Long-Term Performance of an Image-Based Short-Term Risk Model for Breast Cancer.
Long-Term Performance of an Image-Based Short-Term Risk Model for Breast Cancer.
复制标题
DOI：
10.1200/jco.22.01564
复制
发表时间：
2023-05-10
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
与传统的基于生活方式/家庭的风险模型相比，基于图像的人工智能乳腺癌短期风险模型显示出较高的区分性能。尚未研究图像衍生风险模型的长期性能。我们对2010年在瑞典开始的乳腺X线摄影筛查队列中随机选择的8，604名40-74岁女性进行了病例队列研究。在进入研究时收集乳房X线照片、年龄、生活方式和家族危险因素。在2022年5月，通过登记匹配共确定了2，028例乳腺癌事件（在子队列中发现了206例乳腺癌事件）。基于图像的模型从研究入组乳房X线照片中提取乳房X线照片特征（密度、微钙化、肿块和这些特征的左右乳房不对称性）和年龄。Tyrer-Cuzick v8风险模型结合了自我报告的生活方式和家族风险因素以及乳腺摄影密度来估计风险。估计绝对风险，并在10年期间比较年龄校正的AUC模型性能（aAUC）。基于图像的风险模型的aAUC范围为0.74（95% CI，0.70至0.78）至0.65（95% CI，0.63 - 0.66）研究入组后1-10年发生的乳腺癌;相应的Tyrer-Cuzick aAUC为0.62（95% CI，0.56 - 0.67）-0.60（95% CI，0.58 - 0.61）。对于症状性癌症，前3年内基于图像的模型的aAUC ≥0.75。乳腺摄影密度高和低的女性显示出相似的aAUC。在整个10年的随访中，20%的乳腺癌患者在研究开始时被基于图像的风险模型视为高风险，而使用基于生活方式的家庭模型为7.1%（P <0.01）。基于图像的风险模型在短期和长期风险评估方面优于Tyrer-Cuzick v8模型，可用于识别可能受益于补充筛查和风险降低策略的女性。
Image-derived artificial intelligence–based short-term risk models for breast cancer have shown high discriminatory performance compared with traditional lifestyle/familial-based risk models. The long-term performance of image-derived risk models has not been investigated. We performed a case-cohort study of 8,604 randomly selected women within a mammography screening cohort initiated in 2010 in Sweden for women age 40-74 years. Mammograms, age, lifestyle, and familial risk factors were collected at study entry. In all, 2,028 incident breast cancers were identified through register matching in May 2022 (206 incident breast cancers were found in the subcohort). The image-based model extracted mammographic features (density, microcalcifications, masses, and left-right breast asymmetries of these features) and age from study entry mammograms. The Tyrer-Cuzick v8 risk model incorporates self-reported lifestyle and familial risk factors and mammographic density to estimate risk. Absolute risks were estimated, and age-adjusted AUC model performances (aAUCs) were compared across the 10-year period. The aAUCs of the image-based risk model ranged from 0.74 (95% CI, 0.70 to 0.78) to 0.65 (95% CI, 0.63 to 0.66) for breast cancers developed 1-10 years after study entry; the corresponding Tyrer-Cuzick aAUCs were 0.62 (95% CI, 0.56 to 0.67) to 0.60 (95% CI, 0.58 to 0.61). For symptomatic cancers, the aAUCs for the image-based model were ≥0.75 during the first 3 years. Women with high and low mammographic density showed similar aAUCs. Throughout the 10-year follow-up, 20% of all women with breast cancers were deemed high-risk at study entry by the image-based risk model compared with 7.1% using the lifestyle familial-based model (P < .01). The image-based risk model outperformed the Tyrer-Cuzick v8 model for both short-term and long-term risk assessment and could be used to identify women who may benefit from supplemental screening and risk reduction strategies.