MRI-based radiomics for prognosis of pediatric diffuse intrinsic pontine glioma: an international study

Author:

Tam Lydia T12ORCID,Yeom Kristen W12,Wright Jason N34,Jaju Alok5,Radmanesh Alireza6,Han Michelle12,Toescu Sebastian7ORCID,Maleki Maryam8,Chen Eric9,Campion Andrew2,Lai Hollie A1011,Eghbal Azam A1011,Oztekin Ozgur1213,Mankad Kshitij714,Hargrave Darren7,Jacques Thomas S7,Goetti Robert15ORCID,Lober Robert M16,Cheshier Samuel H17,Napel Sandy18,Said Mourad19,Aquilina Kristian7,Ho Chang Y9,Monje Michelle120,Vitanza Nicholas A2122ORCID,Mattonen Sarah A2324ORCID

Affiliation:

1. Stanford University School of Medicine, Stanford, California, USA

2. Department of Radiology, Lucile Packard Children’s Hospital, Stanford University School of Medicine, Stanford, California, USA

3. Department of Radiology, Seattle Children’s Hospital, Seattle, Washington, USA

4. Harborview Medical Center, Seattle, Washington, USA

5. Department of Medical Imaging, Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, Illinois, USA

6. Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA

7. University College London, Great Ormond Street Institute of Child Health, London, UK

8. Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania, USA

9. Departments of Clinical Radiology & Imaging Sciences, Riley Children’s Hospital, Indiana University, Indianapolis, Indiana, USA

10. Department of Radiology, CHOC Children’s Hospital, Orange, California, USA

11. University of California, Irvine, California, USA

12. Department of Neuroradiology, Bakircay University, Cigli Education and Research Hospital, Izmir, Turkey

13. Department of Neuroradiology, Health Science University, Tepecik Education and Research Hospital, Izmir, Turkey

14. Department of Radiology, Great Ormond Street Hospital for Children, London, UK

15. Department of Medical Imaging, The Children’s Hospital at Westmead, The University of Sydney, Westmead, Australia

16. Department of Neurosurgery, Dayton Children’s Hospital, Wright State University Boonshoft School of Medicine, Dayton, Ohio, USA

17. Department of Neurosurgery, University of Utah School of Medicine, Salt Lake City, Utah, USA

18. Department of Radiology, Stanford University, Stanford, California, USA

19. Radiology Department Centre International Carthage Médicale, Monastir, Tunisia

20. Department of Neurology and Neurological Sciences, Stanford University, Stanford, California, USA

21. Division of Pediatric Hematology/Oncology, Department of Pediatrics, Seattle Children’s Hospital, Seattle, Washington, USA

22. Ben Towne Center for Childhood Cancer Research, Seattle Children’s Research Institute, Seattle, Washington, USA

23. Department of Medical Biophysics, Western University, London, Onatrio, Canada

24. Department of Oncology, Western University, London, Ontario, Canada

Abstract

Abstract Background Diffuse intrinsic pontine gliomas (DIPGs) are lethal pediatric brain tumors. Presently, MRI is the mainstay of disease diagnosis and surveillance. We identify clinically significant computational features from MRI and create a prognostic machine learning model. Methods We isolated tumor volumes of T1-post-contrast (T1) and T2-weighted (T2) MRIs from 177 treatment-naïve DIPG patients from an international cohort for model training and testing. The Quantitative Image Feature Pipeline and PyRadiomics was used for feature extraction. Ten-fold cross-validation of least absolute shrinkage and selection operator Cox regression selected optimal features to predict overall survival in the training dataset and tested in the independent testing dataset. We analyzed model performance using clinical variables (age at diagnosis and sex) only, radiomics only, and radiomics plus clinical variables. Results All selected features were intensity and texture-based on the wavelet-filtered images (3 T1 gray-level co-occurrence matrix (GLCM) texture features, T2 GLCM texture feature, and T2 first-order mean). This multivariable Cox model demonstrated a concordance of 0.68 (95% CI: 0.61–0.74) in the training dataset, significantly outperforming the clinical-only model (C = 0.57 [95% CI: 0.49–0.64]). Adding clinical features to radiomics slightly improved performance (C = 0.70 [95% CI: 0.64–0.77]). The combined radiomics and clinical model was validated in the independent testing dataset (C = 0.59 [95% CI: 0.51–0.67], Noether’s test P = .02). Conclusions In this international study, we demonstrate the use of radiomic signatures to create a machine learning model for DIPG prognostication. Standardized, quantitative approaches that objectively measure DIPG changes, including computational MRI evaluation, could offer new approaches to assessing tumor phenotype and serve a future role for optimizing clinical trial eligibility and tumor surveillance.

Publisher

Oxford University Press (OUP)

Subject

Electrical and Electronic Engineering,Building and Construction

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3