基于AI的乳腺CAD评分与密度、征象及肿瘤特征的相关性
该回顾性多中心研究纳入2021年美国四个州接受异常乳腺断层摄影后活检的3899例患者,其中735例确诊乳腺癌。用FDA批准的AI-CAD生成病例级评分(0-100),分析其与影像征象、乳腺密度、肿瘤特征的关系。结果显示评分在钙化、致密乳腺、高级别、大肿瘤及高龄患者中更高。
要点
- AI-CAD对钙化及钙化伴肿块评分最高,阅片时应优先关注此类征象。
- DCIS评分高于浸润性癌主要与伴随的钙化征象及肿瘤特征相关。
- 解读AI评分需结合乳腺密度与肿瘤特征,避免单一阈值判断。
核心结论
- AI-CAD评分因乳腺密度、影像表现和肿瘤特征而异。
- AI输出可能反映影像特征与相关肿瘤特征的综合信息,临床解读需结合具体背景。
研究设计与样本
- 回顾性多中心研究,纳入2021年美国四个州异常筛查乳腺断层摄影后接受活检的患者。
- 共3899例患者纳入分析,其中735例确诊为乳腺癌。
- 使用FDA批准的商用AI-CAD工具生成病例级评分,范围为0-100。
- 影像特征分为钙化、肿块、肿块伴钙化、结构扭曲/不对称、仅淋巴结转移五类。
- 乳腺密度分为致密型与非致密型两类,同时收集肿瘤大小、分级及病理类型。
关键影像表现/征象
- 钙化评分为91.6±15.2,肿块伴钙化评分为90.5±16.3,均显著高于单纯肿块评分79.1±23.6(p<0.01)。
- 乳腺癌患者平均评分为78.1±22.9,显著高于非恶性病例的31.8±25.9(p<0.001)。
诊断标准与关键数值
- 乳腺癌患者平均年龄为65.3±11.7岁,显著高于非恶性病例的58.9±11.1岁(p<0.001)。
- 单因素分析中导管原位癌的评分高于浸润性癌(p<0.05)。
- 多因素分析显示高评分与非致密乳腺、更高肿瘤分级、更大肿瘤尺寸、更高龄及钙化等影像特征相关。
- 多因素分析中病理亚型与评分的关联减弱。
临床应用与阅片要点
- AI-CAD评分在钙化和肿块伴钙化表现中最突出,阅片时可辅助提高对钙化病变的警惕性。
- 解读AI评分应结合乳腺密度信息,非致密乳腺中高评分可能更提示恶性。
- 评分与肿瘤分级和大小相关,高评分可作为进一步评估的参考信号。
局限性
- 回顾性研究设计存在选择性偏倚可能。
- 仅纳入接受活检的患者,无法评估筛查人群中AI-CAD的整体表现。
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
RATIONALE AND OBJECTIVES: To determine whether an FDA-approved artificial intelligence computer-aided detection and diagnosis (AI-CAD) system assigns varying case scores based on imaging features, tumor characteristics, and breast density.
MATERIALS AND METHODS: This retrospective multisite study included patients undergoing biopsy after abnormal screening tomosynthesis across four U.S. states in 2021. A commercially available AI-CAD tool generated case-level scores (range 0-100). Imaging features were classified as calcifications, mass, mass with calcifications, architectural distortion/asymmetry, or nodal-only metastasis. Breast density was dichotomized as dense or non-dense. Tumor size, grade and pathology were also collected. Associations were assessed using univariable and multivariable linear regression.
RESULTS: Breast cancer was diagnosed in 735/3899 patients. The mean age and case score for patients with breast cancer were 65.3±11.7 years and 78.1±22.9, respectively, both significantly higher than those of non-malignant cases (58.9±11.1 years and 31.8±25.9; p<0.001). Scores were highest for calcifications (91.6±15.2) and mass with calcifications (90.5±16.3), both significantly higher than mass alone (79.1±23.6; p<0.01). In univariable analysis, ductal carcinoma in-situ (DCIS) had higher scores than invasive cancers (p<0.05). However, in multivariable analysis, higher scores were associated with non-dense breasts, higher tumor grade, larger tumor size, older age, and specific imaging features, such as calcifications, whereas the association with pathologic subtype was attenuated.
CONCLUSION: Our findings suggest AI-CAD scores differ by breast density, imaging presentation, and tumor characteristics. AI outputs may reflect a combination of imaging features and associated tumor characteristics, highlighting the importance of context-informed interpretation of AI outputs in clinical practice.
引用
- Eugene, Parghi, Elabeid, et al. Artificial Intelligence-Based Computer-Aided Detection in Breast Cancer Diagnosis: Variation by Breast Density, Imaging Feature, and Tumor Characteristics. Acad Radiol. 2026. PMID: 42448486. doi:10.1016/j.acra.2026.06.020
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。