We propose glaucoma lesion evaluation and analysis with multimodal imaging (GLEAM), the first publicly available tri-modal glaucoma dataset comprising scanning laser ophthalmoscopy fundus images, circumpapillary OCT images, and visual field pattern deviation maps, annotated with four disease stages, enabling effective exploitation of multimodal complementary information and facilitating accurate diagnosis and treatment across disease stages. To effectively integrate cross-modal information, we propose hierarchical attentive masked modeling (HAMM) for multimodal glaucoma classification. Our framework employs hierarchical attentive encoders and light decoders to focus cross-modal representation learning on the encoder.
@article{arxiv.2603.12800,
title = {GLEAM: A Multimodal Imaging Dataset and HAMM for Glaucoma Classification},
author = {Jiao Wang and Chi Liu and Yiying Zhang and Hongchen Luo and Zhifen Guo and Ying Hu and Ke Xu and Jing Zhou and Hongyan Xu and Ruiting Zhou and Man Tang},
journal= {arXiv preprint arXiv:2603.12800},
year = {2026}
}