基于人工智能的计算机辅助诊断异常评分在乳腺癌患者连续乳腺X线摄影中的趋势
回顾性纳入2015至2019年126例乳腺癌患者,对487张既往乳腺X线片应用AI-CAD计算异常评分,并按每6个月间隔逆序分组。癌症侧乳腺异常评分随检查时间显著上升(斜率0.6/6个月,P<0.001),对侧正常乳腺无趋势(斜率0.03,P=0.776),两者斜率差异显著(P<0.001)。作者认为AI-CAD可能有助于乳腺癌早期检测。
要点
- 癌症侧乳腺AI-CAD异常评分在诊断前连续检查中呈显著上升趋势(斜率0.6/6个月,P<0.001)。
- 对侧正常乳腺异常评分无显著时间趋势(斜率0.03,P=0.776),癌症侧与对侧斜率差异显著(P<0.001)。
- 乳腺X线可见癌斜率0.8(P<0.001),隐匿癌斜率0.1(P=0.6);浸润癌斜率1.4(P=0.002),导管原位癌无显著趋势。
核心结论
- 癌症侧乳腺在既往连续乳腺X线摄影中AI-CAD异常评分升高,提示AI-CAD可能有助于乳腺癌早期检测。
研究设计与样本
- 回顾性研究,纳入2015至2019年126例乳腺癌患者,收集2008年至癌症诊断前的至少两次既往乳腺X线摄影共487张,回顾性应用AI-CAD获取异常评分,以每侧受癌乳腺的对侧乳腺为对照组,按距癌症诊断每6个月间隔逆序分组,采用随机系数模型估计趋势。
关键影像表现/征象
- 癌症侧乳腺异常评分在既往检查期间呈显著上升趋势(斜率0.6/6个月,斜率P<0.001),对侧正常乳腺无趋势(斜率0.03,P=0.776)。
- 癌症侧与对侧乳腺的斜率差异显著(P<0.001)。
- 乳腺X线可见癌的癌症侧异常评分呈显著上升趋势(斜率0.8,P<0.001),乳腺X线隐匿癌趋势不显著(斜率0.1,P=0.6)。
- 浸润癌异常评分斜率呈显著上升趋势(斜率1.4,P=0.002),导管原位癌无显著趋势。
- 浸润癌各分子亚型间异常评分斜率无显著差异(P=0.418)。
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 explore the abnormality score trends of artificial intelligence-based computer-aided diagnosis (AI-CAD) in the serial mammography of patients until a final diagnosis of breast cancer.
METHOD: From 2015 to 2019, 126 breast cancer patients who had at least two previous mammograms obtained from 2008 up to cancer diagnosis were included. AI-CAD was retrospectively applied to 487 previous mammograms and all the abnormality scores calculated by AI-CAD were obtained. The contralateral breast of each affected breast was defined as the control group. We divided all mammograms by 6-month intervals from cancer diagnosis in reverse chronological order. The random coefficient model was used to estimate whether the chronological trend of AI-CAD abnormality scores differed between cancer and normal breasts. Subgroup analyses were performed according to mammographic visibility, invasiveness and molecular subtype of the invasive cancer.
RESULTS: Mean period from initial examination to cancer diagnosis was 6.0 years (range 1.7-10.7 years). The abnormality scores of breasts diagnosed with cancer showed a significantly increasing trend during the previous examination period (slope 0.6 per 6 months, p for the slope < 0.001), while the contralateral normal breast showed no trend (slope 0.03, p = 0.776). The difference in slope between the cancerous and contralateral breasts was significant (p < 0.001). For mammography-visible cancers, the abnormality scores in cancerous breasts showed a significant increasing trend (slope 0.8, p < 0.001), while for mammography-occult cancers, the trend was not significant (slope 0.1, p = 0.6). For invasive cancers, the slope of the abnormality scores showed a significant increasing trend (slope 1.4, p = 0.002), unlike ductal carcinoma in situ (DCIS) which showed no significant trend. There was no significant difference in the slope of abnormality scores among the subtypes of invasive cancers (p = 0.418).
CONCLUSION: Breasts diagnosed with cancer showed an increase in AI-CAD abnormality scores in previous serial mammograms, suggesting that AI-CAD could be useful for early detection of breast cancer.
引用
- Lee SE, Han K, Rho M, et al. Artificial intelligence-based computer-aided diagnosis abnormality score trends in the serial mammography of patients with breast cancer. Eur J Radiol. 2024. PMID: 39024665. doi:10.1016/j.ejrad.2024.111626
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。