A multiparameter radiomic model for accurate prognostic prediction of glioma
Abstract An accurate prediction of prognosis is important for clinical treatments of glioma. In this study, a multiparameter radiomic model is proposed for accurate prognostic prediction of glioma. Three kinds of region of interest were extracted from preoperative postcontrast T1‐weighted images and...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-06-01
|
Series: | MedComm – Future Medicine |
Subjects: | |
Online Access: | https://doi.org/10.1002/mef2.41 |
_version_ | 1797795185482006528 |
---|---|
author | Yan Li Li Bao Caiwei Yang Zhenglong Deng Xin Zhang Pin Xu Xiaorui Su Fanxin Zeng Mir Q. U. Mehrabi Qiang Yue Bin Song Qiyong Gong Su Lui Min Wu |
author_facet | Yan Li Li Bao Caiwei Yang Zhenglong Deng Xin Zhang Pin Xu Xiaorui Su Fanxin Zeng Mir Q. U. Mehrabi Qiang Yue Bin Song Qiyong Gong Su Lui Min Wu |
author_sort | Yan Li |
collection | DOAJ |
description | Abstract An accurate prediction of prognosis is important for clinical treatments of glioma. In this study, a multiparameter radiomic model is proposed for accurate prognostic prediction of glioma. Three kinds of region of interest were extracted from preoperative postcontrast T1‐weighted images and T2 fluid‐attenuated inversion recovery images acquired from 140 glioma patients. Radiomics score (Radscore) was calculated and the conventional image features and clinical molecular characteristics that may be related to progression‐free survival (PFS) were evaluated. Five uniparameter and various combinations of biparameter and multiparameter models based on above characteristics were built. The performance of these models was evaluated by concordance index (C index), and the nomogram of the multiparameter radiomic model was constructed. The results show that the proposed multiparameter radiomic model has a better prediction performance than other models. In the training and validation sets, the calibration curves of the multiparameter radiomic model for the 1‐, 2‐, and 3‐year PFS probability demonstrate a high consistence between predictions and observations. In conclusion, this study demonstrates that the multiparameter radiomic model based on Radscore, conventional image features and clinical molecular characteristics can improve the prediction accuracy of glioma prognosis, which could be informative for individualized treatments. |
first_indexed | 2024-03-13T03:14:04Z |
format | Article |
id | doaj.art-81f2cc821f49460f8124a6e04a55a1a3 |
institution | Directory Open Access Journal |
issn | 2769-6456 |
language | English |
last_indexed | 2024-03-13T03:14:04Z |
publishDate | 2023-06-01 |
publisher | Wiley |
record_format | Article |
series | MedComm – Future Medicine |
spelling | doaj.art-81f2cc821f49460f8124a6e04a55a1a32023-06-26T07:38:27ZengWileyMedComm – Future Medicine2769-64562023-06-0122n/an/a10.1002/mef2.41A multiparameter radiomic model for accurate prognostic prediction of gliomaYan Li0Li Bao1Caiwei Yang2Zhenglong Deng3Xin Zhang4Pin Xu5Xiaorui Su6Fanxin Zeng7Mir Q. U. Mehrabi8Qiang Yue9Bin Song10Qiyong Gong11Su Lui12Min Wu13Department of Radiology, Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital Sichuan University Chengdu ChinaDepartment of Radiology, Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital Sichuan University Chengdu ChinaDepartment of Radiology, Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital Sichuan University Chengdu ChinaDepartment of Interventional Radiology Chengdu Second People's Hospital Chengdu ChinaPharmaceutical Diagnostic Team GE Healthcare, Life Sciences Beijing ChinaApplied Nuclear Techniques in Geosciences Key Laboratory of Sichuan Province Chengdu University of Technology Chengdu ChinaDepartment of Radiology, Huaxi MR Research Center (HMRRC) West China Hospital of Sichuan University Chengdu ChinaDepartment of Clinic Medical Center Dazhou Central Hospital Dazhou ChinaDepartment of Radiology, Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital Sichuan University Chengdu ChinaDepartment of Radiology, Huaxi MR Research Center (HMRRC) West China Hospital of Sichuan University Chengdu ChinaDepartment of Radiology, Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital Sichuan University Chengdu ChinaDepartment of Radiology, Huaxi MR Research Center (HMRRC) West China Hospital of Sichuan University Chengdu ChinaDepartment of Radiology, Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital Sichuan University Chengdu ChinaDepartment of Radiology, Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital Sichuan University Chengdu ChinaAbstract An accurate prediction of prognosis is important for clinical treatments of glioma. In this study, a multiparameter radiomic model is proposed for accurate prognostic prediction of glioma. Three kinds of region of interest were extracted from preoperative postcontrast T1‐weighted images and T2 fluid‐attenuated inversion recovery images acquired from 140 glioma patients. Radiomics score (Radscore) was calculated and the conventional image features and clinical molecular characteristics that may be related to progression‐free survival (PFS) were evaluated. Five uniparameter and various combinations of biparameter and multiparameter models based on above characteristics were built. The performance of these models was evaluated by concordance index (C index), and the nomogram of the multiparameter radiomic model was constructed. The results show that the proposed multiparameter radiomic model has a better prediction performance than other models. In the training and validation sets, the calibration curves of the multiparameter radiomic model for the 1‐, 2‐, and 3‐year PFS probability demonstrate a high consistence between predictions and observations. In conclusion, this study demonstrates that the multiparameter radiomic model based on Radscore, conventional image features and clinical molecular characteristics can improve the prediction accuracy of glioma prognosis, which could be informative for individualized treatments.https://doi.org/10.1002/mef2.41gliomamultiparameterprediction modelprognosisradiomic |
spellingShingle | Yan Li Li Bao Caiwei Yang Zhenglong Deng Xin Zhang Pin Xu Xiaorui Su Fanxin Zeng Mir Q. U. Mehrabi Qiang Yue Bin Song Qiyong Gong Su Lui Min Wu A multiparameter radiomic model for accurate prognostic prediction of glioma MedComm – Future Medicine glioma multiparameter prediction model prognosis radiomic |
title | A multiparameter radiomic model for accurate prognostic prediction of glioma |
title_full | A multiparameter radiomic model for accurate prognostic prediction of glioma |
title_fullStr | A multiparameter radiomic model for accurate prognostic prediction of glioma |
title_full_unstemmed | A multiparameter radiomic model for accurate prognostic prediction of glioma |
title_short | A multiparameter radiomic model for accurate prognostic prediction of glioma |
title_sort | multiparameter radiomic model for accurate prognostic prediction of glioma |
topic | glioma multiparameter prediction model prognosis radiomic |
url | https://doi.org/10.1002/mef2.41 |
work_keys_str_mv | AT yanli amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT libao amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT caiweiyang amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT zhenglongdeng amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT xinzhang amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT pinxu amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT xiaoruisu amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT fanxinzeng amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT mirqumehrabi amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT qiangyue amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT binsong amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT qiyonggong amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT sului amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT minwu amultiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT yanli multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT libao multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT caiweiyang multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT zhenglongdeng multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT xinzhang multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT pinxu multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT xiaoruisu multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT fanxinzeng multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT mirqumehrabi multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT qiangyue multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT binsong multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT qiyonggong multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT sului multiparameterradiomicmodelforaccurateprognosticpredictionofglioma AT minwu multiparameterradiomicmodelforaccurateprognosticpredictionofglioma |