通过多任务学习，低剂量CT deoinging的生成对抗网络具有鲁棒歧视器
Generative Adversarial Network With Robust Discriminator Through Multi-Task Learning for Low-Dose CT Denoising
影响因子:9.80000
分区:医学1区 Top / 计算机：跨学科应用1区 工程：生物医学1区 工程：电子与电气1区 成像科学与照相技术1区
发表日期:2025 Jan
作者:
Sunggu Kyung, Jongjun Won, Seongyong Pak, Sunwoo Kim, Sangyoon Lee, Kanggil Park, Gil-Sun Hong, Namkug Kim
摘要
减少计算机断层扫描（CT）中辐射的剂量对于降低继发性癌症风险至关重要。但是，低剂量CT（LDCT）图像的使用伴随着噪声增加，可能会对诊断产生负面影响。尽管已经开发了许多深度学习算法用于LDCT DeOsising，但仍存在一些挑战，包括放射科医生经历的视觉不一致，各种指标的性能不令人满意，以及对网络在其他CT领域的鲁棒性的不足。为了解决此类问题，本研究提出了三个新颖的积聚。首先，我们通过多任务学习，同时执行三个视觉任务：恢复，图像级和像素级的决策，提出了一个具有强大歧视者的生成对抗网络（GAN）。执行的多任务越多，发电机的转换性能就越好，这意味着多任务学习使歧视者能够为发电机提供更有意义的反馈。第二，引入了两种调节机制，恢复一致性（RC）和非差异抑制（NDS），以提高歧视者的表示能力。这些机制消除了无关的区域，并通过输入和恢复进行了比较歧视者的结果，从而促进了有效的GAN训练。最后，我们将残留的快速傅立叶变换与卷积（RES-FFT-CONV）块一起融合到发电机中，以同时利用频率和空间表示。这种方法通过使用空间（或局部），光谱（或全局）和残留连接提供混合的接收场。在两个降级任务中，使用各种像素和功能空间指标对我们的模型进行了评估。此外，我们与放射科医生进行了视觉评分。结果表明，与最先进的去核技术相比，定量和定性措施的表现都出色。
Abstract
Reducing the dose of radiation in computed tomography (CT) is vital to decreasing secondary cancer risk. However, the use of low-dose CT (LDCT) images is accompanied by increased noise that can negatively impact diagnoses. Although numerous deep learning algorithms have been developed for LDCT denoising, several challenges persist, including the visual incongruence experienced by radiologists, unsatisfactory performances across various metrics, and insufficient exploration of the networks' robustness in other CT domains. To address such issues, this study proposes three novel accretions. First, we propose a generative adversarial network (GAN) with a robust discriminator through multi-task learning that simultaneously performs three vision tasks: restoration, image-level, and pixel-level decisions. The more multi-tasks that are performed, the better the denoising performance of the generator, which means multi-task learning enables the discriminator to provide more meaningful feedback to the generator. Second, two regulatory mechanisms, restoration consistency (RC) and non-difference suppression (NDS), are introduced to improve the discriminator's representation capabilities. These mechanisms eliminate irrelevant regions and compare the discriminator's results from the input and restoration, thus facilitating effective GAN training. Lastly, we incorporate residual fast Fourier transforms with convolution (Res-FFT-Conv) blocks into the generator to utilize both frequency and spatial representations. This approach provides mixed receptive fields by using spatial (or local), spectral (or global), and residual connections. Our model was evaluated using various pixel- and feature-space metrics in two denoising tasks. Additionally, we conducted visual scoring with radiologists. The results indicate superior performance in both quantitative and qualitative measures compared to state-of-the-art denoising techniques.