通过多任务学习实现鲁棒判别器的生成对抗网络用于低剂量CT去噪

Generative Adversarial Network With Robust Discriminator Through Multi-Task Learning for Low-Dose CT Denoising

DOI 原文链接

用sci-hub下载

IEEE TRANSACTIONS ON MEDICAL IMAGING

影响因子:9.8

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

DOI: 10.1109/TMI.2024.3449647

摘要

降低计算机断层扫描（CT）辐射剂量对减少次级癌症风险至关重要。然而，低剂量CT（LDCT）图像伴随噪声增加，可能影响诊断。尽管已有多种深度学习算法用于LDCT去噪，但仍面临如放射科医师视觉不一致、性能指标不理想以及网络在其他CT领域鲁棒性不足等挑战。为解决这些问题，本文提出三项创新。第一，提出一种具有多任务学习的鲁棒判别器生成对抗网络（GAN），同时执行三项视觉任务：恢复、图像级和像素级判定。多任务的执行提升了生成器的去噪性能，即多任务学习使判别器能提供更有意义的反馈。第二，引入两种调节机制：恢复一致性（RC）和非差异抑制（NDS），以增强判别器的表达能力。这些机制通过排除无关区域并比较输入与恢复的判别结果，促进有效的GAN训练。最后，将残差快速傅里叶变换（Res-FFT-Conv）块融入生成器中，利用频域和空间域的特征，提供混合感受野，结合空间（局部）、频谱（全局）与残差连接。模型在两项去噪任务中采用多种像素和特征空间指标进行评估，并由放射科医师进行视觉评分。结果显示，该方法在定量和定性方面均优于最新的去噪技术。

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.