Like in many other research fields, recent developments in computational imaging have focused on developing machine learning (ML) approaches to tackle its main challenges. To improve the performance of computational imaging algorithms, machine learning methods are used for image processing tasks such as noise reduction. Generally, these ML methods heavily rely on the availability of high-quality data on which they are trained. This work explores the application of ML methods, specifically convolutional neural networks (CNNs), in the context of noise reduction for computed tomography (CT) imaging. We utilize a large 2D computed tomography dataset for machine learning to carry out for the first time a comprehensive study on the differences between the observed performances of algorithms trained on simulated noisy data and on real-world experimental noisy data. The study compares the performance of two common CNN architectures, U-Net and MSD-Net, that are trained and evaluated on both simulated and experimental noisy data. The results show that while sinogram denoising performed better with simulated noisy data if evaluated in the sinogram domain, the performance did not carry over to the reconstruction domain where training on experimental noisy data shows a higher performance in denoising experimental noisy data. Training the algorithms in an end-to-end fashion from sinogram to reconstruction significantly improved model performance, emphasizing the importance of matching raw measurement data to high-quality CT reconstructions. The study furthermore suggests the need for more sophisticated noise simulation approaches to bridge the gap between simulated and real-world data in CT image denoising applications and gives insights into the challenges and opportunities in leveraging simulated data for machine learning in computational imaging.
University of Michigan - Shanghai Jiao Tong University Joint Institute（密歇根大学-上海交通大学联合学院）；Shanghai Jiao Tong University（上海交通大学）；University of Hawai’i at Manoa（夏威夷大学马诺阿分校）
本文将最新的快速迭代神经网络框架Momentum-Net应用于低剂量X射线计算机断层扫描（LDCT）图像重建。在所提出的动量网络的每一层，基于模型的图像重建模块解决优化惩罚加权最小二乘问题，图像细化模块使用四层卷积神经网络（CNN）。使用NIH AAPM-Mayo Clinic低剂量CT Grand Challenge数据集的实验结果表明，与最先进的非迭代图像去噪深度神经网络（NN）WavResNet（在LDCT中）相比，所提出的Momentum-Net架构显著提高了图像重建的准确性。我们还研究了适用于图像细化NN学习的谱归一化技术，以满足非扩展NN属性;然而，实验结果表明，这并不能提高动量网络的图像重建性能。
Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising
在医疗实践中使用计算机断层扫描（CT）成像的爆炸性增长，提高了公众对患者相关辐射剂量的关注。然而，减少辐射剂量导致噪声和伪影增加，这不利地降低了扫描的可解释性。因此，一种先进的图像重建算法来提高低剂量ct的诊断性能成为研究人员的主要关注点，但由于该问题的不适定性，这具有挑战性。近年来，基于深度学习的技术已经成为低剂量CT（LDCT）去噪的主要方法。然而，仍然存在一些常见的瓶颈，这阻碍了基于深度学习的技术提供最佳性能。在这项研究中，我们试图减轻这些问题与三个新的吸积。首先，我们提出了一种新的卷积模块作为第一次尝试利用CT图像的邻域相似性去噪任务。我们提出的模块有助于提高去噪的显著幅度。接下来，我们转向CT噪声的非平稳性问题，并引入了一种新的噪声感知均方误差损失用于LDCT去噪。此外，上述损失也有助于减轻使用图像补丁训练CT去噪网络时所需的繁重工作。最后，我们提出了一种新的CT去噪任务的函数。传统的香草型协议往往忽略了精细的结构细节，而专注于全球协议。我们提出的神经网络利用自注意力和像素级GANs来恢复LDCT图像的诊断质量。我们的方法在2016年NIH-AAPM-Mayo Clinic低剂量CT Grand Challenge的公开数据集上进行了验证，其表现明显优于现有的最先进方法。
MDAA-Diff: CT-Guided Multi-Dose Adaptive Attention Diffusion Model for PET Denoising
School of Biomedical Engineering, Southern Medical University（南方医科大学生物医学工程学院）；School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；Nanfang PET Center, Nanfang Hospital Southern Medical University（南方医科大学南芳医院PET中心）
Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising
Northeastern University（东北大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
Friedrich-Alexander Universität Erlangen-Nürnberg (FAU)（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Siemens Healthcare GmbH（西门子医疗有限公司）
深度神经网络在低剂量CT去噪方面取得了巨大成功。然而，这些深度神经网络中的大多数都有几十万个可训练的参数。这与神经网络固有的非线性相结合，使得深度神经网络难以理解，责任心低。在这项研究中，我们介绍了JBFnet，神经网络的低剂量CT去噪。JBFnet的体系结构实现了迭代双边滤波。联合双边滤波器（JBF）的滤波器函数是通过浅层卷积网络学习的。引导图像由深度神经网络估计。JBFnet分为四个滤波块，每个滤波块执行联合双边滤波。每个JBF块由112个可训练的参数组成，使得噪声去除过程非常简单。在滤波之后添加噪声图（NM）以保留高级特征。我们用10名患者的身体扫描数据训练JBFnet，并在AAPM低剂量CT Grand Challenge数据集上对其进行测试。我们将JBFnet与最先进的深度学习网络进行比较。JBFnet在去除噪声的同时保留结构方面优于测试数据集上的CPCE 3D，GAN和深度GFnet。我们进行了几次消融研究，以测试我们的网络架构和训练方法的性能。我们目前的设置实现了最佳性能，同时仍然保持行为问责制。
ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学类脑智能科学与技术研究院）；School of Cyber Science and Engineering, Sichuan University（四川大学网络空间安全学院）
Low-dose CT Denoising with Language-engaged Dual-space Alignment
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学脑智能科学与技术研究院）；Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute（伦斯勒理工学院生物技术与跨学科研究中心）
A deep dictionary network-based foundation model for ultra-low-dose CT denoising
Yanshan University（燕山大学）；Capital Medical University（首都医科大学）；Beijing Friendship Hospital（北京友谊医院）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）
GAN-Based Architecture for Low-dose Computed Tomography Imaging Denoising
College of Life Science and Technology, Huazhong University of Science and Technology（华中科技大学生命科学技术学院）；New York University Shanghai（上海纽约大学）；School of Life Sciences and Biotechnology, Shanghai Jiao Tong University（上海交通大学生命科学技术学院）
WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computer Science, Central China Normal University（华中师范大学计算机学院）；University of Louisville（路易斯维尔大学）
Cycle-Constrained Adversarial Denoising Convolutional Network for PET Image Denoising: Multi-Dimensional Validation on Large Datasets with Reader Study and Real Low-Dose Data
School of Statistics and Data Science, Nankai University（南开大学统计与数据科学学院）；The First Affiliated Hospital of Xi’an Jiaotong University（西安交通大学第一附属医院）；Shanxi Engineering Research Center of Computational Imaging and Medical Intelligence（山西省计算成像与医学智能工程研究中心）
Patch-wise Deep Metric Learning for Unsupervised Low-Dose CT Denoising
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））；VUNO Corp.（VUNO公司）；Chungnam National University College of Medicine（忠南大学医学院）；Chungnam National University Hospital（忠南大学医院）
End-to-end Triple-domain PET Enhancement: A Hybrid Denoising-and-reconstruction Framework for Reconstructing Standard-dose PET Images from Low-dose PET Sinograms
ShanghaiTech University（上海科技大学）；Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司）；Shanghai Clinical Research and Trial Center（上海临床研究与试验中心）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
提出端到端三域 TriPLET 框架，融合投影域去噪、小波域重建和图像域对抗评估，从低剂量 PET 正弦图恢复标准剂量图像，并取得最优相似度与信噪比。
PFCM: Poisson flow consistency models for low-dose CT image denoising
Stanford University（斯坦福大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Karolinska University Hospital（卡罗林斯卡大学医院）；GE HealthCare（GE医疗）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
