LMOD+: A Comprehensive Multimodal Dataset and Benchmark for Developing and Evaluating Multimodal Large Language Models in Ophthalmology.

Artificial intelligence (artificial intelligence) offers potential solutions.

However, advancing multimodal large language models for ophthalmology is hindered by the lack of unified, comprehensive benchmark datasets for development and evaluation.

In this work, we present LMOD+, a large-scale multimodal ophthalmology benchmark dataset comprising 32,633 instances with multi-granular annotations across 12 common ophthalmic conditions and 5 imaging modalities.

First, we expanded the dataset by nearly 50% (from 21,933 to 32,633 instances).