Deep Kernel Representation for Image Reconstruction in PET.

Published on Oct 4, 2021in arXiv: Image and Video Processing
Siqi Li7
Estimated H-index: 7
(UC Davis: University of California, Davis),
Guobao Wang19
Estimated H-index: 19
(UC Davis: University of California, Davis)
Image reconstruction for positron emission tomography (PET) is challenging because of the ill-conditioned tomographic problem and low counting statistics. Kernel methods address this challenge by using kernel representation to incorporate image prior information in the forward model of iterative PET image reconstruction. Existing kernel methods construct the kernels commonly using an empirical process, which may lead to suboptimal performance. In this paper, we describe the equivalence between the kernel representation and a trainable neural network model. A deep kernel method is proposed by exploiting deep neural networks to enable an automated learning of an optimized kernel model. The proposed method is directly applicable to single subjects. The training process utilizes available image prior data to seek the best way to form a set of robust kernels optimally rather than empirically. The results from computer simulations and a real patient dataset demonstrate that the proposed deep kernel method can outperform existing kernel method and neural network method for dynamic PET image reconstruction.
📖 Papers frequently viewed together
1 Author (廖家德)
2015AISTATS: International Conference on Artificial Intelligence and Statistics
5 Authors (Shaogang Ren, ..., Xiaoning Qian)
#1Siqi Li (UC Davis: University of California, Davis)H-Index: 7
#2Guobao Wang (UC Davis: University of California, Davis)H-Index: 19
Combined use of PET and dual-energy CT provides complementary information for multi-parametric imaging. PET-enabled dual-energy CT combines a low-energy X-ray CT image with a high-energy -ray CT (G...
This article reviews the use of a sub-discipline of artificial intelligence (AI), deep learning, for the reconstruction of images in positron emission tomography (PET). Deep learning can be used either directly or as a component of conventional reconstruction, in order to reconstruct images from noisy PET data. The review starts with an overview of conventional PET image reconstruction and then covers the principles of general linear and convolution-based mappings from data to images, and procee...
#1Kuang Gong (Harvard University)H-Index: 15
#2Ciprian Catana (Harvard University)H-Index: 43
Last. Quanzheng Li (Harvard University)H-Index: 33
view all 4 authors...
Recently, deep neural networks have been widely and successfully applied in computer vision tasks and have attracted growing interest in medical imaging. One barrier for the application of deep neural networks to medical imaging is the need for large amounts of prior training pairs, which is not always feasible in clinical practice. This is especially true for medical image reconstruction problems, where raw data are needed. Inspired by the deep image prior framework, in this paper, we proposed ...
#1Ida Häggström (MSK: Memorial Sloan Kettering Cancer Center)H-Index: 6
#2C. Ross SchmidtleinH-Index: 15
Last. Thomas J. Fuchs (MSK: Memorial Sloan Kettering Cancer Center)H-Index: 28
view all 4 authors...
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 fi...
#1Guobao Wang (UC Davis: University of California, Davis)H-Index: 19
Current clinical dynamic PET has an effective temporal resolution of 5-10 seconds, which can be adequate for traditional compartmental modeling but is inadequate for exploiting the benefit of more advanced tracer kinetic modeling for characterization of diseases (e.g., cancer and heart disease). There is a need to improve dynamic PET to allow fine temporal sampling of 1-2 seconds. However, the reconstruction of these short-time frames from tomographic data is extremely challenging as the count l...
Jun 18, 2018 in CVPR (Computer Vision and Pattern Recognition)
#1Xiaolong Wang (CMU: Carnegie Mellon University)H-Index: 86
#2Ross Girshick (Facebook)H-Index: 86
Last. Kaiming He (Facebook)H-Index: 80
view all 4 authors...
Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method [4] in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On ...
Jun 12, 2017 in NeurIPS (Neural Information Processing Systems)
#1Ashish Vaswani (Google)H-Index: 32
#2Noam Shazeer (Google)H-Index: 32
Last. Illia Polosukhin (Google)H-Index: 9
view all 8 authors...
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being mor...
#1Will Hutchcroft (UC Davis: University of California, Davis)H-Index: 3
#2Guobao Wang (UC Davis: University of California, Davis)H-Index: 19
Last. Jinyi Qi (UC Davis: University of California, Davis)H-Index: 53
view all 5 authors...
This paper extends the kernel method that was proposed previously for dynamic PET reconstruction, to incorporate anatomical side information into the PET reconstruction model. In contrast to existing methods that incorporate anatomical information using a penalized likelihood framework, the proposed method incorporates this information in the simpler maximum likelihood (ML) formulation and is amenable to ordered subsets. The new method also does not require any segmentation of the anatomical ima...
#1Philip Novosad (Montreal Neurological Institute and Hospital)H-Index: 1
#2Andrew J. Reader ('KCL': King's College London)H-Index: 32
Recent advances in dynamic positron emission tomography (PET) reconstruction have demonstrated that it is possible to achieve markedly improved end-point kinetic parameter maps by incorporating a temporal model of the radiotracer directly into the reconstruction algorithm. In this work we have developed a highly constrained, fully dynamic PET reconstruction algorithm incorporating both spectral analysis temporal basis functions and spatial basis functions derived from the kernel method applied t...
#1Guobao Wang (UC Davis: University of California, Davis)H-Index: 19
#2Jinyi Qi (UC Davis: University of California, Davis)H-Index: 53
Image reconstruction from low-count positron emission tomography (PET) projection data is challenging because the inverse problem is ill-posed. Prior information can be used to improve image quality. Inspired by the kernel methods in machine learning, this paper proposes a kernel based method that models PET image intensity in each pixel as a function of a set of features obtained from prior information. The kernel-based image model is incorporated into the forward model of PET projection data a...
Cited By0
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.