Predicting Histological Grade in Pediatric Glioma Using Multiparametric Radiomics and Conventional MRI Features

Overview

Journal Sci Rep

Specialty Science

Date 2024 Jun 13

PMID 38871755

Authors

Tengfei Zhou

Baobao Qiao

Bo Peng

Yuqi Liu

Zhenjia Gong

Mengfei Kang

Yu He

Chunying Pang

Yakang Dai

Mao Sheng

Affiliations

Soon will be listed here.

Abstract

Prediction of glioma is crucial to provide a precise treatment plan to optimize the prognosis of children with glioma. However, studies on the grading of pediatric gliomas using radiomics are limited. Meanwhile, existing methods are mainly based on only radiomics features, ignoring intuitive information about tumor morphology on traditional imaging features. This study aims to utilize multiparametric magnetic resonance imaging (MRI) to identify high-grade and low-grade gliomas in children and establish a classification model based on radiomics features and clinical features. A total of 85 children with gliomas underwent tumor resection, and part of the tumor tissue was examined pathologically. Patients were categorized into high-grade and low-grade groups according to World Health Organization guidelines. Preoperative multiparametric MRI data, including contrast-enhanced T1-weighted imaging, T2-weighted imaging, T2-weighted fluid-attenuated inversion recovery, diffusion-weighted images, and apparent diffusion coefficient sequences, were obtained and labeled by two radiologists. The images were preprocessed, and radiomics features were extracted for each MRI sequence. Feature selection methods were used to select radiomics features, and statistically significant clinical features were identified using t-tests. The selected radiomics features and conventional MRI features were used to train the AutoGluon models. The improved model, based on radiomics features and conventional MRI features, achieved a balanced classification accuracy of 66.59%. The cross-validated areas under the receiver operating characteristic curve for the classifier of AutoGluon frame were 0.8071 on the test dataset. The results indicate that the performance of AutoGluon models can be improved by incorporating conventional MRI features, highlighting the importance of the experience of radiologists in accurately grading pediatric gliomas. This method can help predict the grade of pediatric glioma before pathological examination and assist in determining the appropriate treatment plan, including radiotherapy, chemotherapy, drugs, and gene surgery.

References

Louis D, Perry A, Reifenberger G, von Deimling A, Figarella-Branger D, Cavenee W . The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary. Acta Neuropathol. 2016; 131(6):803-20. DOI: 10.1007/s00401-016-1545-1. View

MacDonald T, Aguilera D, Kramm C . Treatment of high-grade glioma in children and adolescents. Neuro Oncol. 2011; 13(10):1049-58. PMC: 3177659. DOI: 10.1093/neuonc/nor092. View

Cabral de Carvalho Correa D, Tesser-Gamba F, Oliveira I, da Silva N, Capellano A, Alves M . Gliomas in children and adolescents: investigation of molecular alterations with a potential prognostic and therapeutic impact. J Cancer Res Clin Oncol. 2021; 148(1):107-119. DOI: 10.1007/s00432-021-03813-1. View

Jackson R, Fuller G, Abi-Said D, Lang F, Gokaslan Z, Shi W . Limitations of stereotactic biopsy in the initial management of gliomas. Neuro Oncol. 2001; 3(3):193-200. PMC: 1920616. DOI: 10.1093/neuonc/3.3.193. View

Koral K, Mathis D, Gimi B, Gargan L, Weprin B, Bowers D . Common pediatric cerebellar tumors: correlation between cell densities and apparent diffusion coefficient metrics. Radiology. 2013; 268(2):532-7. DOI: 10.1148/radiol.13121362. View

Smirniotopoulos J, Murphy F, Rushing E, Rees J, Schroeder J . Patterns of contrast enhancement in the brain and meninges. Radiographics. 2007; 27(2):525-51. DOI: 10.1148/rg.272065155. View

Yang J, Antin P, Berx G, Blanpain C, Brabletz T, Bronner M . Guidelines and definitions for research on epithelial-mesenchymal transition. Nat Rev Mol Cell Biol. 2020; 21(6):341-352. PMC: 7250738. DOI: 10.1038/s41580-020-0237-9. View

Gielen J, De Schepper A, Vanhoenacker F, Parizel P, Wang X, Sciot R . Accuracy of MRI in characterization of soft tissue tumors and tumor-like lesions. A prospective study in 548 patients. Eur Radiol. 2004; 14(12):2320-30. DOI: 10.1007/s00330-004-2431-0. View

Qi Y, Zhao T, Han M . The application of radiomics in predicting gene mutations in cancer. Eur Radiol. 2022; 32(6):4014-4024. DOI: 10.1007/s00330-021-08520-6. View

10.

Yip S, Aerts H . Applications and limitations of radiomics. Phys Med Biol. 2016; 61(13):R150-66. PMC: 4927328. DOI: 10.1088/0031-9155/61/13/R150. View

11.

Chiu F, Yen Y . Efficient Radiomics-Based Classification of Multi-Parametric MR Images to Identify Volumetric Habitats and Signatures in Glioblastoma: A Machine Learning Approach. Cancers (Basel). 2022; 14(6). PMC: 8945893. DOI: 10.3390/cancers14061475. View

12.

Zhou M, Scott J, Chaudhury B, Hall L, Goldgof D, Yeom K . Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors, and Machine-Learning Approaches. AJNR Am J Neuroradiol. 2017; 39(2):208-216. PMC: 5812810. DOI: 10.3174/ajnr.A5391. View

13.

Yamasaki F, Kurisu K, Satoh K, Arita K, Sugiyama K, Ohtaki M . Apparent diffusion coefficient of human brain tumors at MR imaging. Radiology. 2005; 235(3):985-91. DOI: 10.1148/radiol.2353031338. View

14.

Wu C, Zheng H, Li J, Zhang Y, Duan S, Li Y . MRI-based radiomics signature and clinical factor for predicting H3K27M mutation in pediatric high-grade gliomas located in the midline of the brain. Eur Radiol. 2021; 32(3):1813-1822. DOI: 10.1007/s00330-021-08234-9. View

15.

Chiang J, Diaz A, Makepeace L, Li X, Han Y, Li Y . Clinical, imaging, and molecular analysis of pediatric pontine tumors lacking characteristic imaging features of DIPG. Acta Neuropathol Commun. 2020; 8(1):57. PMC: 7181591. DOI: 10.1186/s40478-020-00930-9. View

16.

Hoffman L, Veldhuijzen van Zanten S, Colditz N, Baugh J, Chaney B, Hoffmann M . Clinical, Radiologic, Pathologic, and Molecular Characteristics of Long-Term Survivors of Diffuse Intrinsic Pontine Glioma (DIPG): A Collaborative Report From the International and European Society for Pediatric Oncology DIPG Registries. J Clin Oncol. 2018; 36(19):1963-1972. PMC: 6075859. DOI: 10.1200/JCO.2017.75.9308. View

17.

Vamvakas A, Williams S, Theodorou K, Kapsalaki E, Fountas K, Kappas C . Imaging biomarker analysis of advanced multiparametric MRI for glioma grading. Phys Med. 2019; 60:188-198. DOI: 10.1016/j.ejmp.2019.03.014. View

18.

Wang J, Hu Y, Zhou X, Bao S, Chen Y, Ge M . A radiomics model based on DCE-MRI and DWI may improve the prediction of estimating IDH1 mutation and angiogenesis in gliomas. Eur J Radiol. 2022; 147:110141. DOI: 10.1016/j.ejrad.2021.110141. View