基于深度学习从三维重建数字乳腺断层合成图像中估计乳腺体积密度
Volumetric Breast Density Estimation From Three-Dimensional Reconstructed Digital Breast Tomosynthesis Images Using Deep Learning.
作者信息
Ahluwalia Vinayak S, Doiphode Nehal, Mankowski Walter C, Cohen Eric A, Pati Sarthak, Pantalone Lauren, Bakas Spyridon, Brooks Ari, Vachon Celine M, Conant Emily F, Gastounioti Aimilia, Kontos Despina
机构信息
Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA.
Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA.
出版信息
JCO Clin Cancer Inform. 2024 Dec;8:e2400103. doi: 10.1200/CCI.24.00103. Epub 2024 Dec 9.
PURPOSE
Breast density is a widely established independent breast cancer risk factor. With the increasing utilization of digital breast tomosynthesis (DBT) in breast cancer screening, there is an opportunity to estimate volumetric breast density (VBD) routinely. However, current available methods extrapolate VBD from two-dimensional (2D) images acquired using DBT and/or depend on the existence of raw DBT data, which is rarely archived by clinical centers because of storage constraints.
METHODS
We retrospectively analyzed 1,080 nonactionable three-dimensional (3D) reconstructed DBT screening examinations acquired between 2011 and 2016. Reference tissue segmentations were generated using previously validated software that uses 3D reconstructed slices and raw 2D DBT data. We developed a deep learning (DL) model that segments dense and fatty breast tissue from background. We then applied this model to estimate %VBD and absolute dense volume (ADV) in cm in a separate case-control sample (180 cases and 654 controls). We created two conditional logistic regression models, relating each model-derived density measurement to likelihood of contralateral breast cancer diagnosis, adjusted for age, BMI, family history, and menopausal status.
RESULTS
The DL model achieved unweighted and weighted Dice scores of 0.88 (standard deviation [SD] = 0.08) and 0.76 (SD = 0.15), respectively, on the held-out test set, demonstrating good agreement between the model and 3D reference segmentations. There was a significant association between the odds of breast cancer diagnosis and model-derived VBD (odds ratio [OR], 1.41 [95 % CI, 1.13 to 1.77]; = .002), with an AUC of 0.65 (95% CI, 0.60 to 0.69). ADV was also significantly associated with breast cancer diagnosis (OR, 1.45 [95% CI, 1.22 to 1.73]; < .001) with an AUC of 0.67 (95% CI, 0.62 to 0.71).
CONCLUSION
DL-derived density measures derived from 3D reconstructed DBT images are associated with breast cancer diagnosis.
目的
乳腺密度是一个已被广泛认可的独立乳腺癌风险因素。随着数字乳腺断层合成（DBT）在乳腺癌筛查中的应用日益增加，有机会常规估计乳腺体积密度（VBD）。然而，目前可用的方法是从使用DBT获取的二维（2D）图像推断VBD，和/或依赖于原始DBT数据的存在，由于存储限制，临床中心很少存档这些数据。
方法
我们回顾性分析了2011年至2016年间获取的1080例不可操作的三维（3D）重建DBT筛查检查。使用先前验证的软件生成参考组织分割，该软件使用3D重建切片和原始2D DBT数据。我们开发了一种深度学习（DL）模型，用于从背景中分割致密和脂肪乳腺组织。然后，我们将该模型应用于在一个单独的病例对照样本（180例病例和654例对照）中估计VBD百分比和以厘米为单位的绝对致密体积（ADV）。我们创建了两个条件逻辑回归模型，将每个模型得出的密度测量值与对侧乳腺癌诊断的可能性相关联，并根据年龄、体重指数、家族史和绝经状态进行调整。
结果
在保留测试集上，DL模型的无加权和加权Dice分数分别为0.88（标准差[SD]=0.08）和0.76（SD=0.15），表明模型与3D参考分割之间具有良好的一致性。乳腺癌诊断的几率与模型得出的VBD之间存在显著关联（优势比[OR]，1.41[95%CI，1.13至1.77]；P=.002），曲线下面积（AUC）为0.65（95%CI，0.60至0.69）。ADV也与乳腺癌诊断显著相关（OR，1.45[95%CI，1.22至1.73]；P<.001），AUC为0.67（95%CI，0.62至0.71）。
结论
从3D重建DBT图像得出的DL衍生密度测量值与乳腺癌诊断相关。
Zotero 插件