Quantitative magnetic resonance imaging radiomics predicts photoreceptorness status in retinoblastoma.
Authors
Affiliations (15)
Affiliations (15)
- European Retinoblastoma Imaging Collaboration, Amsterdam, Netherlands. [email protected].
- Imaging and Biomarkers, Cancer Center Amsterdam, Amsterdam, Netherlands. [email protected].
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Location VUmc, De Boelelaan 1117, Amsterdam, Noord Holland, 1081HV, Netherlands. [email protected].
- Imaging and Biomarkers, Cancer Center Amsterdam, Amsterdam, Netherlands.
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Location VUmc, De Boelelaan 1117, Amsterdam, Noord Holland, 1081HV, Netherlands.
- Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University, Portland, United States.
- Ocular Oncology Service, Emory Eye Center, Atlanta, United States.
- Department of Human Genetics, Amsterdam UMC, Location VUmc, Amsterdam, Netherlands.
- European Retinoblastoma Imaging Collaboration, Amsterdam, Netherlands.
- Department of Radiology, Institute Curie, Paris, France.
- Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany.
- Department of Radiology, Centre Hospitalier Universitaire Vaudois (CHUV) and University of Lausanne, Lausanne, Switzerland.
- Department of Diagnostic Imaging, University Children's Hospital Zurich, Zurich, Switzerland.
- Unit of NeuroImaging and NeuroIntervention, Azienda Ospedaliera Universitaria Santa Maria alle Scotte, Siena, Italy.
- Department of Ophthalmology, Amsterdam UMC, Location VUmc, Amsterdam, Netherlands.
Abstract
Molecular characteristics of retinoblastoma cannot be assessed before treatment because tumor biopsy is contraindicated. Photoreceptorness reflects photoreceptor-related gene expression and tumor differentiation. Non-invasive imaging biomarkers that capture this biology are therefore needed. To evaluate whether quantitative radiomics derived from pretreatment magnetic resonance imaging can predict loss of photoreceptorness in retinoblastoma and validate this approach in an independent cohort. In this retrospective multicenter study, patients with retinoblastoma who underwent primary enucleation and had both pretreatment T2-weighted magnetic resonance imaging and genome-wide messenger RNA expression data were included. Tumors in the highest and lowest photoreceptorness quartiles were analyzed. Whole-tumor segmentations were used to extract radiomic features with PyRadiomics. Multiple machine-learning pipelines were evaluated using repeated stratified cross-validation, and the best-performing model was tested in an independent cohort. Forty-five patients (median age, 18 months [range, 2-70], 18 female) were included: 29 in the training cohort and 16 in the independent testing cohort. The best-performing model used recursive feature elimination with a random forest classifier and achieved a mean cross-validated area under the receiver operating characteristic curve of 0.83 in the training cohort. In the independent testing cohort, the model achieved an area under the receiver operating characteristic curve of 0.81 (95% confidence interval, 0.54-1.00) for predicting loss of photoreceptorness. Quantitative magnetic resonance imaging radiomics showed preliminary moderate-to-good discriminatory performance for non-invasively predicting photoreceptorness status in retinoblastoma. These proof-of-concept findings suggest that radiomics may capture imaging features related to molecular tumor differentiation and could support the development of personalized treatment strategies.