超声造影、超分辨成像及人工智能在乳腺疾病中的应用进展

The Application Value of Contrast-Enhanced Ultrasound Combined with Super-Resolution and Artificial Intelligence in Breast Disease

摘要: 乳腺癌是全球女性第一大癌症，改善患者预后、降低死亡率的关键是早期诊断，在我国超声是乳腺疾病筛查和诊断的首选影像学手段，但传统超声在诊断特异性、微血管显示能力以及结果一致性方面仍存在一定局限，其准确性特别依赖操作医师的经验水平。超声造影(CEUS)可显著提升微血流显示能力，超分辨成像(SRUS)突破衍射极限能实现微血管可视化、定量化，人工智能(AI)可实现影像数据的定量化、自动化、智能化分析，三者融合应用，可实现“解剖结构 + 微血管形态 + 智能分析”的多维度信息整合，显著提升乳腺疾病诊断效能。本文系统综述CEUS、SRUS及AI在乳腺良恶性鉴别、早期诊断、疗效评估、预后预测中的临床应用进展。

Abstract: Breast cancer is a highly common malignant tumor in women worldwide, and early diagnosis is the key to improving patient prognosis and reducing mortality. Ultrasound is the preferred imaging method for breast disease screening and diagnosis, but traditional ultrasound still has limitations in diagnostic specificity, microvascular display ability, and consistency of results, and its accuracy is highly dependent on the experience of the operating physician. Ultrasound imaging can significantly improve blood flow display capabilities, super-resolution imaging can break through the diffraction limit to achieve microvascular visualization, and artificial intelligence can realize the automation, quantification and intelligent analysis of image data, significantly improving the accuracy and efficiency of diagnosis. The integration of the three realizes the multi-dimensional information integration of “anatomical structure + microvascular morphology + intelligent analysis”, significantly improving the diagnostic efficiency of breast diseases. This article systematically reviews the application value of CEUS, SRUS, and AI in the differentiation, early diagnosis, efficacy evaluation, and prognosis prediction of benign and malignant breasts.