Orbital CT deep learning models in thyroid eye disease rival medical specialists' performance in optic neuropathy prediction in a quaternary referral center and revealed impact of the bony walls.
Authors
Affiliations (10)
Affiliations (10)
- Department of Neuroradiology, Singapore General Hospital, Singapore, Singapore.
- SingHealth Duke-NUS Radiological Sciences Academic Clinical Programme, Singapore, Singapore.
- NUS Graduate School, National University of Singapore, Singapore, Singapore.
- Save Sight Institute, University of Sydney, Camperdown, Australia.
- Department of Oculoplastic Surgery, Sydney Eye Hospital, Sydney, Australia.
- Department of Oculoplastic Surgery, Singapore National Eye Centre, Singapore, Singapore.
- Department of Computer Science, School of Computing, National University of Singapore, Singapore, Singapore.
- Data Science, Singapore Eye Research Institute, Singapore, Singapore.
- A*Star, Institute of High Performance Computing (IHPC), Singapore, Singapore.
- Department of Vascular and Interventional Radiology, Singapore General Hospital, Singapore, Singapore.
Abstract
To develop and evaluate orbital CT deep learning (DL) models in optic neuropathy (ON) prediction in patients diagnosed with thyroid eye disease (TED), using partial versus entire 2D versus 3D images for input. Patients with TED ±ON diagnosed at a quaternary-level practice and who underwent orbital CT between 2002 and 2017 were included. DL models were developed using annotated CT data. The DL models were used to evaluate the hold-out test set. ON classification performances were compared between models and medical specialists, and saliency maps applied to randomized cases. 36/252 orbits in 126 TED patients (mean age, 51 years; 81 women) had clinically confirmed ON. With 2D image input for ON prediction, our models achieved (a) sensitivity 89%, AUC 0.86 on entire coronal orbital apex including bony walls, and (b) specificity 92%, AUC 0.79 on partial axial lateral orbital wall only annotations. ON classification performance was similar (<i>p</i> = 0.58) between DL model and medical specialists. DL models trained on 2D CT annotations rival medical specialists in ON classification, with potential to objectively enhance clinical triage for sight-saving intervention and incorporate model variants in the workflow to harness differential performance metrics.