Improving Generalization of Deep Learning for Glaucoma Classification Under Real-World Domain Shift via Unsupervised...

To develop and evaluate an unsupervised domain adaptation (UDA) framework for glaucoma classification from fundus images that improves the generalizability of deep learning (DL) models across heterogeneous imaging characteristics and clinical settings.

We developed an adversarial UDA framework that adapts a labeled source domain to an unlabeled target domain by jointly optimizing glaucoma classification and domain discrimination. A total of 6906 fundus images were included: 1422 images (full-view and optic nerve head-cropped) derived from 711 fundus photographs of 520 patients from the University of Illinois Chicago and 5484 images from three public datasets (RIMONE-DL, n = 371; REFUGE, n = 259; LAG, n = 4854). Performance was evaluated across multiple source-target domain pairs. Saliency map analysis compared feature utilization between UDA and standard DL models.

Across diverse source-target dataset pairs, the proposed UDA framework improved standard DL classification accuracy by up to 40.0% and area under the curve (AUC) by up to 59.8% in extreme domain shift experiments. UDA also reduced the performance gap to the ideal target-trained model by up to 82.6% for accuracy and 38.1% for AUC. When applied to unseen domains, UDA improved classification accuracy by up to 14.7% relative to standard DL.

The proposed UDA framework improves cross-domain generalizability of DL-based glaucoma classification from fundus images. Compared with standard DL models, UDA exhibits feature utilization patterns more aligned with an ideal baseline, reducing overreliance on optic nerve head-specific cues and supporting more robust decision-making under domain shift.

By enabling glaucoma classification without requiring labeled data from new clinical sites, this UDA framework addresses a key barrier to deploying artificial intelligence-based screening tools across diverse real-world ophthalmic settings.