基于人工智能的乳腺X线摄影肿瘤大小测量:与病理学的一致性及与多模态影像人工阅片的比较
本回顾性研究纳入925名女性共936个乳腺癌,评估基于人工智能(AI)在乳腺X线摄影上测量肿瘤大小与最终病理的一致性,并与其他影像模态比较。AI异常评分50%时与病理一致性最高(ICC=0.54),与乳腺X线摄影相当;但52.0%(487/936)病例存在大小不一致。
要点
- AI异常评分50%时肿瘤大小与病理一致性最高(ICC=0.54),与乳腺X线摄影相当。
- 52.0%(487/936)病例AI测量与病理不一致,多见于年轻、致密乳腺、多灶性病变及较低异常评分者。
- 导管原位癌和HER2阳性癌中,AI一致性高于乳腺X线摄影。
核心结论
- AI异常评分50%的肿瘤大小测量与病理呈中等一致性,但与乳腺X线摄影相当,超过半数病例存在大小不一致,需进一步改进和研究。
研究设计与样本
- 回顾性研究,纳入925名女性(平均年龄55.3岁±11.6)共936个乳腺癌,术前均行数字乳腺X线摄影、乳腺超声和磁共振成像;AI测量在后处理乳腺X线图像上进行,勾画异常评分10%、50%和90%的区域;以组织病理学为参考标准,采用组内相关系数(ICC)分析一致性。
诊断标准与关键数值
- AI异常评分50%时与病理一致性最高(ICC=0.54,95%CI:0.49-0.59),与乳腺X线摄影相当(ICC=0.54,95%CI:0.48-0.60,p=0.40);导管原位癌中AI一致性ICC=0.76(95%CI:0.67-0.84),HER2阳性癌中ICC=0.73(95%CI:0.52-0.85),均高于乳腺X线摄影。
临床应用与阅片要点
- AI测量与病理一致性中等且超过半数病例大小不一致,阅片和报告时需注意AI测量值可能高估或低估肿瘤大小,尤其在年轻、致密乳腺、多灶性病变及低异常评分病例中。
局限性
- 原文结论指出AI测量存在局限性,强调需要进一步改进和研究。
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
PURPOSE: To evaluate the agreement between artificial intelligence (AI)-based tumor size measurements of breast cancer and the final pathology and compare these results with those of other imaging modalities.
MATERIAL AND METHODS: This retrospective study included 925 women (mean age, 55.3 years ± 11.6) with 936 breast cancers, who underwent digital mammography, breast ultrasound, and magnetic resonance imaging before breast cancer surgery. AI-based tumor size measurement was performed on post-processed mammographic images, outlining areas with AI abnormality scores of 10, 50, and 90%. Absolute agreement between AI-based tumor sizes, image modalities, and histopathology was assessed using intraclass correlation coefficient (ICC) analysis. Concordant and discordant cases between AI measurements and histopathologic examinations were compared.
RESULTS: Tumor size with an abnormality score of 50% showed the highest agreement with histopathologic examination (ICC = 0.54, 95% confidential interval [CI]: 0.49-0.59), showing comparable agreement with mammography (ICC = 0.54, 95% CI: 0.48-0.60, p = 0.40). For ductal carcinoma in situ and human epidermal growth factor receptor 2-positive cancers, AI revealed a higher agreement than that of mammography (ICC = 0.76, 95% CI: 0.67-0.84 and ICC = 0.73, 95% CI: 0.52-0.85). Overall, 52.0% (487/936) of cases were discordant, with these cases more commonly observed in younger patients with dense breasts, multifocal malignancies, lower abnormality scores, and different imaging characteristics.
CONCLUSION: AI-based tumor size measurements with abnormality scores of 50% showed moderate agreement with histopathology but demonstrated size discordance in more than half of the cases. While comparable to mammography, its limitations emphasize the need for further refinement and research.
引用
- Kwon MR, Kim SH, Park GE, et al. Artificial intelligence-based tumor size measurement on mammography: agreement with pathology and comparison with human readers' assessments across multiple imaging modalities. Radiol Med. 2025. PMID: 40540124. doi:10.1007/s11547-025-02033-8
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。