Radiology Center, Kindai University Hospital, 377-2, Ono-higashi, Osaka-sayama, Osaka 589-8511, Japan.
Graduate School of Health Sciences, Niigata University, 2-746, Asahimachidori, Chuouku, Niigata 951-8518, Japan.
Biomed Phys Eng Express. 2022 Jun 30;8(4). doi: 10.1088/2057-1976/ac7ada.
This study investigates the equivalence or compatibility between U-Net and visual segmentations of fibroglandular tissue regions by mammography experts for calculating the breast density and mean glandular dose (MGD). A total of 703 mediolateral oblique-view mammograms were used for segmentation. Two region types were set as the ground truth (determined visually): (1) one type included only the region where fibroglandular tissue was identifiable (called the 'dense region'); (2) the other type included the region where the fibroglandular tissue may have existed in the past, provided that apparent adipose-only parts, such as the retromammary space, are excluded (the 'diffuse region'). U-Net was trained to segment the fibroglandular tissue region with an adaptive moment estimation optimiser, five-fold cross-validated with 400 training and 100 validation mammograms, and tested with 203 mammograms. The breast density and MGD were calculated using the van Engeland and Dance formulas, respectively, and compared between U-Net and the ground truth with the Dice similarity coefficient and Bland-Altman analysis. Dice similarity coefficients between U-Net and the ground truth were 0.895 and 0.939 for the dense and diffuse regions, respectively. In the Bland-Altman analysis, no proportional or fixed errors were discovered in either the dense or diffuse region for breast density, whereas a slight proportional error was discovered in both regions for the MGD (the slopes of the regression lines were -0.0299 and -0.0443 for the dense and diffuse regions, respectively). Consequently, the U-Net and ground truth were deemed equivalent (interchangeable) for breast density and compatible (interchangeable following four simple arithmetic operations) for MGD. U-Net-based segmentation of the fibroglandular tissue region was satisfactory for both regions, providing reliable segmentation for breast density and MGD calculations. U-Net will be useful in developing a reliable individualised screening-mammography programme, instead of relying on the visual judgement of mammography experts.
本研究旨在探讨 U-Net 与乳腺摄影专家对纤维腺体组织区域的视觉分割在计算乳房密度和平均腺体剂量（MGD）方面的等效性或兼容性。共使用了 703 张侧位斜位 mammograms 进行分割。设置了两种区域类型作为地面实况（通过视觉确定）：（1）一种类型仅包含可识别纤维腺体组织的区域（称为“致密区域”）；（2）另一种类型包含过去可能存在纤维腺体组织的区域，但排除明显的脂肪-only 部分，如乳房后间隙（“弥散区域”）。U-Net 使用自适应矩估计优化器进行纤维腺体组织区域的分割，使用 400 张训练 mammograms 和 100 张验证 mammograms 进行五折交叉验证，并使用 203 张 mammograms 进行测试。使用 van Engeland 和 Dance 公式分别计算乳房密度和 MGD，并使用 Dice 相似系数和 Bland-Altman 分析比较 U-Net 与地面实况之间的差异。U-Net 与地面实况在致密区域和弥散区域的 Dice 相似系数分别为 0.895 和 0.939。在 Bland-Altman 分析中，致密区域和弥散区域的乳房密度均未发现比例或固定误差，而 MGD 则在两个区域均发现轻微的比例误差（回归线的斜率分别为致密区域和弥散区域的-0.0299 和-0.0443）。因此，U-Net 和地面实况在乳房密度方面是等效的（可互换的），在 MGD 方面是兼容的（经过四个简单的算术运算后可互换）。U-Net 对纤维腺体组织区域的分割在两个区域都令人满意，为乳房密度和 MGD 的计算提供了可靠的分割。U-Net 将有助于开发可靠的个体化筛查 mammography 计划，而无需依赖乳腺摄影专家的视觉判断。
