文献速递血管炎

探索人类专家对巨细胞动脉炎和健康受试者血管超声图像分类的图像分辨率极限:GCA-US-AI项目

Exploring the limit of image resolution for human expert classification of vascular ultrasound images in giant cell arteritis and healthy subjects: the GCA-US-AI project.
PubMed 文献 · Ann Rheum Dis · 2025-06-13

31名国际巨细胞动脉炎超声专家通过网页练习,对5个血管节段的10张超声图像在不同分辨率(32×32至512×512像素)下分类为GCA、正常或无法分类。分类性能随分辨率提高而改善,在224×224像素达到平台,此时总体敏感度为0.767(95%CI 0.737-0.796),特异度为0.862(95%CI 0.831-0.888)。结论认为224×224像素可确保人类专家可靠分类,并与许多常见AI架构输入要求一致。

要点

  • 31名国际专家对5个血管节段超声图像进行GCA、正常或无法分类的判断。
  • 分类性能随分辨率提高而改善,在224×224像素达到平台。
  • 224×224像素时总体敏感度0.767(95%CI 0.737-0.796),特异度0.862(95%CI 0.831-0.888)。

核心结论

  • 224×224像素的分辨率可确保人类专家可靠分类,并与许多常见AI架构的输入要求一致,从而为计划中的AI开发提供重要指导。

研究设计与样本

  • 31名国际巨细胞动脉炎超声专家参与基于网页的练习,对5个血管节段(颞浅总动脉、其额支和顶支(均横切面)、腋动脉横切面和腋动脉纵切面)各10张超声图像进行分类,相同图像以32×32、64×64、128×128、224×224和512×512像素不同分辨率展示,每位参与者共分类250张图像。

主要发现

  • 分类性能随分辨率提高而改善,直至达到阈值,在224×224像素处趋于平台。
  • 在224×224像素时,总体分类敏感度为0.767(95%CI 0.737-0.796),特异度为0.862(95%CI 0.831-0.888)。

关键数值与推荐

  • 在224×224像素时,总体分类敏感度为0.767(95%CI 0.737-0.796),特异度为0.862(95%CI 0.831-0.888)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: Prompt diagnosis of giant cell arteritis (GCA) with ultrasound is crucial for preventing severe ocular and other complications, yet expertise in ultrasound performance is scarce. The development of an artificial intelligence (AI)-based assistant that facilitates ultrasound image classification and helps to diagnose GCA early promises to close the existing gap. In the projection of the planned AI, this study investigates the minimum image resolution required for human experts to reliably classify ultrasound images of arteries commonly affected by GCA for the presence or absence of GCA. METHODS: Thirty-one international experts in GCA ultrasonography participated in a web-based exercise. They were asked to classify 10 ultrasound images for each of 5 vascular segments as GCA, normal, or not able to classify. The following segments were assessed: (1) superficial common temporal artery, (2) its frontal and (3) parietal branches (all in transverse view), (4) axillary artery in transverse view, and 5) axillary artery in longitudinal view. Identical images were shown at different resolutions, namely 32 × 32, 64 × 64, 128 × 128, 224 × 224, and 512 × 512 pixels, thereby resulting in a total of 250 images to be classified by every study participant. RESULTS: Classification performance improved with increasing resolution up to a threshold, plateauing at 224 × 224 pixels. At 224 × 224 pixels, the overall classification sensitivity was 0.767 (95% CI, 0.737-0.796), and specificity was 0.862 (95% CI, 0.831-0.888). CONCLUSIONS: A resolution of 224 × 224 pixels ensures reliable human expert classification and aligns with the input requirements of many common AI-based architectures. Thus, the results of this study substantially guide projected AI development.

来源:Ann Rheum Dis,查看原文。版权归原作者所有。

引用

  1. Bauer CJ, Chrysidis S, Dejaco C, et al. Exploring the limit of image resolution for human expert classification of vascular ultrasound images in giant cell arteritis and healthy subjects: the GCA-US-AI project. Ann Rheum Dis. 2025. PMID: 40514330. doi:10.1016/j.ard.2025.05.010

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。