文献速递乳腺乳腺X线

深度学习模型在常规临床实践中预测乳腺X线摄影乳腺密度的作用

Impact of a Deep Learning Model for Predicting Mammographic Breast Density in Routine Clinical Practice.
PubMed 文献 · J Am Coll Radiol · 2022-05-23

该前瞻性研究纳入三个临床站点共85124例连续筛查乳腺X线摄影,评估深度学习模型对乳腺密度评估的影响;暴露于模型的A、B站点致密分类的调整比值比降低,未暴露的C站点升高,提示模型可减少致密分类。

要点

  • 深度学习模型可降低筛查乳腺X线摄影被归类为致密的 odds。
  • 模型在学术实践站点和社区实践站点均观察到致密分类 odds 降低。
  • 未暴露于模型的站点致密分类 odds 升高,提示密度评估存在时间趋势。

核心结论

  • 深度学习模型可降低筛查乳腺X线摄影被归类为致密的 odds。

研究设计与样本

  • 经机构审查委员会批准的前瞻性研究,纳入三个临床站点2017年和2019年两个时段的连续筛查乳腺X线摄影,共85124例;深度学习模型于2018年在站点A(学术实践)和站点B(社区实践)对所有筛查乳腺X线摄影实施,站点C(社区实践)从未暴露于模型。

诊断标准与关键数值

  • 站点A暴露于深度学习模型后,致密分类的调整比值比为0.93(95%CI 0.86-0.99;P=0.024)。
  • 站点B暴露于深度学习模型后,致密分类的调整比值比为0.81(95%CI 0.70-0.93;P=0.003)。
  • 站点C未暴露于深度学习模型,致密分类的调整比值比为1.13(95%CI 1.01-1.27;P=0.033)。

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

OBJECTIVE: Legislation in 38 states requires patient notification of dense mammographic breast tissue because increased density is a marker of breast cancer risk and can limit mammographic sensitivity. Because radiologist density assessments vary widely, our objective was to implement and measure the impact of a deep learning (DL) model on mammographic breast density assessments in clinical practice.

METHODS: This institutional review board-approved prospective study identified consecutive screening mammograms performed across three clinical sites over two periods: 2017 period (January 1, 2017, through September 30, 2017) and 2019 period (January 1, 2019, through September 30, 2019). The DL model was implemented at sites A (academic practice) and B (community practice) in 2018 for all screening mammograms. Site C (community practice) was never exposed to the DL model. Prospective densities were evaluated, and multivariable logistic regression models evaluated the odds of a dense mammogram classification as a function of time and site.

RESULTS: We identified 85,124 consecutive screening mammograms across the three sites. Across time intervals, odds of a dense classification decreased at sites exposed to the DL model, site A (adjusted odds ratio [aOR], 0.93; 95% confidence interval [CI], 0.86-0.99; P = .024) and site B (aOR, 0.81 [95% CI, 0.70-0.93]; P = .003), and odds increased at the site unexposed to the model (site C) (aOR, 1.13 [95% CI, 1.01-1.27]; P = .033).

DISCUSSION: A DL model reduces the odds of screening mammograms categorized as dense. Accurate density assessments could help health care systems more appropriately use limited supplemental screening resources and help better inform traditional clinical risk models.

来源:J Am Coll Radiol,查看原文。版权归原作者所有。

引用

  1. Dontchos, Cavallo-Hom, Lamb, et al. Impact of a Deep Learning Model for Predicting Mammographic Breast Density in Routine Clinical Practice. J Am Coll Radiol. 2022. PMID: 35618002. doi:10.1016/j.jacr.2022.04.001

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。