Dose-aware Diffusion Model for 3D PET Image Denoising: Multi-institutional Validation with Reader Study and Real Low-dose Data
Huidong Xie, Weijie Gan, Reimund Bayerlein, Bo Zhou, Ming-Kai Chen, Michal Kulon, Annemarie Boustani, Kuan-Yin Ko, Der-Shiun Wang, Benjamin A. Spencer, Wei Ji, … 展开作者
Huidong Xie, Weijie Gan, Reimund Bayerlein, Bo Zhou, Ming-Kai Chen, Michal Kulon, Annemarie Boustani, Kuan-Yin Ko, Der-Shiun Wang, Benjamin A. Spencer, Wei Ji, Xiongchao Chen, Qiong Liu, Xueqi Guo, Menghua Xia, Yinchi Zhou, Hui Liu, Liang Guo, Hongyu An, Ulugbek S. Kamilov, Hanzhong Wang, Biao Li, Axel Rominger, Kuangyu Shi, Ge Wang, Ramsey D. Badawi, Chi Liu
备注：
18 Pages, 16 Figures, 5 Tables. Paper under review. First-place Freek J. Beekman Young Investigator Award at SNMMI 2024. Code available after paper publication. arXiv admin note: substantial text overlap with arXiv:2311.04248
Reducing scan times, radiation dose, and enhancing image quality for lower-performance scanners, are critical in low-dose PET imaging. Deep learning techniques have been investigated for PET image denoising. However, existing models have often resulted in compromised image quality when achieving low-count/low-dose PET and have limited generalizability to different image noise-levels, acquisition protocols, and patient populations. Recently, diffusion models have emerged as the new state-of-the-art generative model to generate high-quality samples and have demonstrated strong potential for medical imaging tasks. However, for low-dose PET imaging, existing diffusion models failed to generate consistent 3D reconstructions, unable to generalize across varying noise-levels, often produced visually-appealing but distorted image details, and produced images with biased tracer uptake. Here, we develop DDPET-3D, a dose-aware diffusion model for 3D low-dose PET imaging to address these challenges. Collected from 4 medical centers globally with different scanners and clinical protocols, we evaluated the proposed model using a total of 9,783 18F-FDG studies with low-dose levels ranging from 1% to 50%. With a cross-center, cross-scanner validation, the proposed DDPET-3D demonstrated its potential to generalize to different low-dose levels, different scanners, and different clinical protocols. As confirmed with reader studies performed by board-certified nuclear medicine physicians, experienced readers judged the images to be similar or superior to the full-dose images and previous DL baselines based on qualitative visual impression. Lesion-level quantitative accuracy was evaluated using a Monte Carlo simulation study and a lesion segmentation network. The presented results show the potential to achieve low-dose PET while maintaining image quality. Real low-dose scans was also included for evaluation.
Two-Phase Multi-Dose-Level PET Image Reconstruction with Dose Level Awareness
School of Computer Science, Sichuan University（四川大学计算机学院）；School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University（上海科技大学生物医学工程学院 & 先进医学材料与器件国家重点实验室）；Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司）
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）
Zhejiang University（浙江大学）；Binjiang Institute of Zhejiang University（浙江大学滨江研究院）；Hangzhou Universal Medical Imaging Diagnostic Center（杭州全景医学影像诊断中心）
18F-fluorodeoxyglucose (18F-FDG) Positron Emission Tomography (PET) imaging usually needs a full-dose radioactive tracer to obtain satisfactory diagnostic results, which raises concerns about the potential health risks of radiation exposure, especially for pediatric patients. Reconstructing the low-dose PET (L-PET) images to the high-quality full-dose PET (F-PET) ones is an effective way that both reduces the radiation exposure and remains diagnostic accuracy. In this paper, we propose a resource-efficient deep learning framework for L-PET reconstruction and analysis, referred to as transGAN-S…
Gating is commonly used in PET imaging to reduce respiratory motion blurring and facilitate more sophisticated motion correction methods. In the applications of low dose PET, however, reducing injection dose causes increased noise and reduces signal-to-noise ratio (SNR), subsequently corrupting the motion estimation/correction steps, causing inferior image quality. To tackle these issues, we first propose a Siamese adversarial network (SAN) that can efficiently recover high dose gated image volume from low dose gated image volume. To ensure the appearance consistency between the recovered gate…
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。
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）
Due to the widespread use of positron emission tomography (PET) in clinical practice, the potential risk of PET-associated radiation dose to patients needs to be minimized. However, with the reduction in the radiation dose, the resultant images may suffer from noise and artifacts that compromise diagnostic performance. In this paper, we propose a parameter-transferred Wasserstein generative adversarial network (PT-WGAN) for low-dose PET image denoising. The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural…
Indian Institute of Technology (IIT) Bombay（印度理工学院孟买分校）；IITB-Monash Research Academy（印度理工学院孟买分校-莫纳什研究学院）；Monash University（莫纳什大学）
Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer dose or acquisition time reduces photon counts, which can deteriorate image quality. Recent deep-neural-network (DNN) based methods for image-to-image translation enable the mapping of low-quality PET images (acquired using substantially reduced dose), coupled with the associated magnetic resonance imaging (MRI) images, to high-quality PET images. However, s…
FedFTN: Personalized Federated Learning with Deep Feature Transformation Network for Multi-institutional Low-count PET Denoising
Yale University（耶鲁大学）；University of Southern California（南加州大学）；University of California Irvine（加州大学欧文分校）；University of Science and Technology of China（中国科学技术大学）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属瑞金医院）；Inselspital, Bern University Hospital（伯尔尼大学医院 Inselspital）；University of Bern（伯尔尼大学）；Technical University of Munich（慕尼黑工业大学）
Self is the Best Learner: CT-free Ultra-Low-Dose PET Organ Segmentation via Collaborating Denoising and Segmentation Learning
School of Biomedical Engineering, Southern Medical University（生物医学工程学院，南方医科大学）；School of Biomedical Engineering, Shanghai Jiao Tong University（生物医学工程学院，上海交通大学）；Nanfang PET Center, Nanfang Hospital Southern Medical University（南芳PET中心，南方医科大学南芳医院）；Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University（广东省医学图像处理重点实验室，南方医科大学）；Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University（广东省医学影像与诊断技术工程实验室，南方医科大学）；Pazhou Lab（琶洲实验室）
Cycle-Constrained Adversarial Denoising Convolutional Network for PET Image Denoising: Multi-Dimensional Validation on Large Datasets with Reader Study and Real Low-Dose Data
Despite its tremendous value for the diagnosis, treatment monitoring and surveillance of children with cancer, whole body staging with positron emission tomography (PET) is time consuming and associated with considerable radiation exposure. 100x (1% of the standard clinical dosage) ultra-low-dose/ultra-fast whole-body PET reconstruction has the potential for cancer imaging with unprecedented speed and improved safety, but it cannot be achieved by the naive use of machine learning techniques. In this study, we utilize the global similarity between baseline and follow-up PET and magnetic resonan…
TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
School of Computer Science, Sichuan University（四川大学计算机学院）；School of Computer Science, Chengdu University of Information Technology（成都信息工程大学计算机学院）；School of Biomedical Engineering, ShanghaiTech University（上海科技大学生物医学工程学院）；Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司）
POUR-Net: A Population-Prior-Aided Over-Under-Representation Network for Low-Count PET Attenuation Map Generation
Yale University（耶鲁大学）；University of California Irvine（加利福尼亚大学尔湾分校）；Canon Medical Research USA Inc.（佳能医疗研究美国公司）；Siemens Medical Solutions Inc.（西门子医疗解决方案公司）
University of California Los Angeles（加利福尼亚大学洛杉矶分校）；Duke University Medical Center（杜克大学医学中心）
This paper develops a method of biologically guided deep learning for post-radiation FDG-PET image outcome prediction based on pre-radiation images and radiotherapy dose information. Based on the classic reaction-diffusion mechanism, a novel biological model was proposed using a partial differential equation that incorporates spatial radiation dose distribution as a patient-specific treatment information variable. A 7-layer encoder-decoder-based convolutional neural network (CNN) was designed and trained to learn the proposed biological model. As such, the model could generate post-radiation F…
2.5D Multi-view Averaging Diffusion Model for 3D Medical Image Translation: Application to Low-count PET Reconstruction with CT-less Attenuation Correction
Yale School of Medicine（耶鲁医学院）；University of California Irvine（加州大学欧文分校）；Yale University（耶鲁大学）
The University of Tennessee（田纳西大学）；Siemens Medical Solutions Inc.（西门子医疗解决方案公司）
Direct reconstruction of positron emission tomography (PET) data using deep neural networks is a growing field of research. Initial results are promising, but often the networks are complex, memory utilization inefficient, produce relatively small 2D image slices (e.g., 128x128), and low count rate reconstructions are of varying quality. This paper proposes FastPET, a novel direct reconstruction convolutional neural network that is architecturally simple, memory space efficient, works for non-trivial 3D image volumes and is capable of processing a wide spectrum of PET data including low-dose a…
Manifold-Constrained PET Reconstruction with Learned Flow-Matching Priors
ZJU-UIUC Institute, Zhejiang University（浙江大学紫金港研究院）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息与电子工程学院）；College of Optical Science and Engineering, Zhejiang University（浙江大学光电科学与工程学院）；Vivo Mobile Communication Co., Ltd.（维沃移动通信有限公司）；College of Biomedical Engineering and Instrument Science, Zhejiang University（浙江大学生物医学工程与仪器科学学院）
Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
Sichuan University（四川大学）；University of Sydney（悉尼大学）；Chengdu University of Information Technology（成都信息工程大学）；ShanghaiTech University（上海科技大学）；Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能科技有限公司）
针对低剂量 PET 重建中扩散模型采样慢、条件对应保持不足的问题，提出由 CPM 与 IRM 构成的由粗到细框架，并引入辅助引导和对比扩散策略，提升速度、重建质量及临床可靠性。
Image2Points:A 3D Point-based Context Clusters GAN for High-Quality PET Image Reconstruction
School of Computer Science, Sichuan University（四川大学计算机学院）；School of Computer Science, Chengdu University of Information Technology（成都信息工程大学计算机学院）；School of Biomedical Engineering, ShanghaiTech University（上海科技大学生物医学工程学院）；Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司研发部）
MCAD: Multi-modal Conditioned Adversarial Diffusion Model for High-Quality PET Image Reconstruction
School of Computer Science, Sichuan University（四川大学计算机学院）；The Hong Kong Polytechnic University（香港理工大学）；School of Computer Science, Chengdu University of Information Technology（成都信息工程大学计算机学院）
Positron Emission Tomography (PET) is an important tool for studying Alzheimer's disease (AD). PET scans can be used as diagnostics tools, and to provide molecular characterization of patients with cognitive disorders. However, multiple tracers are needed to measure glucose metabolism (18F-FDG), synaptic vesicle protein (11C-UCB-J), and $β$-amyloid (11C-PiB). Administering multiple tracers to patient will lead to high radiation dose and cost. In addition, access to PET scans using new or less-available tracers with sophisticated production methods and short half-life isotopes may be very limit…
Multibranch Generative Models for Multichannel Imaging with an Application to PET/CT Synergistic Reconstruction
Univ. Brest, LaTIM, INSERM, UMR 1101（布雷斯特大学、LaTIM研究所、法国国家健康与医学研究院、UMR 1101联合研究单位）；Nuclear Medicine Department, Poitiers University Hospital（普瓦捷大学医院核医学科）
Patlak Parametric Image Estimation from Dynamic PET Using Diffusion Model Prior
J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida（J. Crayton Pruitt家族生物医学工程系，佛罗里达大学）；Department of Radiology, University of Florida（放射学系，佛罗里达大学）；Interdisciplinary Program in Bioengineering, Seoul National University（生物工程跨学科项目，首尔国立大学）；Department of Nuclear Medicine, Seoul National University College of Medicine（核医学系，首尔国立大学医学院）；Department of Radiology, University of California Davis Health（放射学系，加州大学戴维斯医学中心）
Quantitative accuracy and thus diagnostic precision in Emission Tomography is impaired by the inherent random characteristics of the data acquisition leading to statistical image noise. Edge preserving spatial variation regularized iterative image reconstruction approaches require case-specific control parameter adaptation for optimized contrast-vs-noise tradeoff. For MLEM reconstruction, we propose and evaluate iRDF which automatically adapts RDP edge preservation parameters according to local image noise and PET data characteristics. In order to distinguish between clustered noise spots and …
PAII Inc.（PAII公司）；The First Affiliated Hospital Zhejiang University（浙江大学附属第一医院）；Ping An Technology（平安科技）；Chang Gung Memorial Hospital（长庚纪念医院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Huadong Hospital Affiliated to Fudan University（复旦大学附属华东医院）；First Affiliated Hospital of Xi'an Jiaotong University（西安交通大学第一附属医院）；People's Hospital of Shanxi Province（山西省人民医院）；Nanfang Hospital, Southern Medical University（南方医科大学南方医院）；The First Hospital of Lanzhou University（兰州大学第一医院）；Chang Gung University（长庚大学）
Accurate organ at risk (OAR) segmentation is critical to reduce the radiotherapy post-treatment complications. Consensus guidelines recommend a set of more than 40 OARs in the head and neck (H&N) region, however, due to the predictable prohibitive labor-cost of this task, most institutions choose a substantially simplified protocol by delineating a smaller subset of OARs and neglecting the dose distributions associated with other OARs. In this work we propose a novel, automated and highly effective stratified OAR segmentation (SOARS) system using deep learning to precisely delineate a comprehe…
REACT-KD: Region-Aware Cross-modal Topological Knowledge Distillation for Interpretable Medical Image Classification
Department of Health Technology and Informatics, Hong Kong Polytechnic University（健康科技与信息技术系，香港理工大学）；Department of Nuclear Medicine and PET, Hong Kong Sanatorium and Hospital（核医学与PET部门，香港疗养院及医院）
Imam Abdulrahman Bin Faisal University（伊玛目阿卜杜勒拉赫曼·本·费萨尔大学）
To accurately quantify in vivo radiotracer uptake using Positron Emission Tomography (PET) is a challenging task due to low signal-to-noise ratio (SNR) and poor spatial resolution of PET camera along with the finite image sampling constraint. Furthermore, inter lesion variations of the SNR and contrast along with the variations in size of the lesion make the quantitation even more difficult. One of the ways to improve the quantitation is via post reconstruction filtering with Gaussian Filter (GF). Edge preserving Bilateral Filter (BF) and Nonlinear Diffusion Filter (NDF) are the alternatives t…
The University of Tennessee（田纳西大学）；Siemens Medical Solutions USA Inc.（美国西门子医疗解决方案公司）
Purpose: Neural network image reconstruction directly from measurement data is a relatively new field of research, that until now has been limited to producing small single-slice images (e.g., 1x128x128). This paper proposes a novel and more efficient network design for Positron Emission Tomography called DirectPET which is capable of reconstructing multi-slice image volumes (i.e., 16x400x400) from sinograms. Approach: Large-scale direct neural network reconstruction is accomplished by addressing the associated memory space challenge through the introduction of a specially designed Radon inver…
FedSynthCT-Brain: A Federated Learning Framework for Multi-Institutional Brain MRI-to-CT Synthesis
Institute of Biomedical Engineering（生物医学工程研究所）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工大学）；Department of Radiation Oncology（放射肿瘤科）；University Medical Center Schleswig-Holstein（什勒斯威-霍斯特大学医院）；Department of Experimental and Clinical Medicine（实验与临床医学系）；Magna Graecia University（马格拉西亚大学）；Department of Information Engineering（信息工程系）；Università Politecnica delle Marche（帕尔米拉理工大学）
