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 architectures. The proposed framework consists of three segments, namely denoising, reconstruction and super resolution. The denoising and the super resolution segments act as processing steps. The reconstruction segment consists of a novel double U-Net generator (DUG) which learns the sinogram-to-image transformation. This entire network was trained on positron emission tomography (PET) and computed tomography (CT) images. The reconstruction framework approximates two-dimensional (2-D) mapping from projection domain to image domain. The architecture proposed in this proof-of-concept work is a novel approach to direct image reconstruction; further improvement is required to implement it in a clinical setting.
In this paper, we explore a novel method for tomographic image reconstruction in the field of SPECT imaging. Deep Learning methodologies and more specifically deep convolutional neural networks (CNN) are employed in the new reconstruction method, which is referred to as "CNN Reconstruction - CNNR". For training of the CNNR Projection data from software phantoms were used. For evaluation of the efficacy of the CNNR method, both software and hardware phantoms were used. The resulting tomographic images are compared to those produced by filtered back projection (FBP) [1], the "Maximum Likelihood …
The improvement of computed tomography (CT) image resolution is beneficial to the subsequent medical diagnosis, but it is usually limited by the scanning devices and great expense. Convolutional neural network (CNN)-based methods have achieved promising ability in super-resolution. However, existing methods mainly focus on the super-resolution of reconstructed image and do not fully explored the approach of super-resolution from projection-domain. In this paper, we studied the characteristic of projection and proposed a CNN-based super-resolution method to establish the mapping relationship of…
Traditional dictionary learning based CT reconstruction methods are patch-based and the features learned with these methods often contain shifted versions of the same features. To deal with these problems, the convolutional sparse coding (CSC) has been proposed and introduced into various applications. In this paper, inspired by the successful applications of CSC in the field of signal processing, we propose a novel sparse-view CT reconstruction method based on CSC with gradient regularization on feature maps. By directly working on whole image, which need not to divide the image into overlapp…
Improved Image Reconstruction and Diffusion Parameter Estimation Using a Temporal Convolutional Network Model of Gradient Trajectory Errors
Vanderbilt University Institute of Imaging Science（范德比尔特大学影像科学研究所）；Vanderbilt University Medical Center（范德比尔特大学医学中心）；Department of Biomedical Engineering（生物医学工程系）；Department of Radiology and Radiological Sciences（放射学与放射科学系）
Compressed sensing magnetic resonance imaging (CS-MRI) is a theoretical framework that can accurately reconstruct images from undersampled k-space data with a much lower sampling rate than the one set by the classical Nyquist-Shannon sampling theorem. Therefore, CS-MRI can efficiently accelerate acquisition time and relieve the psychological burden on patients while maintaining high imaging quality. The problems with traditional CS-MRI reconstruction are solved by iterative numerical solvers, which usually suffer from expensive computational cost and the lack of accurate handcrafted priori. In…
Many real-world signal sources are complex-valued, having real and imaginary components. However, the vast majority of existing deep learning platforms and network architectures do not support the use of complex-valued data. MRI data is inherently complex-valued, so existing approaches discard the richer algebraic structure of the complex data. In this work, we investigate end-to-end complex-valued convolutional neural networks - specifically, for image reconstruction in lieu of two-channel real-valued networks. We apply this to magnetic resonance imaging reconstruction for the purpose of acce…
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Zhejiang University（浙江大学）
Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a novel 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervise…
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…
Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation problem, will degrade the imaging quality. In this paper, we propose a novel LDCT reconstruction network that unrolls the iterative scheme and performs in both image and manifold spaces. Because patch manifolds of medical images have low-dimensional structures, we can build graphs from the manifolds. Then, we simultaneously leverage the spatial convolution to extract the local pixel-level features from the images and incorporate the graph convolution to analyze the nonlocal topological features in manifold…
Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School（马萨诸塞州总医院与哈佛医学院戈登医学影像中心）；Department of Biomedical Engineering, University of California, Davis（加利福尼亚大学戴维斯分校生物医学工程系）；Department of Statistics, University of California, Davis（加利福尼亚大学戴维斯分校统计系）
PET image reconstruction is challenging due to the ill-poseness of the inverse problem and limited number of detected photons. Recently deep neural networks have been widely and successfully used in computer vision tasks and attracted growing interests in medical imaging. In this work, we trained a deep residual convolutional neural network to improve PET image quality by using the existing inter-patient information. An innovative feature of the proposed method is that we embed the neural network in the iterative reconstruction framework for image representation, rather than using it as a post…
University of Dundee（邓迪大学）；University Hospital Poitiers（普瓦捷大学医院）
Objective. Dual-energy computed tomography (DECT) has the potential to improve contrast, reduce artifacts and the ability to perform material decomposition in advanced imaging applications. The increased number or measurements results with a higher radiation dose and it is therefore essential to reduce either number of projections per energy or the source X-ray intensity, but this makes tomographic reconstruction more ill-posed. Approach. We developed the multi-channel convolutional analysis operator learning (MCAOL) method to exploit common spatial features within attenuation images at differ…
Deep convolutional framelets for dose reconstruction in BNCT with Compton camera detector
Istituto Nazionale di Fisica Nucleare（国家核物理研究所）；Università degli Studi di Bari Aldo Moro（巴里阿尔多·莫罗大学）；Nanjing University of Science and Technology（南京理工大学）
College of Computer Science, Sichuan University（四川大学计算机学院）；Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China and the School of Electronics Engineering and Computer Science, Peking University, China（北京大学电子工程与计算机科学学院）；Shanghai First-imaging Information Technology co. LTD（上海第一影像信息技术有限公司）；school of Mathematics and Computer Science, Gannan Normal University（赣南师范大学数学与计算机科学学院）；Rutgers, the State University of New Jersey（罗格斯大学（新泽西州立大学））；Department of Radiology, West China Hospital of Sichuan University（四川大学华西医院放射科）
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explor…
University of Minnesota（明尼苏达大学）；Sungkyunkwan University（成均馆大学）
Recent studies show that deep learning (DL) based MRI reconstruction outperforms conventional methods, such as parallel imaging and compressed sensing (CS), in multiple applications. Unlike CS that is typically implemented with pre-determined linear representations for regularization, DL inherently uses a non-linear representation learned from a large database. Another line of work uses transform learning (TL) to bridge the gap between these two approaches by learning linear representations from data. In this work, we combine ideas from CS, TL and DL reconstructions to learn deep linear convol…
Thayer School of Engineering（塞耶工程学院）；Dartmouth College（达特茅斯学院）；Department of Physics（物理系）
Traditionally, nonlinear inversion, direct inversion, or wave estimation methods have been used for reconstructing images from MRE displacement data. In this work, we propose a convolutional neural network architecture that can map MRE displacement data directly into elastograms, circumventing the costly and computationally intensive classical approaches. In addition to the mean squared error reconstruction objective, we also introduce a secondary loss inspired by the MRE mechanical models for training the neural network. Our network is demonstrated to be effective for generating MRE images th…
