UltraBench 2：迈向超声视觉基础模型的稳健评估
UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound
浏览论文内容
中文总结 AI 辅助
针对超声基础模型评估缺乏统一基准的问题，提出覆盖广泛解剖和任务的 UltraBench 2，比较现有视觉基础模型，发现超声预训练在分类领先，通用模型在分割上持平。
中文摘要 AI 辅助
基准测试在机器学习及其应用领域（包括医疗保健）的研究中日益关键。然而，尽管近年来新型超声基础模型不断涌现，用于评估它们的精心设计的基准测试的发展却滞后了。这一不足导致了对竞争模型的评估分散且不一致，使得衡量进展变得困难。为解决此问题，我们推出了 UltraBench 2，这是一个全面的基准测试，覆盖广泛的解剖部位和任务，并注重标准化、可复现性和易用性。利用该基准，我们比较了现有的用于超声图像分析的视觉基础模型。我们的分析表明，超声特异性预训练在分类任务上仍处于领先地位，但最先进的多用途模型在分割任务上已与之持平。
英文摘要
Benchmarking is an increasingly critical part of research in machine learning and the domains where it is applied, including healthcare. Yet, despite the steady development of new ultrasound foundation models in recent years, the development of well-designed benchmarks to evaluate them has lagged behind. This deficiency has led to fragmented and inconsistent evaluations of competing models, making it difficult to measure progress. To address this issue, we introduce UltraBench 2, a comprehensive benchmark with wide anatomical and task coverage, and a focus on standardization, reproducibility, and ease-of-use. Using this benchmark, we compare existing vision foundation models for ultrasound image analysis. Our analyses demonstrate that ultrasound-specific pretraining still leads on classification, but that state-of-the-art general-purpose models have drawn level on segmentation.
发表机构
- University of California, Los Angeles（加州大学洛杉矶分校）
- Université Laval（拉瓦尔大学）
- Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）
- UCLA David Geffen School of Medicine（加州大学洛杉矶分校大卫·格芬医学院）
机构由 AI 辅助整理，请以论文原文为准。
