首页|用于低剂量CT图像去噪的多级双树复小波网络

用于低剂量CT图像去噪的多级双树复小波网络

扫码查看
原文链接
  • 万方数据
  • 维普
基于卷积神经网络(CNN)的图像去噪方法能有效去除低剂量计算机断层扫描(CT)图像伴随的伪影和噪声,从而确保CT设备输出高质量图像同时降低辐射,这对患者健康和医学诊断具有重要意义.为了进一步提高低剂量CT图像的质量,提出一种小波域去噪网络MDTNet.首先,基于双树复小波变换(DTCWT)构造多级编解码去噪网络,在多个尺度上提取特征以保留更多高频细节;然后,利用扩展的像素重排技术替代卷积上下采样,实现多级输入和特征融合,从而降低计算复杂度;最后,通过大量训练找到最佳的去噪模型,即二级MDTNet配合LeGall滤波器和Qshift_b滤波器,并选择较大尺寸的CT图像作为训练数据.使用AAPM数据集评估MDTNet的性能,实验结果表明,MDTNet能有效去除条纹状伪影和噪声,在定量和定性评估中性能均优于同类型去噪方法.与FWDNet相比,对于1 mm的切片,MDTNet的平均峰值信噪比(PSNR)和结构相似性指数(SSIM)分别提高了 0.088 7 dB和0.002 4;对于3 mm的切片,分别提升了 0.144 3 dB和0.003.对于单张512×512像素的低剂量CT图像去噪,MDTNet在GPU上仅需0.193 s.MDTNet在保持高效率的同时保留了更多的高频细节,能够为低剂量CT图像去噪提供一种新的框架.
Multi-Level Dual-Tree Complex Wavelet Network for Low-Dose CT Image Denoising
Based on the Convolutional Neural Network(CNN),image denoising methods can effectively remove the artifacts and noise associated with low-dose Computed Tomography(CT),thereby ensuring high-quality output while minimizing radiation exposure.This information is of great significance for patient health and medical diagnosis.This study proposes a novel denoising network called MDTNet to enhance the quality of low-dose CT images.In this approach,multilevel encoder-decoder denoising networks are constructed using a Dual-Tree Complex Wavelet Transform(DTCWT),which enables the preservation of high-frequency details.Moreover,a pixel shuffle was employed to facilitate multi-level input and feature fusion,resulting in significantly reduced computation and memory complexity.In addition,by training a set of residual mappings in the wavelet domain,optimal denoising performance was achieved using a two-level MDTNet with LeGall and Qshift_b filters.The effectiveness of the MDTNet was evaluated on the 2016 NIH-AAPM-Mayo Clinic low-dose CT grand challenge dataset.The experimental results demonstrate that MDTNet outperforms state-of-the-art denoising methods in quantitative and qualitative evaluations.Specifically,compared with the FWDNet,on 1 mm slices,MDTNet improved the average Peak Signal-to-Noise Ratio(PSNR)and Structural Similarity Index Measure(SSIM)by 0.088 7 dB and 0.002 4,respectively;on a 3 mm slice,the increase was 0.144 3 dB and 0.003,respectively.Moreover,MDTNet processed 512X512 low-dose CT images on a Graphical Processing Unit(GPU)in 0.193 s.Preserving high-frequency details while maintaining efficiency,MDTNet presents an innovative framework for denoising low-dose CT images.

low-dose CT imageimage denoisingConvolutional Neural Network(CNN)Dual-Tree Complex Wavelet Transform(DTCWT)pixel shuffle

张鲁、田春伟、宋焕生、刘侍刚

展开 >

长安大学教育技术与网络中心,陕西西安 710064

西北工业大学软件学院,陕西西安 710072

西北工业大学深圳研究院,广东深圳 518057

长安大学信息工程学院,陕西西安 710064

陕西师范大学计算机科学学院,陕西西安 710119

展开 >

低剂量CT图像 图像去噪 卷积神经网络 双树复小波变换 像素重排

广东省基础与应用基础研究基金深圳市科技创新委员会项目中国博士后科学基金中国博士后科学基金

2021A1515110079JSGG202208311050020042022TQ02592022M722599

2024

10.19678/j.issn.1000-3428.0067563

计算机工程
华东计算技术研究所　上海市计算机学会

计算机工程

CSTPCD北大核心
影响因子：0.581
ISSN：1000-3428
年,卷(期)：2024.50(9)