From the Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada (O.A., G.E.M., M.J.Y.); and Department of Public Health Sciences (J.T.P.) and Department of Radiology and Medical Imaging (J.A.H.), University of Virginia, Box 800170, Charlottesville, VA 22908.
Radiology. 2015 May;275(2):366-76. doi: 10.1148/radiol.15141686. Epub 2015 Feb 25.
To estimate the reliability of a reference standard two-dimensional area-based method and three automated volumetric breast density measurements by using repeated measures.
Thirty women undergoing screening mammography consented to undergo a repeated left craniocaudal examination performed by a second technologist in this prospective institutional review board-approved HIPAA-compliant study. Breast density was measured by using an area-based method (Cumulus ABD) and three automated volumetric methods (CumulusV [University of Toronto], Volpara [version 1.4.5; Volpara Solutions, Wellington, New Zealand), and Quantra [version 2.0; Hologic, Danbury, Conn]). Discrepancy between the first and second breast density measurements (Δ1-2) was obtained for each algorithm by subtracting the second measurement from the first. The Δ1-2 values of each algorithm were then analyzed with a random-effects model to derive Bland-Altman-type limits of measurement agreement.
Variability was higher for Cumulus ABD and CumulusV than for Volpara or Quantra. The within-breast density measurement standard deviations were 3.32% (95% confidence interval [CI]: 2.65, 4.44), 3.59% (95% CI: 2.86, 4.48), 0.99% (95% CI: 0.79, 1.33), and 1.64% (95% CI: 1.31, 1.39) for Cumulus ABD, CumulusV, Volpara, and Quantra, respectively. Although the mean discrepancy between repeat breast density measurements was not significantly different from zero for any of the algorithms, larger absolute breast density discrepancy (Δ1-2) values were associated with larger breast density values for Cumulus ABD and CumulusV but not for Volpara and Quantra.
Variability in a repeated measurement of breast density is lowest for Volpara and Quantra; these algorithms may be more suited to incorporation into a risk model.
使用重复测量来评估二维基于面积的参考标准方法和三种自动容积乳腺密度测量的可靠性。
在这项前瞻性机构审查委员会批准的 HIPAA 合规研究中，30 名接受筛查性乳房 X 线摄影的女性同意接受第二位技术员进行的重复左侧头尾位检查。使用基于面积的方法（Cumulus ABD）和三种自动容积方法（CumulusV [多伦多大学]、Volpara [版本 1.4.5；Volpara Solutions，惠灵顿，新西兰]和 Quantra [版本 2.0；Hologic，丹伯里，康涅狄格州]）来测量乳腺密度。通过从第一次测量中减去第二次测量来获得每个算法的第一次和第二次乳腺密度测量之间的差异（Δ1-2）。然后，使用随机效应模型分析每个算法的 Δ1-2 值，以得出 Bland-Altman 类型的测量一致性界限。
Cumulus ABD 和 CumulusV 的变异性高于 Volpara 或 Quantra。乳腺内密度测量标准偏差分别为 3.32%（95%置信区间[CI]：2.65，4.44）、3.59%（95% CI：2.86，4.48）、0.99%（95% CI：0.79，1.33）和 1.64%（95% CI：1.31，1.39），分别为 Cumulus ABD、CumulusV、Volpara 和 Quantra。尽管对于任何算法，重复乳腺密度测量的平均差异均不显著不为零，但对于 Cumulus ABD 和 CumulusV，较大的绝对乳腺密度差异（Δ1-2）值与较大的乳腺密度值相关，但对于 Volpara 和 Quantra 则不是。
在乳腺密度的重复测量中，Volpara 和 Quantra 的变异性最低；这些算法可能更适合纳入风险模型。
