OUCopula: Bi-Channel Multi-Label Copula-Enhanced Adapter-Based CNN for Myopia Screening Based on OU-UWF Images

TL;DR

This paper introduces OUCopula, a novel bi-channel CNN framework that leverages copula functions to jointly predict multiple myopia-related scores from OU-UWF images, outperforming single-eye models.

Contribution

The paper presents a new copula-enhanced multi-label CNN architecture for joint prediction of myopia scores from bi-eye images, addressing correlation and heterogeneity in outputs.

Findings

OUCopula outperforms backbone models in myopia score prediction.

Bi-channel input significantly improves prediction accuracy over single-eye models.

The framework demonstrates potential for extension to multi-channel paradigms.

Abstract

Myopia screening using cutting-edge ultra-widefield (UWF) fundus imaging is potentially significant for ophthalmic outcomes. Current multidisciplinary research between ophthalmology and deep learning (DL) concentrates primarily on disease classification and diagnosis using single-eye images, largely ignoring joint modeling and prediction for Oculus Uterque (OU, both eyes). Inspired by the complex relationships between OU and the high correlation between the (continuous) outcome labels (Spherical Equivalent and Axial Length), we propose a framework of copula-enhanced adapter convolutional neural network (CNN) learning with OU UWF fundus images (OUCopula) for joint prediction of multiple clinical scores. We design a novel bi-channel multi-label CNN that can (1) take bi-channel image inputs subject to both high correlation and heterogeneity (by sharing the same backbone network and employing adapters to parameterize the channel-wise discrepancy), and (2) incorporate correlation information between continuous output labels (using a copula). Solid experiments show that OUCopula achieves satisfactory performance in myopia score prediction compared to backbone models. Moreover, OUCopula can far exceed the performance of models constructed for single-eye inputs. Importantly, our study also hints at the potential extension of the bi-channel model to a multi-channel paradigm and the generalizability of OUCopula across various backbone CNNs.