Positron emission tomography (PET) scanners continue to increase sensitivity and axial coverage by adding an ever expanding array of block detectors. As they age, one or more block detectors may lose sensitivity due to a malfunction or component failure. The sinogram data missing as a result thereof can lead to artifacts and other image degradations. We propose to mitigate the effects of malfunctioning block detectors by carrying out sinogram repair using a deep convolutional neural network. Experiments using whole-body patient studies with varying amounts of raw data removed are used to show that the neural network significantly outperforms previously published methods with respect to normalized mean squared error for raw sinograms, a multi-scale structural similarity measure for reconstructed images and with regard to quantitative accuracy.
To reconstruct a radioactive tracer distribution with positron emission tomography (PET), the background attenuation correction is needed to eliminate image artifacts. Recent research shows that time-of-flight (TOF) PET data determine the attenuation sinogram up to a constant, and its gradient can be computed using an analytic algorithm. In this paper, we study a direct estimation of the sinogram only from TOF PET data. First, the gradient of the attenuation sinogram is estimated using the aforementioned algorithm. Then, a relationship is established to link the differential attenuation sinogr…
Filling of incomplete sinograms from sparse PET detector configurations using a residual U-Net
Department of Mathematics and Mathematical Statistics, Umeå University（数学与统计学系，乌梅大学）；Department of Mathematical Sciences, University of Copenhagen（数学科学系，哥本哈根大学）；Norsk Regnesentral, Oslo（奥斯陆挪威计算中心）；UiT Machine Learning Group, Department of Physics and Technology, UiT The Arctic University of Norway（UiT机器学习组，物理与技术系，UiT北极大学）；The PET Imaging Center, University Hospital of North Norway（北挪威大学医院PET成像中心）；Nuclear Medicine and Radiation Biology Research Group, Department of Clinical Medicine, UiT The Arctic University of Norway（核医学与辐射生物学研究组，临床医学系，UiT北极大学）；Department of Diagnostics and Intervention, Oncology, Umeå University（诊断与介入系，肿瘤学，乌梅大学）；Department of Diagnostics and Intervention, Radiation Physics, Umeå University（诊断与介入系，辐射物理学，乌梅大学）
One of the major challenges in design and developing of PET, scanners are the presence of inactive areas between the detector blocks which degrade the image spatial resolution and leads to streaking artifacts especially when we employ analytical image reconstruction. The aim of this study is to assess the feasibility of generating the gap-free PET image using the deep convolutional encoder-decoder in sinogram space. The gap-corrupted sinograms of simulated HRRT scanner, sinograms without gaps as ideal/ground truth and predicted sinograms owing to the implemented our deep-fill method were quant…
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…
Complete time of flight (TOF) sinograms of state-of-the-art TOF PET scanners have a large memory footprint. Currently, they contain ~4e9 data bins which amount to ~17GB in 32bit floating point precision. Using iterative algorithms to reconstruct such enormous TOF sinograms becomes increasingly challenging due to the memory requirements and the computation time needed to evaluate the forward model for every data bin. This is especially true for more advanced optimization algorithms such as the SPDHG algorithm which allows for the use of non-smooth priors using subsets with guaranteed convergenc…
An efficient approach with theoretical guarantees to simultaneously reconstruct activity and attenuation sinogram for TOF-PET
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China（数学科学国家重点实验室，数学与系统科学研究院，中国科学院，北京100190，中国）；University of Chinese Academy of Sciences, Beijing 100190, China（中国科学院大学，北京100190，中国）
University of California, San Francisco（加州大学旧金山分校）；University of New Mexico（新墨西哥大学）；Washington University（华盛顿大学）；University of Iowa（爱荷华大学）；University of Washington（华盛顿大学）
Historically, patient datasets have been used to develop and validate various reconstruction algorithms for PET/MRI and PET/CT. To enable such algorithm development, without the need for acquiring hundreds of patient exams, in this paper we demonstrate a deep learning technique to generate synthetic but realistic whole-body PET sinograms from abundantly-available whole-body MRI. Specifically, we use a dataset of 56 $^{18}$F-FDG-PET/MRI exams to train a 3D residual UNet to predict physiologic PET uptake from whole-body T1-weighted MRI. In training we implemented a balanced loss function to gene…
We developed a positron emission tomography (PET) system for multiple-isotope imaging. Our PET system, named multiple-isotope PET (MI-PET), can distinguish between different tracer nuclides using coincidence measurement of prompt gamma-rays, which are emitted after positron emission. In MI-PET imaging with a pure positron emitter and prompt-gamma emitter, because of the imperfectness of prompt gamma-ray detection, an image for a pure positron emitter taken by MI-PET is superposed by a positron-γ emitter. Therefore, in order to make isolated images of the pure positron emitter, we developed ima…
Zhejiang University（浙江大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；First Hospital of Shanxi Medical University（山西医科大学第一医院）
Patlak model is widely used in 18F-FDG dynamic positron emission tomography (PET) imaging, where the estimated parametric images reveal important biochemical and physiology information. Because of better noise modeling and more information extracted from raw sinogram, direct Patlak reconstruction gains its popularity over the indirect approach which utilizes reconstructed dynamic PET images alone. As the prerequisite of direct Patlak methods, raw data from dynamic PET are rarely stored in clinics and difficult to obtain. In addition, the direct reconstruction is time-consuming due to the bottl…
J-PET Framework is an open-source software platform for data analysis, written in C++ and based on the ROOT package. It provides a common environment for implementation of reconstruction, calibration and filtering procedures, as well as for user-level analyses of Positron Emission Tomography data. The library contains a set of building blocks that can be combined by users with even little programming experience, into chains of processing tasks through a convenient, simple and well-documented API. The generic input-output interface allows processing the data from various sources: low-level data…
Gordon Center for Medical Imaging（戈登医学影像中心）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Martinos Center for Biomedical Imaging（马蒂诺斯生物医学影像中心）；University of California, Davis（加州大学戴维斯分校）
Direct reconstruction methods have been developed to estimate parametric images directly from the measured PET sinograms by combining the PET imaging model and tracer kinetics in an integrated framework. Due to limited counts received, signal-to-noise-ratio (SNR) and resolution of parametric images produced by direct reconstruction frameworks are still limited. Recently supervised deep learning methods have been successfully applied to medical imaging denoising/reconstruction when large number of high-quality training labels are available. For static PET imaging, high-quality training labels c…
Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）；Weill Cornell Medicine（威尔康奈尔医学院）
Positron emission tomography (PET) is a cornerstone of modern radiology. The ability to detect cancer and metastases in whole body scans fundamentally changed cancer diagnosis and treatment. One of the main bottlenecks in the clinical application is the time it takes to reconstruct the anatomical image from the deluge of data in PET imaging. State-of-the art methods based on expectation maximization can take hours for a single patient and depend on manual fine-tuning. This results not only in financial burden for hospitals but more importantly leads to less efficient patient handling, evaluati…
Positron emission tomographs (PET) do not measure an image directly. Instead, they measure at the boundary of the field-of-view (FOV) of PET tomograph a sinogram that consists of measurements of the sums of all the counts along the lines connecting two detectors. As there is a multitude of detectors build-in typical PET tomograph structure, there are many possible detector pairs that pertain to the measurement. The problem is how to turn this measurement into an image (this is called imaging). Decisive improvement in PET image quality was reached with the introduction of iterative reconstructi…
This paper explores convolutional generative networks as an alternative to iterative reconstruction algorithms in medical image reconstruction. The task of medical image reconstruction involves mapping of projection main data collected from the detector to the image domain. This mapping is done typically through iterative reconstruction algorithms which are time consuming and computationally expensive. Trained deep learning networks provide faster outputs as proven in various tasks across computer vision. In this work we propose a direct reconstruction framework exclusively with deep learning …
