Saved in:
Bibliographic Details
Main Authors: Xu, Pusheng, Gong, Xia, Chen, Xiaolan, Zhang, Weiyi, Yang, Jiancheng, Yan, Bingjie, Yuan, Meng, Zheng, Yalin, He, Mingguang, Shi, Danli
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.19624
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918034744016896
author Xu, Pusheng
Gong, Xia
Chen, Xiaolan
Zhang, Weiyi
Yang, Jiancheng
Yan, Bingjie
Yuan, Meng
Zheng, Yalin
He, Mingguang
Shi, Danli
author_facet Xu, Pusheng
Gong, Xia
Chen, Xiaolan
Zhang, Weiyi
Yang, Jiancheng
Yan, Bingjie
Yuan, Meng
Zheng, Yalin
He, Mingguang
Shi, Danli
contents Purpose: To develop a bilingual multimodal visual question answering (VQA) benchmark for evaluating VLMs in ophthalmology. Methods: Ophthalmic image posts and associated captions published between January 1, 2016, and December 31, 2024, were collected from WeChat Official Accounts. Based on these captions, bilingual question-answer (QA) pairs in Chinese and English were generated using GPT-4o-mini. QA pairs were categorized into six subsets by question type and language: binary (Binary_CN, Binary_EN), single-choice (Single-choice_CN, Single-choice_EN), and open-ended (Open-ended_CN, Open-ended_EN). The benchmark was used to evaluate the performance of three VLMs: GPT-4o, Gemini 2.0 Flash, and Qwen2.5-VL-72B-Instruct. Results: The final OphthalWeChat dataset included 3,469 images and 30,120 QA pairs across 9 ophthalmic subspecialties, 548 conditions, 29 imaging modalities, and 68 modality combinations. Gemini 2.0 Flash achieved the highest overall accuracy (0.548), outperforming GPT-4o (0.522, P < 0.001) and Qwen2.5-VL-72B-Instruct (0.514, P < 0.001). It also led in both Chinese (0.546) and English subsets (0.550). Subset-specific performance showed Gemini 2.0 Flash excelled in Binary_CN (0.687), Single-choice_CN (0.666), and Single-choice_EN (0.646), while GPT-4o ranked highest in Binary_EN (0.717), Open-ended_CN (BLEU-1: 0.301; BERTScore: 0.382), and Open-ended_EN (BLEU-1: 0.183; BERTScore: 0.240). Conclusions: This study presents the first bilingual VQA benchmark for ophthalmology, distinguished by its real-world context and inclusion of multiple examinations per patient. The dataset reflects authentic clinical decision-making scenarios and enables quantitative evaluation of VLMs, supporting the development of accurate, specialized, and trustworthy AI systems for eye care.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19624
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking Large Multimodal Models for Ophthalmic Visual Question Answering with OphthalWeChat
Xu, Pusheng
Gong, Xia
Chen, Xiaolan
Zhang, Weiyi
Yang, Jiancheng
Yan, Bingjie
Yuan, Meng
Zheng, Yalin
He, Mingguang
Shi, Danli
Computer Vision and Pattern Recognition
Artificial Intelligence
Purpose: To develop a bilingual multimodal visual question answering (VQA) benchmark for evaluating VLMs in ophthalmology. Methods: Ophthalmic image posts and associated captions published between January 1, 2016, and December 31, 2024, were collected from WeChat Official Accounts. Based on these captions, bilingual question-answer (QA) pairs in Chinese and English were generated using GPT-4o-mini. QA pairs were categorized into six subsets by question type and language: binary (Binary_CN, Binary_EN), single-choice (Single-choice_CN, Single-choice_EN), and open-ended (Open-ended_CN, Open-ended_EN). The benchmark was used to evaluate the performance of three VLMs: GPT-4o, Gemini 2.0 Flash, and Qwen2.5-VL-72B-Instruct. Results: The final OphthalWeChat dataset included 3,469 images and 30,120 QA pairs across 9 ophthalmic subspecialties, 548 conditions, 29 imaging modalities, and 68 modality combinations. Gemini 2.0 Flash achieved the highest overall accuracy (0.548), outperforming GPT-4o (0.522, P < 0.001) and Qwen2.5-VL-72B-Instruct (0.514, P < 0.001). It also led in both Chinese (0.546) and English subsets (0.550). Subset-specific performance showed Gemini 2.0 Flash excelled in Binary_CN (0.687), Single-choice_CN (0.666), and Single-choice_EN (0.646), while GPT-4o ranked highest in Binary_EN (0.717), Open-ended_CN (BLEU-1: 0.301; BERTScore: 0.382), and Open-ended_EN (BLEU-1: 0.183; BERTScore: 0.240). Conclusions: This study presents the first bilingual VQA benchmark for ophthalmology, distinguished by its real-world context and inclusion of multiple examinations per patient. The dataset reflects authentic clinical decision-making scenarios and enables quantitative evaluation of VLMs, supporting the development of accurate, specialized, and trustworthy AI systems for eye care.
title Benchmarking Large Multimodal Models for Ophthalmic Visual Question Answering with OphthalWeChat
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.19624