Online citations, reference lists, and bibliographies.
Please confirm you are human
(Sign Up for free to never see this)
← Back to Search

Diffusion Radiomics As A Diagnostic Model For Atypical Manifestation Of Primary Central Nervous System Lymphoma: Development And Multicenter External Validation

Daesung Kang, J. Park, Y. Kim, J. Kim, J. Y. Oh, Jung-Youn Kim, YiKyung Kim, S. Kim, H. S. Kim
Published 2018 · Medicine

Save to my Library
Download PDF
Analyze on Scholarcy
Share
Background Radiomics is a rapidly growing field in neuro-oncology, but studies have been limited to conventional MRI, and external validation is critically lacking. We evaluated technical feasibility, diagnostic performance, and generalizability of a diffusion radiomics model for identifying atypical primary central nervous system lymphoma (PCNSL) mimicking glioblastoma. Methods A total of 1618 radiomics features were extracted from diffusion and conventional MRI from 112 patients (training set, 70 glioblastomas and 42 PCNSLs). Feature selection and classification were optimized using a machine-learning algorithm. The diagnostic performance was tested in 42 patients of internal and external validation sets. The performance was compared with that of human readers (2 neuroimaging experts), cerebral blood volume (90% histogram cutoff, CBV90), and apparent diffusion coefficient (10% histogram, ADC10) using the area under the receiver operating characteristic curve (AUC). Results The diffusion radiomics was optimized with the combination of recursive feature elimination and a random forest classifier (AUC 0.983, stability 2.52%). In internal validation, the diffusion model (AUC 0.984) showed similar performance with conventional (AUC 0.968) or combined diffusion and conventional radiomics (AUC 0.984) and better than human readers (AUC 0.825-0.908), CBV90 (AUC 0.905), or ADC10 (AUC 0.787) in atypical PCNSL diagnosis. In external validation, the diffusion radiomics showed robustness (AUC 0.944) and performed better than conventional radiomics (AUC 0.819) and similar to combined radiomics (AUC 0.946) or human readers (AUC 0.896-0.930). Conclusion The diffusion radiomics model had good generalizability and yielded a better diagnostic performance than conventional radiomics or single advanced MRI in identifying atypical PCNSL mimicking glioblastoma.
This paper references
10.1016/j.mri.2012.06.010
Radiomics: the process and the challenges.
Virendra Kumar (2012)
10.1148/radiol.13130016
Recurrent glioblastoma: optimum area under the curve method derived from dynamic contrast-enhanced T1-weighted perfusion MR imaging.
W. J. Chung (2013)
10.1007/s11548-013-0840-8
The Medical Imaging Interaction Toolkit: challenges and advances
M. Nolden (2013)
10.1109/ICCV.2015.478
Infinite Feature Selection
Giorgio Roffo (2015)
10.1016/J.MRI.2003.09.001
Influence of MRI acquisition protocols and image intensity normalization methods on texture classification.
G. Collewet (2004)
10.1038/npjbcancer.2016.12
Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set
H. Li (2016)
10.1016/j.mric.2010.10.006
Diffusion MR imaging in central nervous system.
Claudio de Carvalho Rangel (2011)
10.1158/1078-0432.CCR-16-0702
Large-scale Radiomic Profiling of Recurrent Glioblastoma Identifies an Imaging Predictor for Stratifying Anti-Angiogenic Treatment Response
P. Kickingereder (2016)
10.1162/153244303322753616
An Introduction to Variable and Feature Selection
I. Guyon (2003)
10.1016/j.neuroimage.2016.02.036
Removing inter-subject technical variability in magnetic resonance imaging studies
Jean-Philippe Fortin (2016)
10.1038/srep13087
Machine Learning methods for Quantitative Radiomic Biomarkers
Chintan Parmar (2015)
10.1016/j.nicl.2014.08.008
Statistical normalization techniques for magnetic resonance imaging☆☆☆
R. Shinohara (2014)
10.1016/j.ejrad.2016.07.005
Utility of dynamic contrast-enhanced magnetic resonance imaging for differentiating glioblastoma, primary central nervous system lymphoma and brain metastatic tumor.
S. Lu (2016)
10.1148/radiol.14132740
Primary central nervous system lymphoma and atypical glioblastoma: multiparametric differentiation by using diffusion-, perfusion-, and susceptibility-weighted MR imaging.
P. Kickingereder (2014)
10.1111/J.1600-0587.2012.07348.X
Collinearity: a review of methods to deal with it and a simulation study evaluating their performance
C. Dormann (2013)
10.1016/j.neuroimage.2010.09.025
A reproducible evaluation of ANTs similarity metric performance in brain image registration
B. Avants (2011)
10.1038/ncomms5006
Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
H. Aerts (2014)
10.1109/42.563664
Multimodality image registration by maximization of mutual information
F. Maes (1997)
Australian Imaging Biomarkers Lifestyle Flagship Study of Ageing; Alzheimer’s Disease Neuroimaging Initiative. Statistical normalization techniques for magnetic resonance imaging
RT Shinohara (2014)
10.1148/radiol.14131895
Atypical imaging features of primary central nervous system lymphoma that mimics glioblastoma: utility of intravoxel incoherent motion MR imaging.
C. Suh (2014)
Alzheimer’s Disease Neuroimaging Initiative. Removing intersubject technical variability in magnetic resonance imaging studies
JP Fortin (2016)
10.1371/journal.pone.0173430
The performance of MR perfusion-weighted imaging for the differentiation of high-grade glioma from primary central nervous system lymphoma: A systematic review and meta-analysis
Weilin Xu (2017)
10.3174/ajnr.A2171
Central Nervous System Lymphoma: Characteristic Findings on Traditional and Advanced Imaging
I. Haldorsen (2011)
10.3174/ajnr.A0872
Primary Cerebral Lymphoma and Glioblastoma Multiforme: Differences in Diffusion Characteristics Evaluated with Diffusion Tensor Imaging
C. Toh (2008)
Texture Analysis Methods - A Review
A. Materka (1998)
10.3174/ajnr.A1750
Diffusion-Weighted MR Imaging Derived Apparent Diffusion Coefficient Is Predictive of Clinical Outcome in Primary Central Nervous System Lymphoma
R. Barajas (2010)
10.1148/radiol.2016160845
Radiomic Profiling of Glioblastoma: Identifying an Imaging Predictor of Patient Survival with Improved Performance over Established Clinical and Radiologic Risk Models.
P. Kickingereder (2016)
10.3389/fonc.2015.00272
Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer
Chintan Parmar (2015)
10.1002/jmri.25583
Diffusion radiomics analysis of intratumoral heterogeneity in a murine prostate cancer model following radiotherapy: Pixelwise correlation with histology
Y. Lin (2017)
10.1038/srep23428
Reproducibility of radiomics for deciphering tumor phenotype with imaging
B. Zhao (2016)
On Bias , Variance , 0 / 1-Loss , and the Curse-of-Dimensionality
Weiqiang Dong (2014)
Diffusion-weighted MR imaging of intracerebral masses: comparison with conventional MR imaging and histologic findings.
T. Stadnik (2001)
10.1158/1078-0432.CCR-16-2910
Radiomics Features of Multiparametric MRI as Novel Prognostic Factors in Advanced Nasopharyngeal Carcinoma
Bin Zhang (2017)
10.1043/1543-2165-132.11.1830
Primary central nervous system lymphoma.
S. Bhagavathi (2008)
10.3171/FOC.2006.21.5.4
Distinguishing primary central nervous system lymphoma from other central nervous system diseases: a neurosurgical perspective on diagnostic dilemmas and approaches.
M. Hunt (2006)
10.1001/jamaoncol.2015.0298
Atypical Imaging Findings in an Immunocompetent Patient. Primary central nervous system lymphoma.
J. Savage (2015)
10.1109/ICAPR.2009.36
Relevant and Redundant Feature Analysis with Ensemble Classification
Rakkrit Duangsoithong (2009)
10.1186/1471-2164-9-S2-S27
Gene selection algorithm by combining reliefF and mRMR
Y. Zhang (2007)
10.1093/neuonc/now135
Radiogenomics to characterize regional genetic heterogeneity in glioblastoma
L. Hu (2017)
10.3389/fonc.2016.00071
Exploratory Study to Identify Radiomics Classifiers for Lung Cancer Histology
Weimiao Wu (2016)
10.1093/neuonc/now256
MRI features predict survival and molecular markers in diffuse lower-grade gliomas
H. Zhou (2017)



This paper is referenced by
10.1007/s00330-020-06927-1
Current status and quality of radiomics studies in lymphoma: a systematic review
Hongxi Wang (2020)
10.1002/jmri.27288
Primary Central Nervous System Lymphoma: Clinical Evaluation of Automated Segmentation on Multiparametric MRI Using Deep Learning
Lenhard Pennig (2020)
10.1007/s00234-018-2091-4
Radiomics features to distinguish glioblastoma from primary central nervous system lymphoma on multi-parametric MRI
YiKyung Kim (2018)
10.1016/j.clineuro.2019.105565
Application of Radiomics in Central Nervous System Diseases: a Systematic literature review
Yanghua Fan (2019)
10.1038/s41598-018-37984-8
Combining Multiple Magnetic Resonance Imaging Sequences Provides Independent Reproducible Radiomics Features
A. Lecler (2019)
10.1007/s00234-020-02424-w
Promises of artificial intelligence in neuroradiology: a systematic technographic review
A. Olthof (2020)
10.3171/2018.8.FOCUS18325
Machine learning applications for the differentiation of primary central nervous system lymphoma from glioblastoma on imaging: a systematic review and meta-analysis.
A. Nguyen (2018)
10.1007/s00330-020-06993-5
MR imaging of epithelial ovarian cancer: a combined model to predict histologic subtypes
LuoDan Qian (2020)
10.1186/s40644-019-0266-9
Man or machine? Prospective comparison of the version 2018 EASL, LI-RADS criteria and a radiomics model to diagnose hepatocellular carcinoma
Hanyu Jiang (2019)
10.1007/s00330-020-07414-3
Diffusion and perfusion MRI radiomics obtained from deep learning segmentation provides reproducible and comparable diagnostic model to human in post-treatment glioblastoma
J. Park (2020)
10.1007/s00330-019-06548-3
Diffusion- and perfusion-weighted MRI radiomics model may predict isocitrate dehydrogenase (IDH) mutation and tumor aggressiveness in diffuse lower grade glioma
Minjae Kim (2019)
10.3348/JKSR.2020.81.3.467
뇌종양 영상의 현재와 미래
박 지은 (2020)
10.31557/apjcb.2020.5.4.189-199
Reviewing the Role of Artificial Intelligence in Cancer
Shankargouda Patil (2020)
10.1007/s00330-018-5830-3
Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging
Y. Park (2018)
10.1007/s00330-018-5747-x
Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types
Y. Zhang (2018)
10.1038/s41598-019-42276-w
Radiomic features and multilayer perceptron network classifier: a robust MRI classification strategy for distinguishing glioblastoma from primary central nervous system lymphoma
Jihye Yun (2019)
10.3348/kjr.2019.0847
Radiomics and Deep Learning from Research to Clinical Workflow: Neuro-Oncologic Imaging
J. Park (2020)
10.1038/s41598-020-68980-6
Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation
S. Bae (2020)
10.1155/2020/5042356
Differential Diagnosis of Solitary Fibrous Tumor/Hemangiopericytoma and Angiomatous Meningioma Using Three-Dimensional Magnetic Resonance Imaging Texture Feature Model
Junyi Dong (2020)
10.1007/s10278-020-00322-4
Deep Convolutional Radiomic Features on Diffusion Tensor Images for Classification of Glioma Grades
Zhiwei Zhang (2020)
10.1007/s00234-020-02529-2
Diffusion tensor and postcontrast T1-weighted imaging radiomics to differentiate the epidermal growth factor receptor mutation status of brain metastases from non-small cell lung cancer
Y. Park (2020)
10.3348/kjr.2018.0070
Reproducibility and Generalizability in Radiomics Modeling: Possible Strategies in Radiologic and Statistical Perspectives
J. Park (2019)
10.1016/j.acra.2020.05.040
Radiomics Signatures Based on Multiparametric MRI for the Preoperative Prediction of the HER2 Status of Patients with Breast Cancer.
J. Zhou (2020)
10.3322/caac.21552
Artificial intelligence in cancer imaging: Clinical challenges and applications
W. Bi (2019)
10.1007/s00259-019-04372-x
Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics
M. Sollini (2019)
10.1007/s00330-020-07074-3
MR imaging of thymomas: a combined radiomics nomogram to predict histologic subtypes
G. Xiao (2020)
10.3389/fonc.2020.00534
Accurate Preoperative Distinction of Intracranial Hemangiopericytoma From Meningioma Using a Multihabitat and Multisequence-Based Radiomics Diagnostic Technique
Jing-wei Wei (2020)
10.1016/j.nicl.2019.101912
18F-FDG-PET-based radiomics features to distinguish primary central nervous system lymphoma from glioblastoma
Z. Kong (2019)
10.3348/jksr.2020.0150
The Latest Trends in Attention Mechanisms and Their Application in Medical Imaging
신 형섭 (2020)
10.1186/s12885-019-6504-5
A systematic review reporting quality of radiomics research in neuro-oncology: toward clinical utility and quality improvement using high-dimensional imaging features
J. Park (2020)
10.1007/s00234-019-02312-y
Diffusion tensor imaging radiomics in lower-grade glioma: improving subtyping of isocitrate dehydrogenase mutation status
C. J. Park (2019)
10.1016/j.wneu.2018.11.155
Differentiation of Primary Central Nervous System Lymphoma From Glioblastoma: Quantitative Analysis Using Arterial Spin Labeling and Diffusion Tensor Imaging.
A. A. A. Abdel Razek (2019)
See more
Semantic Scholar Logo Some data provided by SemanticScholar