Abstract
Purpose
H3K27M-mutant associated brainstem glioma (BSG) carries a very poor prognosis. We aimed to predict H3K27M mutation status by amide proton transfer–weighted (APTw) imaging and radiomic features.
Methods
Eighty-one BSG patients with APTw imaging at 3T MR and known H3K27M status were retrospectively studied. APTw values (mean, median, and max) and radiomic features within manually delineated 3D tumor masks were extracted. Comparison of APTw measures between H3K27M-mutant and wildtype groups was conducted by two-sample Student’s T/Mann–Whitney U test and receiver operating characteristic curve (ROC) analysis. H3K27M-mutant prediction using APTw-derived radiomics was conducted using a machine learning algorithm (support vector machine) in randomly selected train (n = 64) and test (n = 17) sets. Sensitivity analysis with additional random splits of train and test sets, 2D tumor masks, and other classifiers were conducted. Finally, a prospective cohort including 29 BSG patients was acquired for validation of the radiomics algorithm.
Results
BSG patients with H3K27M-mutant were younger and had higher max APTw values than those with wildtype. APTw-derived radiomic measures reflecting tumor heterogeneity could predict H3K27M mutation status with an accuracy of 0.88, sensitivity of 0.92, and specificity of 0.80 in the test set. Sensitivity analysis confirmed the predictive ability (accuracy range: 0.71–0.94). In the independent prospective validation cohort, the algorithm reached an accuracy of 0.86, sensitivity of 0.88, and specificity of 0.85 for predicting H3K27M-mutation status.
Conclusion
BSG patients with H3K27M-mutant had higher max APTw values than those with wildtype. APTw-derived radiomics could accurately predict a H3K27M-mutant status in BSG patients.
Similar content being viewed by others
Data availability
The data would be available if the corresponding author received requirement from qualified researchers.
References
Larson JD, et al. Histone H3.3 K27M Accelerates spontaneous brainstem glioma and drives restricted changes in bivalent gene expression. Cancer Cell. 2019;35(1):140-155.e7. https://doi.org/10.1016/j.ccell.2018.11.015.
Nagaraja S, et al. Histone variant and cell context determine H3K27M reprogramming of the enhancer landscape and oncogenic state. Mol Cell. 2019;76(6):965–80. https://doi.org/10.1016/j.molcel.2019.08.030.
Nikbakht H, et al. Spatial and temporal homogeneity of driver mutations in diffuse intrinsic pontine glioma. Nat Commun. 2016;7:11185. https://doi.org/10.1038/ncomms11185.
Pan C, et al. Molecular profiling of tumors of the brainstem by sequencing of CSF-derived circulating tumor DNA. Acta Neuropathol. 2019;137(2):297–306. https://doi.org/10.1007/s00401-018-1936-6.
Hoffman LM, et al. Spatial genomic heterogeneity in diffuse intrinsic pontine and midline high-grade glioma: implications for diagnostic biopsy and targeted therapeutics. Acta Neuropathol Commun. 2016;4:1. https://doi.org/10.1186/s40478-015-0269-0.
Grimm SA, Chamberlain MC. Brainstem glioma: a review. Curr Neurol Neurosci Rep. 2013;13(5):346. https://doi.org/10.1007/s11910-013-0346-3.
Yamasaki F, et al. Magnetic resonance spectroscopic detection of lactate is predictive of a poor prognosis in patients with diffuse intrinsic pontine glioma. Neuro Oncol. 2011;13(7):791–801. https://doi.org/10.1093/neuonc/nor038.
Piccardo A, et al. Advanced MR imaging and (18)F-DOPA PET characteristics of H3K27M-mutant and wild-type pediatric diffuse midline gliomas. Eur J Nucl Med Mol Imaging. 2019;46(8):1685–94. https://doi.org/10.1007/s00259-019-04333-4.
Smits M, van den Bent MJ. Imaging correlates of adult glioma genotypes. Radiology. 2017;284(2):316–31. https://doi.org/10.1148/radiol.2017151930.
Zhou J, et al. Three-dimensional amide proton transfer MR imaging of gliomas: Initial experience and comparison with gadolinium enhancement. J Magn Reson Imaging. 2013;38(5):1119–28. https://doi.org/10.1002/jmri.24067.
Su X, et al. Automated machine learning based on radiomics features predicts H3 K27M mutation in midline gliomas of the brain. Neuro Oncol. 2020;22(3):393–401. https://doi.org/10.1093/neuonc/noz184.
Pan CC, et al. A machine learning-based prediction model of H3K27M mutations in brainstem gliomas using conventional MRI and clinical features. Radiother Oncol. 2019;130:172–9. https://doi.org/10.1016/j.radonc.2018.07.011.
Zhang B, et al. Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas. Neuro Oncol. 2017;19(1):109–17. https://doi.org/10.1093/neuonc/now121.
Sakai Y, et al. MRI Radiomic features to predict IDH1 mutation status in gliomas: a machine learning approach using gradient tree boosting. Int J Mol Sci. 2020;21(21):8004. https://doi.org/10.3390/ijms21218004.
Togao O, et al. Amide proton transfer imaging of brain tumors using a self-corrected 3D fast spin-echo dixon method: comparison with separate B0 correction. Magn Reson Med. 2017;77(6):2272–9. https://doi.org/10.1002/mrm.26322.
Zhou J, et al. APT-weighted MRI: techniques, current neuro applications, and challenging issues. J Magn Reson Imaging. 2019;50(2):347–64. https://doi.org/10.1002/jmri.26645.
Louis DN, et al. The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary. Acta Neuropathol. 2016;131(6):803–20. https://doi.org/10.1007/s00401-016-1545-1.
Solomon DA, et al. Diffuse midline gliomas with histone H3–K27M mutation: a series of 47 cases assessing the spectrum of morphologic variation and associated genetic alterations. Brain Pathol. 2016;26(5):569–80. https://doi.org/10.1111/bpa.12336.
Benesty J, Chen J, Huang Y, Cohen I. Pearson correlation coefficient. In: Noise reduction in speech processing. Heidelberg: Springer; 2009. p. 37–40.
Kenji Kira LAR. A practical approach to feature selection Machine Learning. Proceedings of the Ninth International Workshop on Machine Learning. 1992;249–56.
Wu G, et al. Somatic histone H3 alterations in pediatric diffuse intrinsic pontine gliomas and non-brainstem glioblastomas. Nat Genet. 2012;44(3):251–3. https://doi.org/10.1038/ng.1102.
Hoffman LM, et al. 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):1963–72. https://doi.org/10.1200/JCO.2017.75.9308.
Daoud EV, et al. Adult brainstem gliomas with H3K27M mutation: radiology, pathology, and prognosis. J Neuropathol Exp Neurol. 2018;77(4):302–11. https://doi.org/10.1093/jnen/nly006.
Aboian MS, et al. Imaging characteristics of pediatric diffuse midline gliomas with histone H3 K27M Mutation. AJNR Am J Neuroradiol. 2017;38(4):795–800. https://doi.org/10.3174/ajnr.A5076.
Fisher PG, et al. A clinicopathologic reappraisal of brain stem tumor classification. Identification of pilocystic astrocytoma and fibrillary astrocytoma as distinct entities. Cancer. 2000;89(7):1569–76. https://doi.org/10.1002/1097-0142(20001001)89:7%3c1569::aid-cncr22%3e3.0.co;2-0.
Sotirios B, et al. The role of APT imaging in gliomas grading: a systematic review and meta-analysis. Eur J Radiol. 2020;133:09353. https://doi.org/10.1016/j.ejrad.2020.109353.
Paech D, et al. Assessing the predictability of IDH mutation and MGMT methylation status in glioma patients using relaxation-compensated multipool CEST MRI at 7.0T. Neuro Oncol. 2018;20(12):1661–71. https://doi.org/10.1093/neuonc/noy073.
Joo B, et al. Amide proton transfer imaging might predict survival and IDH mutation status in high-grade glioma. Eur Radiol. 2019;29(12):6643–52. https://doi.org/10.1007/s00330-019-06203-x.
Park JE, et al. Pre- and posttreatment glioma: comparison of amide proton transfer imaging with MR spectroscopy for biomarkers of tumor proliferation. Radiology. 2016;278(2):514–23. https://doi.org/10.1148/radiol.2015142979.
Castel D, et al. Histone H3F3A and HIST1H3B K27M mutations define two subgroups of diffuse intrinsic pontine gliomas with different prognosis and phenotypes. Acta Neuropathol. 2015;130(6):815–27. https://doi.org/10.1007/s00401-015-1478-0.
Zhou J, et al. Using the amide proton signals of intracellular proteins and peptides to detect pH effects in MRI. Nat Med. 2003;9(8):1085–90. https://doi.org/10.1038/nm907.
Griffiths JR. Are cancer cells acidic? Br J Cancer. 1991;64(3):425–7.
Anderson G. Tumour microenvironment: roles of the aryl hydrocarbon receptor, O-GlcNAcylation, acetyl-CoA and melatonergic pathway in regulating dynamic metabolic interactions across cell types-tumour microenvironment and metabolism. Int J Mol Sci. 2020;22(1):141. https://doi.org/10.3390/ijms22010141.
Funding
This study was funded by the National Science Foundation of China (Nos. 81870958 and 81571631), the Beijing Municipal Natural Science Foundation for Distinguished Young Scholars (No. JQ20035), the Special Fund of the Pediatric Medical Coordinated Development Center of Beijing Hospitals Authority (No. XTYB201831). FB was supported by the NIHR biomedical research center at UCLH.
Author information
Authors and Affiliations
Contributions
Data management, data processing, statistical analysis, and manuscript drafting: Zhizheng Zhuo. Data management and lesion segmentation: Liying Qu. Clinical information acquisition and clinical diagnosis: Peng Zhang. Data acquisition, lesion segmentation, and clinical diagnosis: Yunyun Duan. Lesion segmentation and clinical evaluation: Dan Cheng. Manuscript editing: Xiaolu Xu. Manuscript editing: Ting Sun. MRI data acquisition: Jinli Ding. MRI data acquisition: Cong Xie. Histopathological and molecular information: Xing Liu. Manuscript editing and review: Sven Haller. Manuscript editing and review: Frederik Barkhof. Patient recruitment and clinical diagnosis: Liwei Zhang. Study design, manuscript editing and final approval of this manuscript: Yaou Liu.
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the Topical Collection on Oncology - Brain.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Zhuo, Z., Qu, L., Zhang, P. et al. Prediction of H3K27M-mutant brainstem glioma by amide proton transfer–weighted imaging and its derived radiomics. Eur J Nucl Med Mol Imaging 48, 4426–4436 (2021). https://doi.org/10.1007/s00259-021-05455-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00259-021-05455-4