Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institute of Health, USA.
Kaiser Permanente Washington Health Research Institute, Seattle, WA, USA.
JNCI Cancer Spectr. 2021 Feb 6;5(3). doi: 10.1093/jncics/pkab015. eCollection 2021 Jun.
Benign breast disease (BBD) is a strong breast cancer risk factor, but identifying patients that might develop invasive breast cancer remains a challenge.
By applying machine-learning to digitized hematoxylin and eosin-stained biopsies and computer-assisted thresholding to mammograms obtained circa BBD diagnosis, we generated quantitative tissue composition metrics and determined their association with future invasive breast cancer diagnosis. Archival breast biopsies and mammograms were obtained for women (18-86 years of age) in a case-control study, nested within a cohort of 15 395 BBD patients from Kaiser Permanente Northwest (1970-2012), followed through mid-2015. Patients who developed incident invasive breast cancer (ie, cases; n = 514) and those who did not (ie, controls; n = 514) were matched on BBD diagnosis age and plan membership duration. All statistical tests were 2-sided.
Increasing epithelial area on the BBD biopsy was associated with increasing breast cancer risk (odds ratio [OR] = 1.85, 95% confidence interval [CI] = 1.13 to 3.04; = .02). Conversely, increasing stroma was associated with decreased risk in nonproliferative, but not proliferative, BBD ( = .002). Increasing epithelium-to-stroma proportion (OR = 2.06, 95% CI =1.28 to 3.33; = .002) and percent mammographic density (MBD) (OR = 2.20, 95% CI = 1.20 to 4.03; = .01) were independently and strongly predictive of increased breast cancer risk. In combination, women with high epithelium-to-stroma proportion and high MBD had substantially higher risk than those with low epithelium-to-stroma proportion and low MBD (OR = 2.27, 95% CI = 1.27 to 4.06; = .005), particularly among women with nonproliferative ( = .01) vs proliferative ( = .33) BBD.
Among BBD patients, increasing epithelium-to-stroma proportion on BBD biopsies and percent MBD at BBD diagnosis were independently and jointly associated with increasing breast cancer risk. These findings were particularly striking for women with nonproliferative disease (comprising approximately 70% of all BBD patients), for whom relevant predictive biomarkers are lacking.
良性乳腺疾病（BBD）是乳腺癌的一个强危险因素，但确定可能发展为浸润性乳腺癌的患者仍然具有挑战性。
通过将机器学习应用于数字化苏木精和伊红染色的活检以及在 BBD 诊断时获得的计算机辅助阈值化的乳房 X 光片，我们生成了定量组织成分指标，并确定了它们与未来浸润性乳腺癌诊断的关联。该研究对 Kaiser Permanente Northwest（1970-2012 年）队列中 15395 例 BBD 患者中的一部分（18-86 岁）进行了病例对照研究，通过对存档的乳房活检和乳房 X 光片进行分析，随访至 2015 年年中。患有浸润性乳腺癌（即病例；n=514）和未患有浸润性乳腺癌（即对照；n=514）的患者按 BBD 诊断年龄和计划成员资格期限进行匹配。所有统计检验均为双侧检验。
BBD 活检中上皮面积的增加与乳腺癌风险的增加相关（比值比[OR] = 1.85，95%置信区间[CI] = 1.13 至 3.04； =.02）。相反，在非增殖性 BBD 中，基质的增加与风险降低相关，但在增殖性 BBD 中则没有（ =.002）。上皮与基质比例（OR = 2.06，95%CI = 1.28 至 3.33； =.002）和乳腺密度百分比（MBD）（OR = 2.20，95%CI = 1.20 至 4.03； =.01）的增加与乳腺癌风险的增加独立且高度相关。综合来看，上皮与基质比例高且 MBD 高的女性患乳腺癌的风险显著高于上皮与基质比例低且 MBD 低的女性（OR = 2.27，95%CI = 1.27 至 4.06； =.005），尤其是在非增殖性 BBD 女性中（ =.01）与增殖性 BBD 女性（ =.33）相比。
在 BBD 患者中，BBD 活检中的上皮与基质比例增加以及 BBD 诊断时的 MBD 百分比与乳腺癌风险的增加独立且共同相关。对于非增殖性疾病（占所有 BBD 患者的约 70%）患者，这些发现尤为明显，而这些患者缺乏相关的预测性生物标志物。
