Application value of radiomics model based on multiparametric MRI glioma peritumoral region in glioma prognosis evaluation
10.19405/j.cnki.issn1000-1492.2024.01.025
- Author:
Qiuyang Hou
1
;
Chengkun Ye
2
;
Chang Liu
1
;
Jianghao Xing
3
;
Yaqiong Ge
4
;
Jiangdian Song
5
;
Kexue Deng
1
Author Information
1. Dept of Radiology，South District，The First Affiliated Hospital of University of Science and Technology of China，Hefei 230036
2. Dept of Neurosurgery，South District，The First Affiliated Hospital of University of Science and Technology of China，Hefei 230036
3. Dept of Oncology，The First Affiliated Hospital of Anhui Medical University，Hefei 230022
4. GE Healthcare China，Shanghai 210000
5. Dept oSchool of Health Management，China Medical University，Shenyang 110001f Radiology，South District，The First Affiliated Hospital of University of Science and Technology of China，Hefei 230036
- Publication Type:Journal Article
- Keywords:
radiomics;
glioma;
peritumoral region;
survival;
nomogram
- From:
Acta Universitatis Medicinalis Anhui
2024;59(1):154-161
- CountryChina
- Language:Chinese
-
Abstract:
Objective : To evaluate the prognostic value of a radiomics model based on the peritumoral region of gli- oma．
Methods :138 patients with glioma were retrospectively analyzed ，medical imaging interaction toolkit ( MITK) software was used to obtain the magnetic resonance imaging (MRI) images of peritumoral area 5 mm，10 mm and 20 mm from the tumor edge and extract texture features．The texture features were screened the radiomics model was established and the radiomic score was calculated．A clinical prediction model and a combined predic- tion model along with Rad-score and clinical risk factors were established．The combined prediction model was dis- played as a nomogram，and the predictive performance of the model for survival in glioma patients was evaluated.
Results : In the validation set，the C-index value of the radiomics model based on the peritumoral region 10 mm a- way from the tumor edge based on T2 weighted image (T2WI) images was 0. 663 (95% CI = 0. 72－0. 78) ，resul- ting in the best prediction performance．On the training set and validation set，the C-index of the nomogram was 0. 770 and 0. 730，respectively，indicating that the prediction performance of nomogram was better than those of the radiomics model and clinical prediction model．The model had the highest prediction effect on the 3-year survival rate of glioma patients (training set area under curve (AUC) = 0. 93，95% CI = 0. 83 － 0. 98 ; validation set AUC = 0. 88，95% CI = 0. 76 －0. 99) ．The calibration curve showed that the joint prediction nomogram in both the training set and the validation set had good performance．
Conclusion : The combined prediction model based on the preoperative T2WI images in the peritumoral region 10 mm from the tumor edge and the clinicopathological risk factors can accurately predict the prognosis of glioma，providing the best effect of prediction on the 3-year survival rate of glioma.
- Full text:2024062509211833414基于多参数磁共振瘤周区域的...胶质瘤预后评估中的应用价值_侯秋阳.pdf
