai Clinical Medical Center of Neurosurgery, Shanghai, ChinaShanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, ChinaResearch Units of New Technologies of Micro-Endoscopy Combination in Skull Base Surgery (2018RU008), Chinese Academy of Medical Sciences (CAMS), Shanghai, ChinaBackground and goalNoninvasive prediction of isocitrate dehydrogenase (IDH) mutation status in glioma guides surgical strategies and individualized management. We explored the capability on preoperatively identifying IDH status of combining a convolutional neural network (CNN) and a novel imaging modality, ultra-high field 7.0 Tesla (T) chemical exchange saturation transfer (CEST) imaging.MethodWe enrolled 84 glioma patients of different tumor grades in this retrospective study. Amide proton transfer CEST and structural Magnetic Resonance (MR) imaging at 7T were performed preoperatively, and the tumor regions are manually segmented, leading to the “annotation” maps that offers the location and shape information of the tumors. The tumor region slices in CEST and T1 images were further cropped out as samples and combined with the annotation maps, which were inputted to a 2D CNN model for generating IDH predictions. Further comparison analysis to radiomics-based prediction methods was performed to demonstrate the crucial role of CNN for predicting IDH based on CEST and T1 images.ResultsA fivefold cross-validation was performed on the 84 patients and 4090 slices. We observed a model based on only CEST achieved accuracy of 74.01% ± 1.15%, and the area under the curve (AUC) of 0.8022 ± 0.0147. When using T1 image only, the prediction performances dropped to accuracy of 72.52% ± 1.12% and AUC of 0.7904 ± 0.0214, which indicates no superiority of CEST over T1. However, when we combined CEST and T1 together with the annotation maps, the performances of the CNN model were further boosted to accuracy of 82.94% ± 1.23% and AUC of 0.8868 ± 0.0055, suggesting the importance of a joint analysis of CEST and T1. Finally, using the same inputs, the CNN-based predictions achieved significantly improved performances above those from radiomics-based predictions (logistic regression and support vector machine) by 10% to 20% in all metrics.Conclusion7T CEST and structural MRI jointly offer improved sensitivity and specificity of preoperative non-invasive imaging for the diagnosis of IDH mutation status. As the first study of CNN model on imaging acquired at ultra-high field MR, our results could demonstrate the potential of combining ultra-high-field CEST and CNN for facilitating decision-making in clinical practice. However, due to the limited cases and B1 inhomogeneities, the accuracy of this model will be improved in our further study.https://www.frontiersin.org/articles/10.3389/fonc.2023.1134626/fullconvolutional neural networkchemical exchange saturation transferultra-high field MRradiomicsglioma |
| spellingShingle | Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yifan Yuan Yang Yu Yang Yu Yang Yu Yang Yu Jun Chang Jun Chang Jun Chang Jun Chang Jun Chang Ying-Hua Chu Wenwen Yu Yi-Cheng Hsu Liebig Alexander Patrick Mianxin Liu Qi Yue Qi Yue Qi Yue Qi Yue Qi Yue Qi Yue Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla Frontiers in Oncology convolutional neural network chemical exchange saturation transfer ultra-high field MR radiomics glioma |
| title | Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla |
| title_full | Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla |
| title_fullStr | Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla |
| title_full_unstemmed | Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla |
| title_short | Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla |
| title_sort | convolutional neural network to predict idh mutation status in glioma from chemical exchange saturation transfer imaging at 7 tesla |
| topic | convolutional neural network chemical exchange saturation transfer ultra-high field MR radiomics glioma |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2023.1134626/full |
| work_keys_str_mv | AT yifanyuan convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yifanyuan convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yifanyuan convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yifanyuan convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yifanyuan convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yifanyuan convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yangyu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yangyu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yangyu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yangyu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT junchang convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT junchang convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT junchang convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT junchang convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT junchang convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yinghuachu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT wenwenyu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT yichenghsu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT liebigalexanderpatrick convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT mianxinliu convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT qiyue convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT qiyue convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT qiyue convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT qiyue convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT qiyue convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla AT qiyue convolutionalneuralnetworktopredictidhmutationstatusingliomafromchemicalexchangesaturationtransferimagingat7tesla |