文献速递乳腺技术与安全US

人工智能在乳腺超声中的应用:AJR专家小组叙述性综述

Artificial Intelligence for Breast Ultrasound: AJR Expert Panel Narrative Review.
PubMed 文献 · AJR Am J Roentgenol · 2024-02-14

乳腺超声用于诊断和筛查,但特异性低且自动乳腺超声阅片耗时。截至本文撰写时,美国FDA已批准或cleared四种AI工具用于决策支持,可提高非专科医生的特异性并缩短判读时间。未来可能用于资源有限地区可触及肿块的分类、腋窝淋巴结转移术前预测和新辅助化疗反应术前预测。

要点

  • FDA已批准或cleared四种AI工具用于乳腺超声决策支持,可提高非专科医生特异性并缩短判读时间。
  • AI工具基于2D数据开发,使用彩色多普勒、弹性成像、电影回放和3D等多模态数据可能提高诊断准确性。
  • 挑战包括训练数据集有限、图像采集变异性大(可能限制算法泛化性)及缺乏实施后评估研究。

核心结论

  • AI工具可为乳腺超声病变分类和/或检测提供决策支持,提高非专科医生特异性并缩短判读时间;未来可能用于资源有限地区可触及肿块分类、腋窝淋巴结转移术前预测和新辅助化疗反应术前预测。

研究设计与样本

  • 专家小组叙述性综述;截至本文撰写时,美国FDA已批准或cleared四种AI工具。

诊断标准与关键数值

  • 当前AI工具旨在为病变分类和/或检测提供决策支持,已显示可提高非专科医生的特异性并缩短判读时间。
  • 当前用于病变分类的AI工具基于2D数据开发。

临床应用与阅片要点

  • AI工具可用于乳腺超声病变分类和/或检测的决策支持,提高非专科医生特异性并缩短判读时间。
  • 使用彩色多普勒、弹性成像、电影回放和3D成像等多模态超声数据可能提高诊断准确性。
  • 资源有限地区可触及肿块患者的分类、腋窝淋巴结转移术前预测和新辅助化疗反应术前预测是潜在未来应用。

局限性

  • 与乳腺X线摄影相比,用于超声AI的 curated 训练数据集有限。
  • 由于设备和操作者相关因素,超声图像采集变异性大,可能限制算法泛化性。
  • 缺乏实施后评估研究。
  • 当前用于病变分类的AI工具基于2D数据开发。

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)。

英文原文(摘要)· 点击展开

Breast ultrasound is used in a wide variety of clinical scenarios, including both diagnostic and screening applications. Limitations of ultrasound, however, include its low specificity and, for automated breast ultrasound screening, the time necessary to review whole-breast ultrasound images. As of this writing, four AI tools that are approved or cleared by the FDA address these limitations. Current tools, which are intended to provide decision support for lesion classification and/or detection, have been shown to increase specificity among nonspecialists and to decrease interpretation times. Potential future applications include triage of patients with palpable masses in low-resource settings, preoperative prediction of axillary lymph node metastasis, and preoperative prediction of neoadjuvant chemotherapy response. Challenges in the development and clinical deployment of AI for ultrasound include the limited availability of curated training datasets compared with mammography, the high variability in ultrasound image acquisition due to equipment- and operator-related factors (which may limit algorithm generalizability), and the lack of postimplementation evaluation studies. Furthermore, current AI tools for lesion classification were developed based on 2D data, but diagnostic accuracy could potentially be improved if multimodal ultrasound data were used, such as color Doppler, elastography, cine clips, and 3D imaging.

来源:AJR Am J Roentgenol,查看原文。版权归原作者所有。

引用

  1. Bahl M, Chang JM, Mullen LA, et al. Artificial Intelligence for Breast Ultrasound: AJR Expert Panel Narrative Review. AJR Am J Roentgenol. 2024. PMID: 38353449. doi:10.2214/AJR.23.30645

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。