Differentiation between spinal cord diffuse midline glioma with histone H3 K27M mutation and wild type: comparative magnetic resonance imaging

Jo Sung Jung, Yoon Seong Choi, Sung Soo Ahn, Seong Yi, Se Hoon Kim, Seung Koo Lee

Research output: Contribution to journalArticle

Abstract

Purpose: Diffuse midline glioma with histone H3 K27M mutation is a new entity described in the 2016 update of the World Health Organization Classification of Tumors of the Central Nervous System. The purpose of this study was to evaluate the clinical and imaging characteristics to predict the presence of H3 K27M mutation in spinal cord glioma using a machine learning–based classification model. Methods: A total of 41 spinal cord glioma patients consisting of 24 H3 K27M mutants and 17 wild types were enrolled in this retrospective study. A total of 17 clinical and radiological features were evaluated. The random forest (RF) model was trained with the clinical and radiological features to predict the presence of H3 K27M mutation. The diagnostic ability of the RF model was evaluated using receiver operating characteristic (ROC) analysis. Area under the ROC curves (AUC) was calculated. Results: MR imaging features of spinal cord diffuse midline gliomas were heterogeneous. Hemorrhage was the only variable that was able to differentiate H3 K27M mutated tumors from wild-type tumors in univariate analysis (p = 0.033). RF classifier yielded 0.632 classification AUC (95% CI, 0.456–0.808), 63.4% accuracy, 45.8% sensitivity, and 88.2% specificity. Conclusion: Our findings indicate that clinical and radiological features are associated with H3 K27M mutation status in spinal cord glioma.

Original languageEnglish
Pages (from-to)313-322
Number of pages10
JournalNeuroradiology
Volume61
Issue number3
DOIs
Publication statusPublished - 2019 Mar 11

Fingerprint

Glioma
Histones
Spinal Cord
Magnetic Resonance Imaging
Mutation
ROC Curve
Central Nervous System Neoplasms
Area Under Curve
Neoplasms
Retrospective Studies
Hemorrhage
Sensitivity and Specificity
Forests

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Clinical Neurology
  • Cardiology and Cardiovascular Medicine

Cite this

Jung, Jo Sung ; Choi, Yoon Seong ; Ahn, Sung Soo ; Yi, Seong ; Kim, Se Hoon ; Lee, Seung Koo. / Differentiation between spinal cord diffuse midline glioma with histone H3 K27M mutation and wild type : comparative magnetic resonance imaging. In: Neuroradiology. 2019 ; Vol. 61, No. 3. pp. 313-322.
@article{61d5c20516df46d5b3e647b91c121048,
title = "Differentiation between spinal cord diffuse midline glioma with histone H3 K27M mutation and wild type: comparative magnetic resonance imaging",
abstract = "Purpose: Diffuse midline glioma with histone H3 K27M mutation is a new entity described in the 2016 update of the World Health Organization Classification of Tumors of the Central Nervous System. The purpose of this study was to evaluate the clinical and imaging characteristics to predict the presence of H3 K27M mutation in spinal cord glioma using a machine learning–based classification model. Methods: A total of 41 spinal cord glioma patients consisting of 24 H3 K27M mutants and 17 wild types were enrolled in this retrospective study. A total of 17 clinical and radiological features were evaluated. The random forest (RF) model was trained with the clinical and radiological features to predict the presence of H3 K27M mutation. The diagnostic ability of the RF model was evaluated using receiver operating characteristic (ROC) analysis. Area under the ROC curves (AUC) was calculated. Results: MR imaging features of spinal cord diffuse midline gliomas were heterogeneous. Hemorrhage was the only variable that was able to differentiate H3 K27M mutated tumors from wild-type tumors in univariate analysis (p = 0.033). RF classifier yielded 0.632 classification AUC (95{\%} CI, 0.456–0.808), 63.4{\%} accuracy, 45.8{\%} sensitivity, and 88.2{\%} specificity. Conclusion: Our findings indicate that clinical and radiological features are associated with H3 K27M mutation status in spinal cord glioma.",
author = "Jung, {Jo Sung} and Choi, {Yoon Seong} and Ahn, {Sung Soo} and Seong Yi and Kim, {Se Hoon} and Lee, {Seung Koo}",
year = "2019",
month = "3",
day = "11",
doi = "10.1007/s00234-019-02154-8",
language = "English",
volume = "61",
pages = "313--322",
journal = "Neuroradiology",
issn = "0028-3940",
publisher = "Springer Verlag",
number = "3",

}

Differentiation between spinal cord diffuse midline glioma with histone H3 K27M mutation and wild type : comparative magnetic resonance imaging. / Jung, Jo Sung; Choi, Yoon Seong; Ahn, Sung Soo; Yi, Seong; Kim, Se Hoon; Lee, Seung Koo.

In: Neuroradiology, Vol. 61, No. 3, 11.03.2019, p. 313-322.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Differentiation between spinal cord diffuse midline glioma with histone H3 K27M mutation and wild type

T2 - comparative magnetic resonance imaging

AU - Jung, Jo Sung

AU - Choi, Yoon Seong

AU - Ahn, Sung Soo

AU - Yi, Seong

AU - Kim, Se Hoon

AU - Lee, Seung Koo

PY - 2019/3/11

Y1 - 2019/3/11

N2 - Purpose: Diffuse midline glioma with histone H3 K27M mutation is a new entity described in the 2016 update of the World Health Organization Classification of Tumors of the Central Nervous System. The purpose of this study was to evaluate the clinical and imaging characteristics to predict the presence of H3 K27M mutation in spinal cord glioma using a machine learning–based classification model. Methods: A total of 41 spinal cord glioma patients consisting of 24 H3 K27M mutants and 17 wild types were enrolled in this retrospective study. A total of 17 clinical and radiological features were evaluated. The random forest (RF) model was trained with the clinical and radiological features to predict the presence of H3 K27M mutation. The diagnostic ability of the RF model was evaluated using receiver operating characteristic (ROC) analysis. Area under the ROC curves (AUC) was calculated. Results: MR imaging features of spinal cord diffuse midline gliomas were heterogeneous. Hemorrhage was the only variable that was able to differentiate H3 K27M mutated tumors from wild-type tumors in univariate analysis (p = 0.033). RF classifier yielded 0.632 classification AUC (95% CI, 0.456–0.808), 63.4% accuracy, 45.8% sensitivity, and 88.2% specificity. Conclusion: Our findings indicate that clinical and radiological features are associated with H3 K27M mutation status in spinal cord glioma.

AB - Purpose: Diffuse midline glioma with histone H3 K27M mutation is a new entity described in the 2016 update of the World Health Organization Classification of Tumors of the Central Nervous System. The purpose of this study was to evaluate the clinical and imaging characteristics to predict the presence of H3 K27M mutation in spinal cord glioma using a machine learning–based classification model. Methods: A total of 41 spinal cord glioma patients consisting of 24 H3 K27M mutants and 17 wild types were enrolled in this retrospective study. A total of 17 clinical and radiological features were evaluated. The random forest (RF) model was trained with the clinical and radiological features to predict the presence of H3 K27M mutation. The diagnostic ability of the RF model was evaluated using receiver operating characteristic (ROC) analysis. Area under the ROC curves (AUC) was calculated. Results: MR imaging features of spinal cord diffuse midline gliomas were heterogeneous. Hemorrhage was the only variable that was able to differentiate H3 K27M mutated tumors from wild-type tumors in univariate analysis (p = 0.033). RF classifier yielded 0.632 classification AUC (95% CI, 0.456–0.808), 63.4% accuracy, 45.8% sensitivity, and 88.2% specificity. Conclusion: Our findings indicate that clinical and radiological features are associated with H3 K27M mutation status in spinal cord glioma.

UR - http://www.scopus.com/inward/record.url?scp=85060468121&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060468121&partnerID=8YFLogxK

U2 - 10.1007/s00234-019-02154-8

DO - 10.1007/s00234-019-02154-8

M3 - Article

C2 - 30662997

AN - SCOPUS:85060468121

VL - 61

SP - 313

EP - 322

JO - Neuroradiology

JF - Neuroradiology

SN - 0028-3940

IS - 3

ER -