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

Basit Öğe Kaydı
dc.authoridHan, Michelle/0000-0003-2812-6193
dc.authoridHargrave, Darren/0000-0001-8219-9807
dc.authoridToescu, Sebastian M/0000-0001-8768-9231
dc.authoridYeom, Kristen/0000-0001-9860-3368
dc.authoridRadmanesh, Alireza/0000-0002-8581-2600
dc.authoridTam, Lydia/0000-0002-9900-3249
dc.authoridAquilina, Kristian/0000-0001-7015-5196
dc.authorwosidHargrave, Darren/H-1066-2014
dc.contributor.authorTam, Lydia T.
dc.contributor.authorYeom, Kristen W.
dc.contributor.authorWright, Jason N.
dc.contributor.authorJaju, Alok
dc.contributor.authorRadmanesh, Alireza
dc.contributor.authorHan, Michelle
dc.contributor.authorToescu, Sebastian
dc.date.accessioned2023-03-22T19:47:32Z
dc.date.available2023-03-22T19:47:32Z
dc.date.issued2021
dc.departmentBelirleneceken_US
dc.description.abstractBackground. 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) andT2-weighted (T2) MRIs from 177 treatment-naive 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 graylevel 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.en_US
dc.identifier.doi10.1093/noajnl/vdab042
dc.identifier.issn2632-2498
dc.identifier.issue1en_US
dc.identifier.pmid33977272en_US
dc.identifier.scopus2-s2.0-85119104101en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.1093/noajnl/vdab042
dc.identifier.urihttps://hdl.handle.net/20.500.14034/753
dc.identifier.volume3en_US
dc.identifier.wosWOS:000905125400065en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.language.isoenen_US
dc.publisherOxford Univ Pressen_US
dc.relation.journalNeuro-Oncology Advancesen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectdiffuse intrinsic pontine gliomasen_US
dc.subjectdiffuse midline gliomaen_US
dc.subjectH3K27M-mutanten_US
dc.subjectmachine learningen_US
dc.subjectmagnetic resonance imagingen_US
dc.subjectradiomicsen_US
dc.subjectImaging Radiomicsen_US
dc.subjectHigh-Gradeen_US
dc.subjectSurvivalen_US
dc.subjectTumorsen_US
dc.subjectSubgroupsen_US
dc.subjectFeaturesen_US
dc.subjectSystemen_US
dc.subjectDipgen_US
dc.titleMRI-based radiomics for prognosis of pediatric diffuse intrinsic pontine glioma: an international studyen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
MRI-based.pdf
Boyut:
560.48 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam metin / Full text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Dahili Tıp Bilimleri Bölümü Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu