ScholarDeck

AI / informaticsEuropean radiology · 2026

Enhanced prediction of postlaminar optic nerve invasion in retinoblastoma using high-resolution MRI: integrating qualitative imaging features, optic nerve measurements and tumor radiomics.

Christiaan M de Bloeme, Sabien van Elst, Sophia Göricke … European Retinoblastoma Imaging Collaboration

OphthalmologyAI / informatics

MRI model integrating radiomics and optic nerve measures predicts optic nerve invasion accurately

Enhanced prediction of postlaminar optic nerve invasion in retinoblastoma using high-resolution MRI: integrating qualitative imaging features, optic nerve measurements and tumor radiomics.

Christiaan M de Bloeme … European Retinoblastoma Imaging Collaboration

European radiology · 2026

Purpose

This study aimed to develop a model for predicting postlaminar optic nerve invasion (postlaminar optic nerve invasion) in retinoblastoma patients using MR imaging.

Methods

This retrospective, multicenter case-control study included patients with histopathologically confirmed postlaminar optic nerve invasion and high-spatial-resolution pretreatment MR images.

n = 146 control

Results

model accurately distinguished eyes with nerve invasion from those without

AUC 0.90 (95% CI 0.86 to 0.95)

null 0

0.86

0.95

CI excludes the null - significant

More results

This resulted in 30 eyes with histopathologically proven postlaminar optic nerve invasion and 146 control eyes without postlaminar optic nerve invasion.

More results

Manual distal optic nerve diameter measurements were chosen for prediction modeling, as this significantly outperformed the automatic approach for detecting postlaminar optic nerve invasion, achieving an AUC of 0.85 compared to 0.68 (p < 0.001) for the automatic method.

“

Conclusion · 1 of 3

This study developed a high-performing model for predicting postlaminar optic nerve invasion, highlighting the value of advanced MR imaging and the integration of both qualitative and quantitative features.

Conclusion · 2 of 3

By enhancing risk assessment, this model could provide clinicians with an additional tool for guiding treatment decisions, optimizing early intervention strategies, and ultimately improving patient care in retinoblastoma management.

Conclusion · 3 of 3

KEY POINTS: Question Accurately detecting postlaminar optic nerve invasion in retinoblastoma remains challenging.

Post

Enhanced prediction of postlaminar optic nerve invasion in retinoblastoma using high-resolution MRI: integrating qualitative imaging features, optic nerve measurements and tumor radiomics.

MRI model integrating radiomics and optic nerve measures predicts optic nerve invasion accurately

Related papers