Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences, Cixi, China.
University of Chinese Academy of Sciences, Beijing, China.
Med Phys. 2023 Dec;50(12):7654-7669. doi: 10.1002/mp.16550. Epub 2023 Jun 6.
Various types of noise artifacts inevitably exist in some medical imaging modalities due to limitations of imaging techniques, which impair either clinical diagnosis or subsequent analysis. Recently, deep learning approaches have been rapidly developed and applied on medical images for noise removal or image quality enhancement. Nevertheless, due to complexity and diversity of noise distribution representations in different medical imaging modalities, most of the existing deep learning frameworks are incapable to flexibly remove noise artifacts while retaining detailed information. As a result, it remains challenging to design an effective and unified medical image denoising method that will work across a variety of noise artifacts for different imaging modalities without requiring specialized knowledge in performing the task.
In this paper, we propose a novel encoder-decoder architecture called Swin transformer-based residual u-shape Network (StruNet), for medical image denoising.
Our StruNet adopts a well-designed block as the backbone of the encoder-decoder architecture, which integrates Swin Transformer modules with residual block in parallel connection. Swin Transformer modules could effectively learn hierarchical representations of noise artifacts via self-attention mechanism in non-overlapping shifted windows and cross-window connection, while residual block is advantageous to compensate loss of detailed information via shortcut connection. Furthermore, perceptual loss and low-rank regularization are incorporated into loss function respectively in order to constrain the denoising results on feature-level consistency and low-rank characteristics.
To evaluate the performance of the proposed method, we have conducted experiments on three medical imaging modalities including computed tomography (CT), optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA).
The results demonstrate that the proposed architecture yields a promising performance of suppressing multiform noise artifacts existing in different imaging modalities.
由于成像技术的限制，各种类型的噪声伪影不可避免地存在于某些医学成像模态中，这会影响临床诊断或后续分析。最近，深度学习方法在医学图像去噪或图像质量增强方面得到了迅速发展和应用。然而，由于不同医学成像模态中噪声分布表示的复杂性和多样性，大多数现有的深度学习框架无法灵活地去除噪声伪影，同时保留详细信息。因此，设计一种有效的、统一的医学图像去噪方法仍然具有挑战性，该方法可以跨不同成像模态的各种噪声伪影工作，而无需专门的任务知识。
在本文中，我们提出了一种新的基于 Swin Transformer 的编码器-解码器架构，称为 Swin transformer 残差 U 形网络（StruNet），用于医学图像去噪。
我们的 StruNet 采用了精心设计的块作为编码器-解码器架构的骨干，它将 Swin Transformer 模块与残差块并行连接。Swin Transformer 模块可以通过在非重叠移位窗口和跨窗口连接中的自注意力机制，有效地学习噪声伪影的分层表示，而残差块通过捷径连接有利于补偿详细信息的损失。此外，感知损失和低秩正则化分别被纳入损失函数中，以便在特征级一致性和低秩特征上约束去噪结果。
为了评估所提出方法的性能，我们在包括计算机断层扫描（CT）、光学相干断层扫描（OCT）和光学相干断层扫描血管造影（OCTA）在内的三种医学成像模态上进行了实验。
结果表明，所提出的架构在抑制不同成像模态中存在的多种噪声伪影方面具有很有前景的性能。
