A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion
BackgroundTo explore the effectiveness of radiomics features based on routine CT to reflect the difference of cerebral hemispheric perfusion.MethodsWe retrospectively recruited 52 patients with severe stenosis or occlusion in the unilateral middle cerebral artery (MCA), and brain CT perfusion showed...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-03-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.851720/full |
| _version_ | 1819161381664980992 |
|---|---|
| author | Qingguo Ren Panpan An Ke Jin Xiaona Xia Zhaodi Huang Jingxu Xu Chencui Huang Qingjun Jiang Xiangshui Meng |
| author_facet | Qingguo Ren Panpan An Ke Jin Xiaona Xia Zhaodi Huang Jingxu Xu Chencui Huang Qingjun Jiang Xiangshui Meng |
| author_sort | Qingguo Ren |
| collection | DOAJ |
| description | BackgroundTo explore the effectiveness of radiomics features based on routine CT to reflect the difference of cerebral hemispheric perfusion.MethodsWe retrospectively recruited 52 patients with severe stenosis or occlusion in the unilateral middle cerebral artery (MCA), and brain CT perfusion showed an MCA area with deficit perfusion. Radiomics features were extracted from the stenosis side and contralateral of the MCA area based on precontrast CT. Two different region of interest drawing methods were applied. Then the patients were randomly grouped into training and testing sets by the ratio of 8:2. In the training set, ANOVA and the Elastic Net Regression with fivefold cross-validation were conducted to filter and choose the optimized features. Moreover, different machine learning models were built. In the testing set, the area under the receiver operating characteristic (AUC) curve, calibration, and clinical utility were applied to evaluate the predictive performance of the models.ResultsThe logistic regression (LR) for the triangle-contour method and artificial neural network (ANN) for the semiautomatic-contour method were chosen as radiomics models for their good prediction efficacy in the training phase (AUC = 0.869, 0.873) and the validation phase (AUC = 0.793, 0.799). The radiomics algorithms of the triangle-contour and semiautomatic-contour method were implemented in the whole training set (AUC = 0.870, 0.867) and were evaluated in the testing set (AUC = 0.760, 0.802). According to the optimal cutoff value, these two methods can classify the vascular stenosis side class and normal side class.ConclusionRadiomic predictive feature based on precontrast CT image could reflect the difference of cerebral hemispheric perfusion to some extent. |
| first_indexed | 2024-12-22T17:11:27Z |
| format | Article |
| id | doaj.art-130b29e244b54e7cbdc4177961bcdb96 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-22T17:11:27Z |
| publishDate | 2022-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-130b29e244b54e7cbdc4177961bcdb962022-12-21T18:19:04ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-03-011610.3389/fnins.2022.851720851720A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric PerfusionQingguo Ren0Panpan An1Ke Jin2Xiaona Xia3Zhaodi Huang4Jingxu Xu5Chencui Huang6Qingjun Jiang7Xiangshui Meng8Radiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Qingdao, ChinaRadiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Qingdao, ChinaDeepwise AI Lab, Beijing Deepwise and League of PHD Technology Co., Ltd., Beijing, ChinaRadiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Qingdao, ChinaRadiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Qingdao, ChinaDeepwise AI Lab, Beijing Deepwise and League of PHD Technology Co., Ltd., Beijing, ChinaDeepwise AI Lab, Beijing Deepwise and League of PHD Technology Co., Ltd., Beijing, ChinaRadiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Qingdao, ChinaRadiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Qingdao, ChinaBackgroundTo explore the effectiveness of radiomics features based on routine CT to reflect the difference of cerebral hemispheric perfusion.MethodsWe retrospectively recruited 52 patients with severe stenosis or occlusion in the unilateral middle cerebral artery (MCA), and brain CT perfusion showed an MCA area with deficit perfusion. Radiomics features were extracted from the stenosis side and contralateral of the MCA area based on precontrast CT. Two different region of interest drawing methods were applied. Then the patients were randomly grouped into training and testing sets by the ratio of 8:2. In the training set, ANOVA and the Elastic Net Regression with fivefold cross-validation were conducted to filter and choose the optimized features. Moreover, different machine learning models were built. In the testing set, the area under the receiver operating characteristic (AUC) curve, calibration, and clinical utility were applied to evaluate the predictive performance of the models.ResultsThe logistic regression (LR) for the triangle-contour method and artificial neural network (ANN) for the semiautomatic-contour method were chosen as radiomics models for their good prediction efficacy in the training phase (AUC = 0.869, 0.873) and the validation phase (AUC = 0.793, 0.799). The radiomics algorithms of the triangle-contour and semiautomatic-contour method were implemented in the whole training set (AUC = 0.870, 0.867) and were evaluated in the testing set (AUC = 0.760, 0.802). According to the optimal cutoff value, these two methods can classify the vascular stenosis side class and normal side class.ConclusionRadiomic predictive feature based on precontrast CT image could reflect the difference of cerebral hemispheric perfusion to some extent.https://www.frontiersin.org/articles/10.3389/fnins.2022.851720/fullcerebral ischemiacomputed tomographymachine learningmiddle cerebral arterydifferent region of interest |
| spellingShingle | Qingguo Ren Panpan An Ke Jin Xiaona Xia Zhaodi Huang Jingxu Xu Chencui Huang Qingjun Jiang Xiangshui Meng A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion Frontiers in Neuroscience cerebral ischemia computed tomography machine learning middle cerebral artery different region of interest |
| title | A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion |
| title_full | A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion |
| title_fullStr | A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion |
| title_full_unstemmed | A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion |
| title_short | A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion |
| title_sort | pilot study of radiomic based on routine ct reflecting difference of cerebral hemispheric perfusion |
| topic | cerebral ischemia computed tomography machine learning middle cerebral artery different region of interest |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.851720/full |
| work_keys_str_mv | AT qingguoren apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT panpanan apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT kejin apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT xiaonaxia apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT zhaodihuang apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT jingxuxu apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT chencuihuang apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT qingjunjiang apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT xiangshuimeng apilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT qingguoren pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT panpanan pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT kejin pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT xiaonaxia pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT zhaodihuang pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT jingxuxu pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT chencuihuang pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT qingjunjiang pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion AT xiangshuimeng pilotstudyofradiomicbasedonroutinectreflectingdifferenceofcerebralhemisphericperfusion |