Bone Suppression of Chest Radiographs With Cascaded Convlutional Networks in Wavelet Domain
Bone Suppression of Chest Radiographs With Cascaded Convlutional Networks in Wavelet Domain
复制标题
小波域级联卷积网络胸部X光片骨抑制
DOI：
10.1109/access.2018.2890300
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.9
通讯作者：
Chen, Wufan
中科院分区：
文献类型：
--
作者：
Chen, Yingyin;Gou, Xiaofang;Chen, Wufan
胸部X光片（CXRs）的骨抑制对于放射科医师诊断肺部疾病和计算机辅助诊断具有潜在的有用性。本文提出了一种小波域级联卷积网络模型（Wavelet-CCN），用于单次常规CXR中的骨抑制。小波系数是稀疏的，适合作为卷积网络的输出。使用真实的两次曝光双能量减影（DES）CXR作为训练数据，训练卷积网络以从CXR的小波系数预测骨图像的小波系数。通过将多级小波分解和级联细化框架相结合，Wavelet-CCN模型可以以多尺度方法自动工作，并在精度和空间分辨率方面逐步细化预测。与传统的CamsNet模型在梯度域进行骨骼预测相比，Wavelet-CCN模型通过预测小波系数来重建骨骼图像，避免了梯度二维积分导致的背景强度不一致问题。从原始CXR中减去预测的骨骼图像以产生软组织图像。Wavelet-CCN模型及其具有不同小波基的变体在由504例真实的两次暴露DES CXR组成的数据集上进行评估（404例用于训练，100例用于测试）。实验结果表明，在所有的变体和不同的小波基，Haar小波的Wavelet-CCN模型的性能最好。Wavelet-CCN模型生成的软组织图像的平均峰值信噪比和结构相似性指数均高于之前的CamsNet模型在梯度域中的平均峰值信噪比和结构相似性指数，分别达到39.4（+/-0.94）dB和0.977（+/-0.004）。结果还表明，小波-CCN模型可以处理由四种类型的X射线机获得的CXR。
Bone suppression of chest radiographs (CXRs) is potentially useful for diagnosing lung diseases for radiologists and computer-aided diagnosis. This paper presents a cascaded convolutional network model in wavelet domain (Wavelet-CCN) for bone suppression in single conventional CXR. Wavelet coefficients are sparse and suitable as the output of convolutional network. The convolutional networks are trained to predict the wavelet coefficients of bone images from the wavelet coefficients of CXRs, using real two-exposure dual energy subtraction (DES) CXRs as training data. By combining the multi-level wavelet decomposition and a cascaded refinement framework, the Wavelet-CCN model can work automatically with a multi-scale approach and progressively refine the prediction in terms of accuracy and spatial resolution. Compared with previous work of CamsNet model which preforms bone prediction in gradient domain, the Wavelet-CCN model predicts the wavelet coefficients to reconstruct bone images and can avoid the inconsistent background intensity caused by 2D integration of gradients. The predicted bone image is subtracted from the original CXR to produce a soft-tissue image. The Wavelet-CCN model and its variants with different wavelet basis are evaluated on a dataset that consists of 504 cases of real two-exposure DES CXRs (404 cases for training and 100 cases for test). Experimental results show that among all the variants and different wavelet bases, the Wavelet-CCN model with Haar wavelet performs best. The average peak signal-to-noise ratio and structural similarity index of the soft-tissue images produced by the proposed Wavelet-CCN model are both higher than those of the previous CamsNet model in gradient domain, reaching values of 39.4 (+/- 0.94) dB and 0.977 (+/- 0.004), respectively. The results also demonstrate that the Wavelet-CCN model can process the CXRs acquired by four types of X-ray machines.