Artificial intelligence (AI) can automatically delineate lesions on computed tomography (CT) and generate radiology report content, yet progress is limited by the scarcity of publicly available CT datasets with lesion-level annotations. To bridge this gap, we introduce CT-Bench, a first-of-its-kind benchmark dataset comprising two components: a Lesion Image and Metadata Set containing 20,335 lesions from 7,795 CT studies with bounding boxes, descriptions, and size information, and a multitask visual question answering benchmark with 2,850 QA pairs covering lesion localization, description, size estimation, and attribute categorization. Hard negative examples are included to reflect real-world diagnostic challenges. We evaluate multiple state-of-the-art multimodal models, including vision-language and medical CLIP variants, by comparing their performance to radiologist assessments, demonstrating the value of CT-Bench as a comprehensive benchmark for lesion analysis. Moreover, fine-tuning models on the Lesion Image and Metadata Set yields significant performance gains across both components, underscoring the clinical utility of CT-Bench.
@article{arxiv.2602.14879,
title = {CT-Bench: A Benchmark for Multimodal Lesion Understanding in Computed Tomography},
author = {Qingqing Zhu and Qiao Jin and Tejas S. Mathai and Yin Fang and Zhizheng Wang and Yifan Yang and Maame Sarfo-Gyamfi and Benjamin Hou and Ran Gu and Praveen T. S. Balamuralikrishna and Kenneth C. Wang and Ronald M. Summers and Zhiyong Lu},
journal= {arXiv preprint arXiv:2602.14879},
year = {2026}
}