人工智能在腹部、妇科、产科、肌骨、血管及介入超声中的应用
本文概述人工智能在腹部、肌骨、妇产及介入超声中的当前与新兴应用,指出超声因操作者依赖性和图像采集固有变异性,其人工智能整合面临不同于CT和MRI的独特挑战,人工智能有望减轻多种变异性、重新校准判读一致性并揭示人类难以检测的诊断模式,同时讨论了现有局限与潜在挑战。
要点
- 超声人工智能可减轻操作者依赖所致的多种变异性并重新校准判读一致性。
- 人工智能有助揭示人类难以检测的诊断模式。
- 超声人工智能整合面临操作者依赖和图像采集固有变异性带来的独特挑战。
核心结论
- 人工智能应用于超声有望减轻多种变异性、重新校准判读一致性并揭示人类难以检测的诊断模式,但整合面临操作者依赖和图像采集固有变异性带来的独特挑战。
研究设计与样本
- 本文为综述,范围涵盖腹部、肌骨、妇产及介入超声中当前与新兴的人工智能应用。
临床应用与阅片要点
- 作者指出,超声人工智能可减轻多种变异性、重新校准判读一致性并揭示人类难以检测的诊断模式。
局限性
- 原文指出超声人工智能整合面临操作者依赖性和图像采集过程固有变异性带来的独特挑战。
- 原文指出本文次要目的是讨论现有局限及此类技术实施可能遇到的潜在挑战。
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
Artificial Intelligence (AI) is a theoretical framework and systematic development of computational models designed to execute tasks that traditionally require human cognition. In medical imaging, AI is used for various modalities, such as computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, and pathologies across multiple organ systems. However, integrating AI into medical ultrasound presents unique challenges compared to modalities like CT and MRI due to its operator-dependent nature and inherent variability in the image acquisition process. AI application to ultrasound holds the potential to mitigate multiple variabilities, recalibrate interpretative consistency, and uncover diagnostic patterns that may be difficult for humans to detect. Progress has led to significant innovation in medical ultrasound-based AI applications, facilitating their adoption in various clinical settings and for multiple diseases. This manuscript primarily aims to provide a concise yet comprehensive exploration of current and emerging AI applications in medical ultrasound within abdominal, musculoskeletal, and obstetric & gynecological and interventional medical ultrasound. The secondary aim is to discuss present limitations and potential challenges such technological implementations may encounter.
引用
- Graumann O, Cui Xin W, Goudie A, et al. Artificial Intelligence in Abdominal, Gynecological, Obstetric, Musculoskeletal, Vascular and Interventional Ultrasound. Ultrasound Med Biol. 2025. PMID: 40754509. doi:10.1016/j.ultrasmedbio.2025.07.008
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。