Volumetric breast density estimation from full-field digital mammograms
Volumetric breast density estimation from full-field digital mammograms
复制标题
DOI：
10.1109/tmi.2005.862741
复制
发表时间：
2006-03-01
影响因子：
10.6
通讯作者：
Karssemeijer, N
中科院分区：
文献类型：
--
作者：
van Engeland, S;Snoeren, PR;Karssemeijer, N
提出了一种根据全场数字乳房 X 线摄影 (FFDM) 获得的乳房 X 线照片估计致密乳腺组织体积的方法。映射到像素的致密组织的厚度是通过使用图像采集的物理模型来确定的。该模型基于这样的假设：乳房由两种类型的组织组成：脂肪和实质。这些组织的有效线性衰减系数源自经验数据，作为管电压 (kVp)、阳极材料、过滤和压缩乳房厚度的函数。通过采用这些，在执行乳房厚度补偿后，使用由乳房组织投影中的最大像素值确定的脂肪组织的参考值来计算给定像素处的组织成分。使用 GE Senographe 2000D 采集的 22 个 FFDM 病例进行了验证，将体积估计值与通过乳腺磁共振成像 (MRI) 数据半自动分割获得的体积进行比较。 MRI 和乳房 X 光检查体积之间的相关性在每个图像上为 0.94，在每个患者上为 0.97。使用 NIRI 数据中的致密组织体积作为金标准，体积估计的平均相对误差为 13.6%。
A method is presented for estimation of dense breast tissue volume from mammograms obtained with full-field digital mammography (FFDM). The thickness of dense tissue mapping to a pixel is determined by using a physical model of image acquisition. This model is based on the assumption that the breast is composed of two types of tissue, fat and parenchyma. Effective linear attenuation coefficients of these tissues are derived from empirical data as a function of tube voltage (kVp), anode material, filtration, and compressed breast thickness. By employing these, tissue composition at a given pixel is computed after performing breast thickness compensation, using a reference value for fatty tissue determined by the maximum pixel value in the breast tissue projection. Validation has been performed using 22 FFDM cases acquired with a GE Senographe 2000D by comparing the volume estimates with volumes obtained by semi-automatic segmentation of breast magnetic resonance imaging (MRI) data. The correlation between MRI and mammography volumes was 0.94 on a per image basis and 0.97 on a per patient basis. Using the dense tissue volumes from NIRI data as the gold standard, the average relative error of the volume estimates was 13.6%.