Convolutional neural network for automated mass segmentation in mammography.
Convolutional neural network for automated mass segmentation in mammography.
复制标题
卷积神经网络用于乳腺摄影中的自动肿块分割。
DOI：
10.1186/s12859-020-3521-y
复制
发表时间：
2020-12-09
影响因子：
3
通讯作者：
Nabavi S
中科院分区：
文献类型：
--
作者：
Abdelhafiz D;Bi J;Ammar R;Yang C;Nabavi S
即使采用诸如深度学习（DL）方法之类的高级方法，乳房X线摄影（MG）图像中的病变的自动分割和定位也具有挑战性。我们开发了一个新的模型的基础上的语义分割U-Net模型的架构，以精确分割MG图像中的肿块病变。所提出的基于端到端卷积神经网络（CNN）的模型通过结合低级和高级特征来提取上下文信息。我们使用庞大的公共数据库（CBIS-DDSM，BCDR-01和INbreast）和康涅狄格大学健康中心（UCHC）的私人数据库训练了所提出的模型。我们将所提出的模型的性能与最先进的DL模型进行了比较，包括全卷积网络（FCN），SegNet，Dilated-Net，原始U-Net和Faster R-CNN模型以及传统的区域生长（RG）方法。所提出的Vanilla U-Net模型在运行时间和交集度量（IOU）方面明显优于Faster R-CNN模型。使用基于数字化胶片和完全数字化的MG图像进行训练，所提出的Vanilla U-Net模型的平均测试准确率为92.6%。所提出的模型实现了0.951的平均Dice系数指数（DI）和0.909的平均IOU，其示出了输出片段与地面实况图中的对应病变的接近程度。在我们的实验中，数据增强非常有效，导致平均DI和平均IOU分别从0.922增加到0.951和0.856增加到0.909。所提出的基于Vanilla U-Net的模型可用于MG图像中肿块的精确分割。这是因为分割过程结合了更多的多尺度空间背景，并捕获更多的局部和全局背景，以预测输入完整MG图像的精确的逐像素分割图。这些检测到的地图可以帮助放射科医生区分良性和恶性病变取决于病变的形状。我们表明，与其他DL和传统模型相比，使用迁移学习，引入增强和修改原始模型的架构在检测肿块病变的平均准确度，平均DI和平均IOU方面具有更好的性能。
Automatic segmentation and localization of lesions in mammogram (MG) images are challenging even with employing advanced methods such as deep learning (DL) methods. We developed a new model based on the architecture of the semantic segmentation U-Net model to precisely segment mass lesions in MG images. The proposed end-to-end convolutional neural network (CNN) based model extracts contextual information by combining low-level and high-level features. We trained the proposed model using huge publicly available databases, (CBIS-DDSM, BCDR-01, and INbreast), and a private database from the University of Connecticut Health Center (UCHC). We compared the performance of the proposed model with those of the state-of-the-art DL models including the fully convolutional network (FCN), SegNet, Dilated-Net, original U-Net, and Faster R-CNN models and the conventional region growing (RG) method. The proposed Vanilla U-Net model outperforms the Faster R-CNN model significantly in terms of the runtime and the Intersection over Union metric (IOU). Training with digitized film-based and fully digitized MG images, the proposed Vanilla U-Net model achieves a mean test accuracy of 92.6%. The proposed model achieves a mean Dice coefficient index (DI) of 0.951 and a mean IOU of 0.909 that show how close the output segments are to the corresponding lesions in the ground truth maps. Data augmentation has been very effective in our experiments resulting in an increase in the mean DI and the mean IOU from 0.922 to 0.951 and 0.856 to 0.909, respectively. The proposed Vanilla U-Net based model can be used for precise segmentation of masses in MG images. This is because the segmentation process incorporates more multi-scale spatial context, and captures more local and global context to predict a precise pixel-wise segmentation map of an input full MG image. These detected maps can help radiologists in differentiating benign and malignant lesions depend on the lesion shapes. We show that using transfer learning, introducing augmentation, and modifying the architecture of the original model results in better performance in terms of the mean accuracy, the mean DI, and the mean IOU in detecting mass lesion compared to the other DL and the conventional models.
登录
查看更多内容
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred
影响因子：
10.9
作者：
Dhungel, Neeraj;Carneiro, Gustavo;Bradley, Andrew P.
通讯作者：
Bradley, Andrew P.
DOI：
10.1016/j.ijmedinf.2018.06.003
发表时间：
2018-09-01
影响因子：
4.9
作者：
Al-antari, Mugahed A.;Al-masni, Mohammed A.;Kim, Tae-Seong
通讯作者：
Kim, Tae-Seong
影响因子：
6.1
作者：
Al-masni, Mohammed A.;Al-antari, Mugahed A.;Kim, Tae-Seong
通讯作者：
Kim, Tae-Seong
影响因子：
6.4
作者：
Ferlay, Jacques;Soerjomataram, Isabelle;Bray, Freddie
通讯作者：
Bray, Freddie