TY - JOUR
T1 - Deep Learning for Noninvasive Assessment of H3 K27M Mutation Status in Diffuse Midline Gliomas Using MR Imaging
AU - Li, Junjie
AU - Zhang, Peng
AU - Qu, Liying
AU - Sun, Ting
AU - Duan, Yunyun
AU - Wu, Minghao
AU - Weng, Jinyuan
AU - Li, Zhaohui
AU - Gong, Xiaodong
AU - Liu, Xing
AU - Wang, Yongzhi
AU - Jia, Wenqing
AU - Su, Xiaorui
AU - Yue, Qiang
AU - Li, Jianrui
AU - Zhang, Zhiqiang
AU - Barkhof, Frederik
AU - Huang, Raymond Y.
AU - Chang, Ken
AU - Sair, Haris
AU - Ye, Chuyang
AU - Zhang, Liwei
AU - Zhuo, Zhizheng
AU - Liu, Yaou
N1 - Funding Information:
We acknowledged all the colleagues who help the patient recruitment and MR imaging. This work was supported by the National Science Foundation of China (Nos. 81870958 and 81571631), the Beijing Municipal Natural Science Foundation for Distinguished Young Scholars (No. JQ20035), Beijing Youth Scholar and the Special Fund of the Pediatric Medical Coordinated Development Center of Beijing Hospitals Authority (No. XTYB201831). Frederik Barkhof was supported by the NIHR Biomedical Research Center at UCLH.
Publisher Copyright:
© 2023 International Society for Magnetic Resonance in Medicine.
PY - 2023
Y1 - 2023
N2 - Background: Determination of H3 K27M mutation in diffuse midline glioma (DMG) is key for prognostic assessment and stratifying patient subgroups for clinical trials. MRI can noninvasively depict morphological and metabolic characteristics of H3 K27M mutant DMG. Purpose: This study aimed to develop a deep learning (DL) approach to noninvasively predict H3 K27M mutation in DMG using T2-weighted images. Study Type: Retrospective and prospective. Population: For diffuse midline brain gliomas, 341 patients from Center-1 (27 ± 19 years, 184 males), 42 patients from Center-2 (33 ± 19 years, 27 males) and 35 patients (37 ± 18 years, 24 males). For diffuse spinal cord gliomas, 133 patients from Center-1 (30 ± 15 years, 80 males). Field Strength/Sequence: 5T and 3T, T2-weighted turbo spin echo imaging. Assessment: Conventional radiological features were independently reviewed by two neuroradiologists. H3 K27M status was determined by histopathological examination. The Dice coefficient was used to evaluate segmentation performance. Classification performance was evaluated using accuracy, sensitivity, specificity, and area under the curve. Statistical Tests: Pearson's Chi-squared test, Fisher's exact test, two-sample Student's t-test and Mann–Whitney U test. A two-sided P value <0.05 was considered statistically significant. Results: In the testing cohort, Dice coefficients of tumor segmentation using DL were 0.87 for diffuse midline brain and 0.81 for spinal cord gliomas. In the internal prospective testing dataset, the predictive accuracies, sensitivities, and specificities of H3 K27M mutation status were 92.1%, 98.2%, 82.9% in diffuse midline brain gliomas and 85.4%, 88.9%, 82.6% in spinal cord gliomas. Furthermore, this study showed that the performance generalizes to external institutions, with predictive accuracies of 85.7%–90.5%, sensitivities of 90.9%–96.0%, and specificities of 82.4%–83.3%. Data Conclusion: In this study, an automatic DL framework was developed and validated for accurately predicting H3 K27M mutation using T2-weighted images, which could contribute to the noninvasive determination of H3 K27M status for clinical decision-making. Evidence Level: 2. Technical Efficacy: Stage 2.
AB - Background: Determination of H3 K27M mutation in diffuse midline glioma (DMG) is key for prognostic assessment and stratifying patient subgroups for clinical trials. MRI can noninvasively depict morphological and metabolic characteristics of H3 K27M mutant DMG. Purpose: This study aimed to develop a deep learning (DL) approach to noninvasively predict H3 K27M mutation in DMG using T2-weighted images. Study Type: Retrospective and prospective. Population: For diffuse midline brain gliomas, 341 patients from Center-1 (27 ± 19 years, 184 males), 42 patients from Center-2 (33 ± 19 years, 27 males) and 35 patients (37 ± 18 years, 24 males). For diffuse spinal cord gliomas, 133 patients from Center-1 (30 ± 15 years, 80 males). Field Strength/Sequence: 5T and 3T, T2-weighted turbo spin echo imaging. Assessment: Conventional radiological features were independently reviewed by two neuroradiologists. H3 K27M status was determined by histopathological examination. The Dice coefficient was used to evaluate segmentation performance. Classification performance was evaluated using accuracy, sensitivity, specificity, and area under the curve. Statistical Tests: Pearson's Chi-squared test, Fisher's exact test, two-sample Student's t-test and Mann–Whitney U test. A two-sided P value <0.05 was considered statistically significant. Results: In the testing cohort, Dice coefficients of tumor segmentation using DL were 0.87 for diffuse midline brain and 0.81 for spinal cord gliomas. In the internal prospective testing dataset, the predictive accuracies, sensitivities, and specificities of H3 K27M mutation status were 92.1%, 98.2%, 82.9% in diffuse midline brain gliomas and 85.4%, 88.9%, 82.6% in spinal cord gliomas. Furthermore, this study showed that the performance generalizes to external institutions, with predictive accuracies of 85.7%–90.5%, sensitivities of 90.9%–96.0%, and specificities of 82.4%–83.3%. Data Conclusion: In this study, an automatic DL framework was developed and validated for accurately predicting H3 K27M mutation using T2-weighted images, which could contribute to the noninvasive determination of H3 K27M status for clinical decision-making. Evidence Level: 2. Technical Efficacy: Stage 2.
KW - H3 K27M mutation
KW - deep learning
KW - diffuse midline glioma
KW - magnetic resonance imaging
UR - http://www.scopus.com/inward/record.url?scp=85146440967&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85146440967&partnerID=8YFLogxK
U2 - 10.1002/jmri.28606
DO - 10.1002/jmri.28606
M3 - Article
C2 - 36692205
AN - SCOPUS:85146440967
SN - 1053-1807
JO - Journal of Magnetic Resonance Imaging
JF - Journal of Magnetic Resonance Imaging
ER -