Zhang Yuanke, Hao Dejing, Lin Yingying, Sun Wanxin, Zhang Jinke, Meng Jing, Ma Fei, Guo Yanfei, Lu Hongbing, Li Guangshun, Liu Jianlei
School of Computer Science, Qufu Normal University, Rizhao, China.
School of Biomedical Engineering, Fourth Military Medical University, Xi'an, China.
Quant Imaging Med Surg. 2023 Oct 1;13(10):6528-6545. doi: 10.21037/qims-23-194. Epub 2023 Sep 14.
Low-dose computed tomography (LDCT) scans can effectively reduce the radiation damage to patients, but this is highly detrimental to CT image quality. Deep convolutional neural networks (CNNs) have shown their potential in improving LDCT image quality. However, the conventional CNN-based approaches rely fundamentally on the convolution operations, which are ineffective for modeling the correlations among nonlocal similar structures and the regionally distinct statistical properties in CT images. This modeling deficiency hampers the denoising performance for CT images derived in this manner.
In this paper, we propose an adaptive global context (AGC) modeling scheme to describe the nonlocal correlations and the regionally distinct statistics in CT images with negligible computation load. We further propose an AGC-based long-short residual encoder-decoder (AGC-LSRED) network for efficient LDCT image noise artifact-suppression tasks. Specifically, stacks of residual AGC attention blocks (RAGCBs) with long and short skip connections are constructed in the AGC-LSRED network, which allows valuable structural and positional information to be bypassed through these identity-based skip connections and thus eases the training of the deep denoising network. For training the AGC-LSRED network, we propose a compound loss that combines the L loss, adversarial loss, and self-supervised multi-scale perceptual loss.
Quantitative and qualitative experimental studies were performed to verify and validate the effectiveness of the proposed method. The simulation experiments demonstrated the proposed method exhibits the best result in terms of noise suppression [root-mean-square error (RMSE) =9.02; peak signal-to-noise ratio (PSNR) =33.17] and fine structure preservation [structural similarity index (SSIM) =0.925] compared with other competitive CNN-based methods. The experiments on real data illustrated that the proposed method has advantages over other methods in terms of radiologists' subjective assessment scores (averaged scores =4.34).
With the use of the AGC modeling scheme to characterize the structural information in CT images and of residual AGC-attention blocks with long and short skip connections to ease the network training, the proposed AGC-LSRED method achieves satisfactory results in preserving fine anatomical structures and suppressing noise in LDCT images.
低剂量计算机断层扫描（LDCT）可以有效减少对患者的辐射损伤，但这对CT图像质量有很大损害。深度卷积神经网络（CNN）已显示出其在提高LDCT图像质量方面的潜力。然而，传统的基于CNN的方法从根本上依赖于卷积操作，这对于建模非局部相似结构之间的相关性以及CT图像中区域不同的统计特性是无效的。这种建模缺陷阻碍了以这种方式获得的CT图像的去噪性能。
在本文中，我们提出了一种自适应全局上下文（AGC）建模方案，以描述CT图像中的非局部相关性和区域不同的统计特性，且计算负载可忽略不计。我们进一步提出了一种基于AGC的长短残差编码器 - 解码器（AGC - LSRED）网络，用于高效的LDCT图像噪声伪影抑制任务。具体而言，在AGC - LSRED网络中构建了具有长短跳跃连接的残差AGC注意力块（RAGCB）堆栈，这使得有价值的结构和位置信息能够通过这些基于恒等的跳跃连接被绕过，从而简化了深度去噪网络的训练。为了训练AGC - LSRED网络，我们提出了一种复合损失，它结合了L损失、对抗损失和自监督多尺度感知损失。
进行了定量和定性实验研究，以验证和确认所提出方法的有效性。模拟实验表明，与其他基于CNN的竞争方法相比，所提出的方法在噪声抑制[均方根误差（RMSE）= 9.02；峰值信噪比（PSNR）= 33.17]和精细结构保留[结构相似性指数（SSIM）= 0.925]方面表现出最佳结果。对真实数据的实验表明，在所提出的方法在放射科医生的主观评估分数方面（平均分数 = 4.34）优于其他方法。
通过使用AGC建模方案来表征CT图像中的结构信息，并使用具有长短跳跃连接的残差AGC注意力块来简化网络训练，所提出的AGC - LSRED方法在保留LDCT图像中的精细解剖结构和抑制噪声方面取得了令人满意的结果。
