Multi‐scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model‐based perceptual similarity
Multi‐scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model‐based perceptual similarity
复制标题
用于合成乳房X光照片的多尺度级联网络，以减少强度失真并增加基于模型的感知相似性
DOI：
10.1002/mp.16007
复制
发表时间：
2022
期刊：
影响因子：
3.8
通讯作者：
Lu, Yao
中科院分区：
文献类型：
--
作者：
Jiang, Gongfa;He, Zilong;Zhou, Yuanpin;Wei, Jun;Xu, Yuesheng;Zeng, Hui;Wu, Jiefang;Qin, Genggeng;Chen, Weiguo;Lu, Yao
合成数字乳腺X线摄影（SDM）是由数字乳腺断层合成摄影（DBT）生成的2D图像，可替代全视野数字乳腺X线摄影（FFDM），以降低乳腺癌筛查的辐射剂量。先前基于深度学习的方法使用FFDM图像作为基础事实，并训练单个神经网络以直接生成具有相似外观的SDM图像（例如，强度分布、纹理）到FFDM图像。但是，FFDM图像具有与DBT不同的纹理图案。纹理模式的差异可能使神经网络的训练不稳定并导致高强度失真，这使得难以减少强度失真并增加感知相似性（例如，相似的纹理）。在临床上，放射科医生希望具有在视觉上感觉像FFDM图像的2D合成图像，并且在DBT中保留诸如肿块和微钙化（MC）的局部结构，因为放射科医生已经在阅读FFDM图像方面接受了很长时间的培训，而局部结构对于诊断很重要。在这项研究中，我们提出使用深度卷积神经网络来学习从DBT生成SDM的变换。方法为了减少强度失真并增加感知相似性，提出了多尺度级联网络（MSCN）来生成低频结构（例如，强度分布）和高频结构（例如，textures）分开。MSCN由两个级联的子网络组成：第一个子网络用于预测FFDM图像的低频部分;第二个子网络用于基于第一个子网络的预测生成具有与FFDM图像相似的纹理的完整SDM图像。均方误差（MSE）目标函数用于训练第一个子网络（称为低频网络），以生成低频SDM图像。梯度引导生成对抗网络的目标函数是训练第二个子网络，称为高频网络，以生成具有与FFDM图像相似的纹理的完整SDM图像。结果从Hologic Selenia系统中回顾性收集了1646例FFDM和DBT病例作为训练和验证数据集，从Hologic Selenia系统中独立收集145例肿块或MC簇的病例作为检验数据集。为了进行比较，基线网络与高频网络具有相同的架构，并直接生成完整的SDM图像。与基线方法相比，所提出的MSCN将峰噪比从25.3提高到27.9 dB，将结构相似性从0.703提高到0.724，并显着增加了感知similarity.ConclusionsThe所提出的方法可以稳定训练并生成具有较低强度失真和较高感知相似性的SDM图像。
PurposeSynthetic digital mammogram (SDM) is a 2D image generated from digital breast tomosynthesis (DBT) and used as a substitute for a full‐field digital mammogram (FFDM) to reduce the radiation dose for breast cancer screening. The previous deep learning‐based method used FFDM images as the ground truth, and trained a single neural network to directly generate SDM images with similar appearances (e.g., intensity distribution, textures) to the FFDM images. However, the FFDM image has a different texture pattern from DBT. The difference in texture pattern might make the training of the neural network unstable and result in high‐intensity distortion, which makes it hard to decrease intensity distortion and increase perceptual similarity (e.g., generate similar textures) at the same time. Clinically, radiologists want to have a 2D synthesized image that feels like an FFDM image in vision and preserves local structures such as both mass and microcalcifications (MCs) in DBT because radiologists have been trained on reading FFDM images for a long time, while local structures are important for diagnosis. In this study, we proposed to use a deep convolutional neural network to learn the transformation to generate SDM from DBT.MethodTo decrease intensity distortion and increase perceptual similarity, a multi‐scale cascaded network (MSCN) is proposed to generate low‐frequency structures (e.g., intensity distribution) and high‐frequency structures (e.g., textures) separately. The MSCN consist of two cascaded sub‐networks: the first sub‐network is used to predict the low‐frequency part of the FFDM image; the second sub‐network is used to generate a full SDM image with textures similar to the FFDM image based on the prediction of the first sub‐network. The mean‐squared error (MSE) objective function is used to train the first sub‐network, termed low‐frequency network, to generate a low‐frequency SDM image. The gradient‐guided generative adversarial network's objective function is to train the second sub‐network, termed high‐frequency network, to generate a full SDM image with textures similar to the FFDM image.Results1646 cases with FFDM and DBT were retrospectively collected from the Hologic Selenia system for training and validation dataset, and 145 cases with masses or MC clusters were independently collected from the Hologic Selenia system for testing dataset. For comparison, the baseline network has the same architecture as the high‐frequency network and directly generates a full SDM image. Compared to the baseline method, the proposed MSCN improves the peak‐to‐noise ratio from 25.3 to 27.9 dB and improves the structural similarity from 0.703 to 0.724, and significantly increases the perceptual similarity.ConclusionsThe proposed method can stabilize the training and generate SDM images with lower intensity distortion and higher perceptual similarity.