A machine learning-based prediction model of H3K27M mutations in brainstem gliomas using conventional MRI and clinical features

Pan, Changcun; Liu, Jia; Tang, Jie; Chen, Xin; Fang, Chen; Wu, Yadong; Geng, Yibo; Xu, Changwu; Zhang, Xinran; Wu, Zhen; Gao, Peiyi; Zhang, Junting; Yan, Hai; Liao, Hongen; Zhang, Liwei

doi:10.1016/j.radonc.2018.07.011

Cited by 42 publications

(36 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction accuracy of a single MRI modality of APTw (acquisition with less than 2 mins) was 0.88 and 0.86 in the retrospective and prospective cohorts respectively, which was comparable or superior to those in previous radiomic studies in diffuse midline glioma and BSG based on conventional multimodal MRI (accuracy<0.85 with FLAIR, T2w, T1w and/or contrast-enhanced T1w) [11,12]. These findings support the hypothesis that APTw-derived radiomic features provide novel radiological biomarkers to help BSG staging, and might be contribute to the improvement of patient management and prognosis prediction.…”

Section: H3k27m Mutations Have Been Widely Reported In Diffuse Midline Glioma (Dmg) and Integrated Intosupporting

confidence: 63%

“…Amide proton transfer weighted (APTw) imaging is a novel MRI technique, which generates image contrast based on the endogenous amide protons in mobile cellular proteins and peptides [10], providing a promising avenue to explore the molecular metabolism associated with the cellular proliferating and gene expression. To fully appreciate tumor heterogeneity, radiomic features from conventional MRI have been successfully used to predict genetic alterations (e.g., isocitrate dehydrogenase [IDH] mutation, H3K27M) in brain tumors [11][12][13][14]. So far, there have been no studies using APTw and its derived radiomics to predict H3K27M mutation status in BSG.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of H3K27M-mutant brainstem glioma by amide proton transfer–weighted imaging and its derived radiomics

Zhuo

Zhang

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

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. MethodsEighty-one BSG patients with APTw imaging at 3T MRI 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 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. ResultsBSG 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. ConclusionBSG patients with H3K27M-mutant had higher max APTw values than those with wildtype. APTwderived radiomics could accurately predict a H3K27M-mutant status in BSG patients.

show abstract

Section: H3k27m Mutations Have Been Widely Reported In Diffuse Midline Glioma (Dmg) and Integrated Intosupporting

confidence: 63%

Section: Introductionmentioning

confidence: 99%

Prediction of H3K27M-mutant brainstem glioma by amide proton transfer–weighted imaging and its derived radiomics

Zhuo

Zhang

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

show abstract

“…These differences included cranial nerve palsies and pyramidal tract signs, as well as tumor size, ring enhancement, growth in the mesencephalon, eccentricity within the pons, and extrapontine extension. Given the clinical utility of noninvasive methods to predict H3 K27M mutation status, there have been recent advances in radiogenomic modeling of baseline conventional MR images in patients with midline glioma [24,35]. In the future, when larger datasets of DIPG with pathologic assessment may be developed, this methodology could be useful for defining additional radiographic features predictive of H3 status specifically in patients with presumed DIPG and, ultimately, may enable radiogenomic pipelines that facilitate real-time clinical translation of these findings.…”

Section: Discussionmentioning

confidence: 99%

Clinical, imaging, and molecular analysis of pediatric pontine tumors lacking characteristic imaging features of DIPG

Chiang

Diaz

Makepeace

et al. 2020

acta neuropathol commun

View full text Add to dashboard Cite

Diffuse intrinsic pontine glioma (DIPG) is most commonly diagnosed based on imaging criteria, with biopsy often reserved for pontine tumors with imaging features not typical for DIPG (atypical DIPG, 'aDIPG'). The histopathologic and molecular spectra of the clinical entity aDIPG remain to be studied systematically. In this study, thirty-three patients with newly diagnosed pontine-centered tumors with imaging inconsistent with DIPG for whom a pathologic diagnosis was subsequently obtained were included. Neoplasms were characterized by routine histology, immunohistochemistry, interphase fluorescence in situ hybridization, Sanger and next-generation DNA/ RNA sequencing, and genome-wide DNA methylome profiling. Clinicopathologic features and survival outcomes were analyzed and compared to those of a contemporary cohort with imaging features consistent with DIPG (typical DIPG, 'tDIPG'). Blinded retrospective neuroimaging review assessed the consistency of the initial imagingbased diagnosis and correlation with histopathology. WHO grade II-IV infiltrating gliomas were observed in 54.6% of the cases; the remaining were low-grade gliomas/glioneuronal tumors or CNS embryonal tumors. Histone H3 K27M mutation, identified in 36% of the cases, was the major prognostic determinant. H3 K27M-mutant aDIPG and H3 K27M-mutant tDIPG had similar methylome profiles but clustered separately from diffuse midline gliomas of the diencephalon and spinal cord. In the aDIPG cohort, clinicoradiographic features did not differ by H3 status, yet significant differences in clinical and imaging features were observed between aDIPG without H3 K27M mutation and tDIPG. Neuroimaging review revealed discordance between the classification of aDIPG and tDIPG and did not correlate with the histology of glial/glioneuronal tumors or tumor grade. One patient (3.1%) developed persistent neurologic deficits after surgery; there were no surgery-related deaths. Our study demonstrates that surgical sampling of aDIPG is well-tolerated and provides significant diagnostic, therapeutic, and prognostic implications, and that neuroimaging alone is insufficient to distinguish aDIPG from tDIPG. H3 K27M-mutant aDIPG is epigenetically and clinically similar to H3 K27M-mutant tDIPG.

show abstract

“…While many studies investigated the use of qualitative and quantitative features derived from conventional and advanced sequences to differentiate high-and low-grade pediatric brain tumors, [28][29][30][31][32][33][34][35][36][37][38] only a few studies tried to link imaging characteristics to molecular markers. 18,19,[39][40][41][42][43][44] Ho et al 39 described different MR imaging patterns based on 15 cases of BRAF V600mutated diencephalic PLGGs and 25 cases of BRAF V600 wild-type JPA/pilomyxoid astrocytomas. Among their findings, which were based on analysis of T2WI and contrast-enhanced T1 sequences, they reported that BRAF V600 wild-type JPA/pilomyxoid astrocytoma presented predominantly as a solitary solid mass with homogeneous or heterogeneous contrast enhancement, whereas the mutated pLGG appeared multiloculated or multinodular following contrast administration.…”

Section: Discussionmentioning

confidence: 99%

Radiomics of Pediatric Low-Grade Gliomas: Toward a Pretherapeutic Differentiation of BRAF-Mutated and BRAF-Fused Tumors

Wagner¹,

Hainc

Khalvati³

et al. 2021

AJNR Am J Neuroradiol

View full text Add to dashboard Cite

BACKGROUND AND PURPOSE: B-Raf proto-oncogene, serine/threonine kinase (BRAF) status has important implications for prognosis and therapy of pediatric low-grade gliomas. Currently, BRAF status classification relies on biopsy. Our aim was to train and validate a radiomics approach to predict BRAF fusion and BRAF V600E mutation. MATERIALS AND METHODS: In this bi-institutional retrospective study, FLAIR MR imaging datasets of 115 pediatric patients with low-grade gliomas from 2 children's hospitals acquired between January 2009 and January 2016 were included and analyzed. Radiomics features were extracted from tumor segmentations, and the predictive model was tested using independent training and testing datasets, with all available tumor types. The model was selected on the basis of a grid search on the number of trees, opting for the best split for a random forest. We used the area under the receiver operating characteristic curve to evaluate model performance.

show abstract

A machine learning-based prediction model of H3K27M mutations in brainstem gliomas using conventional MRI and clinical features

Cited by 42 publications

References 42 publications

Prediction of H3K27M-mutant brainstem glioma by amide proton transfer–weighted imaging and its derived radiomics

Prediction of H3K27M-mutant brainstem glioma by amide proton transfer–weighted imaging and its derived radiomics

Clinical, imaging, and molecular analysis of pediatric pontine tumors lacking characteristic imaging features of DIPG

Radiomics of Pediatric Low-Grade Gliomas: Toward a Pretherapeutic Differentiation of BRAF-Mutated and BRAF-Fused Tumors

Contact Info

Product

Resources

About