交互式医学图像分割：基准数据集与基线

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

November 19, 2024

作者: Junlong Cheng, Bin Fu, Jin Ye, Guoan Wang, Tianbin Li, Haoyu Wang, Ruoyu Li, He Yao, Junren Chen, JingWen Li, Yanzhou Su, Min Zhu, Junjun He

cs.AI

摘要

交互式医学图像分割（IMIS）长期以来受制于大规模、多样化和密集标注数据集的有限可用性，这限制了模型的泛化能力以及在不同模型间的一致评估。在本文中，我们介绍了IMed-361M基准数据集，这是对一般IMIS研究的重大进展。首先，我们从多个数据源收集并标准化了超过640万张医学图像及其对应的地面实况掩模。然后，利用视觉基础模型强大的物体识别能力，我们自动生成了每个图像的密集交互式掩模，并通过严格的质量控制和细粒度管理确保了它们的质量。IMed-361M不同于以往受特定模态或稀疏标注限制的数据集，它涵盖了14种模态和204个分割目标，共计3.61亿个掩模，平均每张图像有56个掩模。最后，我们在该数据集上开发了一个IMIS基准网络，支持通过交互输入（包括点击、边界框、文本提示及其组合）生成高质量掩模。我们从多个角度评估了它在医学图像分割任务中的性能，展示了与现有交互式分割模型相比的卓越准确性和可扩展性。为促进医学计算机视觉基础模型的研究，我们在https://github.com/uni-medical/IMIS-Bench上发布了IMed-361M数据集和模型。

English

Interactive Medical Image Segmentation (IMIS) has long been constrained by the limited availability of large-scale, diverse, and densely annotated datasets, which hinders model generalization and consistent evaluation across different models. In this paper, we introduce the IMed-361M benchmark dataset, a significant advancement in general IMIS research. First, we collect and standardize over 6.4 million medical images and their corresponding ground truth masks from multiple data sources. Then, leveraging the strong object recognition capabilities of a vision foundational model, we automatically generated dense interactive masks for each image and ensured their quality through rigorous quality control and granularity management. Unlike previous datasets, which are limited by specific modalities or sparse annotations, IMed-361M spans 14 modalities and 204 segmentation targets, totaling 361 million masks-an average of 56 masks per image. Finally, we developed an IMIS baseline network on this dataset that supports high-quality mask generation through interactive inputs, including clicks, bounding boxes, text prompts, and their combinations. We evaluate its performance on medical image segmentation tasks from multiple perspectives, demonstrating superior accuracy and scalability compared to existing interactive segmentation models. To facilitate research on foundational models in medical computer vision, we release the IMed-361M and model at https://github.com/uni-medical/IMIS-Bench.