MRIS-Bench: A Large-Scale Medical Referring Image Segmentation Benchmark

MRIS-Bench is a large-scale benchmark dataset for the task of Medical Referring Image Segmentation (MRIS). The dataset is currently under double-blind review, with its full release pending the completion of that process. It was created by author lixiang007666 and is hosted on Hugging Face.

Use Cases

• Benchmarking model performance on medical referring image segmentation based on the described task.
• Training segmentation models that respond to textual descriptions based on the dataset's intended structure.
• Developing and evaluating multimodal AI that links medical language to visual regions based on the dataset's purpose.

Strengths

• Designed as a large-scale benchmark, suggesting substantial size for evaluation.
• Created specifically for the defined task of Medical Referring Image Segmentation (MRIS).

Limitations

• The full dataset, code, and detailed metadata are not yet publicly available, pending review.
• Column-level documentation and sample data are absent, making detailed assessment impossible.
• Row count, file formats, and license information are unknown.

Provenance

Source

huggingface

Freshness

Last updated 2026-05-15 03:22:31; freshness should be verified upon release.