Journal article
Differentiating MYCN-amplified RB1 wild-type retinoblastoma from biallelic RB1 mutant retinoblastoma using MR-based radiomics: a retrospective multicenter case–control study
Scientific reports, Vol.14(1), 25103
10/23/2024
DOI: 10.1038/s41598-024-76933-6
PMCID: PMC11499940
PMID: 39443629
Abstract
MYCN-amplified RB1 wild-type (MYCNampRB1+/+) retinoblastoma is a rare and aggressive subtype, often resistant to standard therapies. Identifying unique MRI features is crucial for diagnosing this subtype, as biopsy is not recommended. This study aimed to differentiate MYCNampRB1+/+ from the most prevalent RB1-/- retinoblastoma using pretreatment MRI and radiomics. Ninety-eight unilateral retinoblastoma patients (19 MYCN cases and 79 matched controls) were included. Tumors on T2-weighted MR images were manually delineated and validated by experienced radiologists. Radiomics analysis extracted 120 features per tumor. Several combinations of feature selection methods, oversampling techniques and machine learning (ML) classifiers were evaluated in a repeated fivefold cross-validation machine learning pipeline to yield the best-performing prediction model for MYCN. The best model used univariate feature selection, data oversampling (duplicating MYCN cases), and logistic regression classifier, achieving a mean AUC of 0.78 (SD 0.12). SHAP analysis highlighted lower sphericity, higher flatness, and greater gray-level heterogeneity as predictive for MYCNampRB1+/+ status, yielding an AUC of 0.81 (SD 0.11). This study shows the potential of MRI-based radiomics to distinguish MYCNampRB1+/+ and RB1-/- retinoblastoma subtypes.
Details
- Title: Subtitle
- Differentiating MYCN-amplified RB1 wild-type retinoblastoma from biallelic RB1 mutant retinoblastoma using MR-based radiomics: a retrospective multicenter case–control study
- Creators
- Christiaan M. de Bloeme - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Amsterdam, The Netherlands Amsterdam, 1007 MB The NetherlandsRobin W. Jansen - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Amsterdam, The Netherlands Amsterdam, 1007 MB The NetherlandsLiesbeth Cardoen - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Paris, FranceSophia Göricke - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Essen, GermanySabien van Elst - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Amsterdam, The Netherlands Amsterdam, 1007 MB The NetherlandsJaime Lyn Jessen - ImpactAparna Ramasubramanian - Children's Hospital of WisconsinAlison H. Skalet - Oregon Health & Science UniversityAudra K. Miller - Oregon Health & Science UniversityPhilippe Maeder - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Lausanne, SwitzerlandOgul E. Uner - Oregon Health & Science UniversityG. Baker Hubbard - Emory Eye CenterHans Grossniklaus - Emory Eye CenterH. Culver Boldt - University of IowaKim E. Nichols - St. Jude Children's Research HospitalRachel C. Brennan - St. Jude Children's Research HospitalSaugata Sen - Tata Medical CenterMériam Koob - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Lausanne, SwitzerlandSelma Sirin - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Zurich, SwitzerlandHervé J. Brisse - Institut CuriePaolo Galluzzi - European Retinoblastoma Imaging Collaboration (ERIC), Amsterdam, The Netherlands Siena, ItalyCharlotte J. Dommering - Dutch Cancer SocietyMatthijs Cysouw - Cancer Center AmsterdamRonald Boellaard - Vrije Universiteit AmsterdamJosephine C. Dorsman - Dutch Cancer SocietyAnnette C. Moll - Dutch Cancer SocietyMarcus C. de Jong - Vrije Universiteit AmsterdamPim de Graaf - Vrije Universiteit Amsterdam
- Resource Type
- Journal article
- Publication Details
- Scientific reports, Vol.14(1), 25103
- Publisher
- Nature Publishing Group UK
- DOI
- 10.1038/s41598-024-76933-6
- PMID
- 39443629
- PMCID
- PMC11499940
- ISSN
- 2045-2322
- eISSN
- 2045-2322
- Grant note
- Stichting Kinderen Kankervrij (KIKA): 342
Initiation and coordination of this study was funded by Stichting Kinderen Kankervrij (KIKA) (grant no. 342) and the Hanarth Foundation (grant for project titled MRI-based Deep Learning Segmentation and Quantita-tive Radiomics in Retinoblastoma: A Next Step Toward Personalized Interventions). Departmental funding was received by Casey Eye Institute, Oregon Health & Science University (A.H.S., A.K.M., and O.E.U.) from the National Institutes of Health (grant P30 EY010572) in addition to unrestricted departmental funding from Re-search to Prevent Blindness. Departmental funding was received by Emory Eye Center, Ocular Oncology Service (O.E.U., G.B.H., and H.G.) via National Eye Institute core grant P30 EY006360.
- Language
- English
- Date published
- 10/23/2024
- Academic Unit
- Ophthalmology and Visual Sciences
- Record Identifier
- 9984738389802771
Metrics
4 Record Views