Model-based deep CNN-regularized reconstruction for digital breast tomosynthesis with a task-based CNN image assessment approach.
Model-based deep CNN-regularized reconstruction for digital breast tomosynthesis with a task-based CNN image assessment approach.
复制标题
基于模型的深度CNN正则化数字乳房断层合成重建与基于任务的CNN图像评估方法。
DOI：
10.1088/1361-6560/ad0eb4
复制
发表时间：
2023-12-13
影响因子：
3.5
通讯作者：
中科院分区：
文献类型：
--
作者：
Objective.数字乳腺断层合成摄影（DBT）是一种准三维乳腺成像模式，可改善乳腺癌筛查和诊断，因为与2D乳腺X射线摄影相比，它减少了纤维腺体组织重叠。然而，DBT存在噪音和模糊问题，这可能会降低微钙化（MC）等癌症细微体征的可检测性。我们的目标是提高图像质量的DBT的图像噪声和MC的显着性。Approach.我们提出了一种用于DBT的基于模型的深度卷积神经网络（deep CNN或DCNN）正则化重建（MDR）。它结合了基于模型的迭代重建（MBIR）方法，该方法对DBT系统的检测器模糊和相关噪声进行建模，并使用正则化去噪框架来学习基于DCNN的去噪器。为了便于基于任务的图像质量评估，我们还提出了两种用于图像评估的DCNN工具：一种噪声估计器（CNN-NE），用于估计图像的均方根（RMS）噪声，另一种MC分类器（CNN-MC）作为DCNN模型观察器，用于评估人类受试者DBT中聚类MC的可检测性。主要结果。我们证明了CNN-NE和CNN-MC对一组物理体模DBT的有效性。MDR方法实现了低RMS噪声和最高的检测面积下的受试者工作特征曲线（AUC）的排名评价CNN-NE和CNN-MC之间的重建方法研究的一个独立的测试集的人类受试者的DBT。意义CNN-NE和CNN-MC可以充当人类观察者的具有成本效益的替代物，以提供用于图像质量比较的任务特定度量。所提出的重建方法显示了将基于物理的MBIR和基于学习的DCNN相结合进行DBT图像重建的前景，这可能会导致乳腺癌筛查和诊断中MC检测的更低剂量和更高的灵敏度和特异性。
Objective. Digital breast tomosynthesis (DBT) is a quasi-three-dimensional breast imaging modality that improves breast cancer screening and diagnosis because it reduces fibroglandular tissue overlap compared with 2D mammography. However, DBT suffers from noise and blur problems that can lower the detectability of subtle signs of cancers such as microcalcifications (MCs). Our goal is to improve the image quality of DBT in terms of image noise and MC conspicuity. Approach. We proposed a model-based deep convolutional neural network (deep CNN or DCNN) regularized reconstruction (MDR) for DBT. It combined a model-based iterative reconstruction (MBIR) method that models the detector blur and correlated noise of the DBT system and the learning-based DCNN denoiser using the regularization-by-denoising framework. To facilitate the task-based image quality assessment, we also proposed two DCNN tools for image evaluation: a noise estimator (CNN-NE) trained to estimate the root-mean-square (RMS) noise of the images, and an MC classifier (CNN-MC) as a DCNN model observer to evaluate the detectability of clustered MCs in human subject DBTs. Main results. We demonstrated the efficacies of CNN-NE and CNN-MC on a set of physical phantom DBTs. The MDR method achieved low RMS noise and the highest detection area under the receiver operating characteristic curve (AUC) rankings evaluated by CNN-NE and CNN-MC among the reconstruction methods studied on an independent test set of human subject DBTs. Significance. The CNN-NE and CNN-MC may serve as a cost-effective surrogate for human observers to provide task-specific metrics for image quality comparisons. The proposed reconstruction method shows the promise of combining physics-based MBIR and learning-based DCNNs for DBT image reconstruction, which may potentially lead to lower dose and higher sensitivity and specificity for MC detection in breast cancer screening and diagnosis.
登录
查看更多内容
DOI：
10.3390/diagnostics12020495
发表时间：
2022-02-14
期刊：
Diagnostics (Basel, Switzerland)
影响因子：
--
作者：
Gomi T;Kijima Y;Kobayashi T;Koibuchi Y
通讯作者：
Koibuchi Y
影响因子：
6.3
作者：
Badal, Andreu;Sharma, Diksha;Badano, Aldo
通讯作者：
Badano, Aldo
影响因子：
19.7
作者：
Chan, Heang-Ping;Goodsitt, Mitchell M.;Wei, Jun
通讯作者：
Wei, Jun
DOI：
10.1073/pnas.90.21.9758
发表时间：
1993-11-01
影响因子：
11.1
作者：
BARRETT, HH;YAO, J;MYERS, KJ
通讯作者：
MYERS, KJ
影响因子：
14.9
作者：
Ahmad R;Bouman CA;Buzzard GT;Chan S;Liu S;Reehorst ET;Schniter P
通讯作者：
Schniter P