Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients

Abstract Interleukin-18 has broad immune regulatory functions. Genomic data and enhanced Magnetic Resonance Imaging data related to LGG patients were downloaded from The Cancer Genome Atlas and Cancer Imaging Archive, and the constructed model was externally validated using hospital MRI enhanced ima...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Zhang, Yao Xiao, Jun Liu, Feng Xiao, Jie Zeng, Hong Zhu, Wei Tu, Hua Guo
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Precision Oncology
Online Access:https://doi.org/10.1038/s41698-025-00966-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849686237505388544
author Zhe Zhang
Yao Xiao
Jun Liu
Feng Xiao
Jie Zeng
Hong Zhu
Wei Tu
Hua Guo
author_facet Zhe Zhang
Yao Xiao
Jun Liu
Feng Xiao
Jie Zeng
Hong Zhu
Wei Tu
Hua Guo
author_sort Zhe Zhang
collection DOAJ
description Abstract Interleukin-18 has broad immune regulatory functions. Genomic data and enhanced Magnetic Resonance Imaging data related to LGG patients were downloaded from The Cancer Genome Atlas and Cancer Imaging Archive, and the constructed model was externally validated using hospital MRI enhanced images and clinical pathological features. Radiomic feature extraction was performed using “PyRadiomics”, feature selection was conducted using Maximum Relevance Minimum Redundancy and Recursive Feature Elimination methods, and a model was built using the Gradient Boosting Machine algorithm to predict the expression status of IL18. The constructed radiomics model achieved areas under the receiver operating characteristic curve of 0.861, 0.788, and 0.762 in the TCIA training dataset (n = 98), TCIA validation dataset (n = 41), and external validation dataset (n = 50). Calibration curves and decision curve analysis demonstrated the calibration and high clinical utility of the model. The radiomics model based on enhanced MRI can effectively predict the expression status of IL18 and the prognosis of LGG.
format Article
id doaj-art-a41fca7cce04429c8b496685df48a546
institution DOAJ
issn 2397-768X
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Precision Oncology
spelling doaj-art-a41fca7cce04429c8b496685df48a5462025-08-20T03:22:46ZengNature Portfolionpj Precision Oncology2397-768X2025-06-019111310.1038/s41698-025-00966-xMachine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patientsZhe Zhang0Yao Xiao1Jun Liu2Feng Xiao3Jie Zeng4Hong Zhu5Wei Tu6Hua Guo7Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityAbstract Interleukin-18 has broad immune regulatory functions. Genomic data and enhanced Magnetic Resonance Imaging data related to LGG patients were downloaded from The Cancer Genome Atlas and Cancer Imaging Archive, and the constructed model was externally validated using hospital MRI enhanced images and clinical pathological features. Radiomic feature extraction was performed using “PyRadiomics”, feature selection was conducted using Maximum Relevance Minimum Redundancy and Recursive Feature Elimination methods, and a model was built using the Gradient Boosting Machine algorithm to predict the expression status of IL18. The constructed radiomics model achieved areas under the receiver operating characteristic curve of 0.861, 0.788, and 0.762 in the TCIA training dataset (n = 98), TCIA validation dataset (n = 41), and external validation dataset (n = 50). Calibration curves and decision curve analysis demonstrated the calibration and high clinical utility of the model. The radiomics model based on enhanced MRI can effectively predict the expression status of IL18 and the prognosis of LGG.https://doi.org/10.1038/s41698-025-00966-x
spellingShingle Zhe Zhang
Yao Xiao
Jun Liu
Feng Xiao
Jie Zeng
Hong Zhu
Wei Tu
Hua Guo
Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients
npj Precision Oncology
title Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients
title_full Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients
title_fullStr Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients
title_full_unstemmed Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients
title_short Machine learning-based MRI radiomics predict IL18 expression and overall survival of low-grade glioma patients
title_sort machine learning based mri radiomics predict il18 expression and overall survival of low grade glioma patients
url https://doi.org/10.1038/s41698-025-00966-x
work_keys_str_mv AT zhezhang machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients
AT yaoxiao machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients
AT junliu machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients
AT fengxiao machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients
AT jiezeng machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients
AT hongzhu machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients
AT weitu machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients
AT huaguo machinelearningbasedmriradiomicspredictil18expressionandoverallsurvivaloflowgradegliomapatients