Bahl Manisha, Chang Jung Min, Mullen Lisa A, Berg Wendie A
Department of Radiology, Massachusetts General Hospital, 55 Fruit St, WAC 240, Boston, MA 02114.
Department of Radiology, Seoul National University Hospital, Seoul, Korea.
AJR Am J Roentgenol. 2024 Dec;223(6):e2330645. doi: 10.2214/AJR.23.30645. Epub 2024 Feb 14.
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.
乳腺超声被广泛应用于各种临床场景，包括诊断和筛查应用。然而，超声的局限性包括其低特异性，以及对于自动乳腺超声筛查而言，审查全乳超声图像所需的时间。截至撰写本文时，有四种获得美国食品药品监督管理局（FDA）批准或认可的人工智能工具解决了这些局限性。目前的工具旨在为病变分类和/或检测提供决策支持，已被证明可提高非专科医生的特异性并减少解读时间。未来潜在的应用包括在资源匮乏地区对可触及肿块患者进行分诊、术前预测腋窝淋巴结转移以及术前预测新辅助化疗反应。超声人工智能开发和临床应用中的挑战包括与乳腺X线摄影相比，经过整理的训练数据集可用性有限、由于设备和操作员相关因素导致超声图像采集的高度变异性（这可能会限制算法的通用性）以及缺乏实施后评估研究。此外，当前用于病变分类的人工智能工具是基于二维数据开发的，但如果使用多模态超声数据，如彩色多普勒、弹性成像、动态图像和三维成像，诊断准确性可能会得到提高。
