文献类型： 会议论文
第一作者： Claire Rossignol
作者： Claire Rossignol 1 ; Florent Sureau 2 ; Emilie Chouzenoux 1 ; Claude Comtat 2 ; Jean-Christophe Pesquet 1 ;
作者机构： 1.CVN, Inria, CentraleSupélec, University Paris Saclay, France
2.BioMaps, Université Paris-Saclay, CEA, CNRS, Inserm, SHFJ, France
关键词： Neurology;Inverse problems;Heuristic algorithms;Graphics processing units;Programming;Oncology;Positron emission tomography
会议名称： IEEE International Conference on Image Processing
主办单位：
页码： 1736-1740
摘要： Positron emission tomography (PET) is a quantitative imaging modality widely used in oncology, neurology, and pharmacology. The data acquired by a PET scanner correspond to projections of the concentration activity, assumed to follow a Poisson distribution. The reconstruction of images from tomographic projections corrupted by Poisson noise is a challenging ill-posed large-scale inverse problem. Several available solvers use the majorization-minimization (MM) principle, though relying on various construction strategies with a lack of unifying framework. This work fills the gap by introducing the concept of Bregman majorization. This leads to a unified view of MM-based methods for image reconstruction in the presence of Poisson noise. From this general approach, we exhibit three algorithmic solutions and compare their computational efficiency on a problem of dynamic PET image reconstruction, either using GPU or CPU processing.
分类号： tp3
- 相关文献
[1]Deep Equilibrium for Hyperparameter Estimation in Dynamic PET Reconstruction. A. Chazottes,É. Chouzenoux,J.-C. Pesquet,F. Sureau. 2024
[2]Numba-accelerated parameter estimation for artificial pancreas applications. Máté Siket,Lehel Dénes-Fazakas,Levente Kovács,Gy?rgy Eigner. 2022
[3]Approaches to a broad range of high performance PDT sensitizers. Antonio M. d'A. Rocha Gonsalvesa,Armenio C. Serraa,Marta Pineiroa,M. Filomena Botelhob. 2009
[4]EEG Source Analysis with a Convolutional Neural Network and Finite Element Analysis. Thanos Delatolas,Marios Antonakakis,Vangelis Sakkalis,Carsten H. Wolters,Michalis Zervakis. 2023
[5]Improving Automatic Segmentation of lymphoma with Additional Medical Knowledge Priors. Liangchen Liu,Benjamin Hou,Manas Kumar Nag,Jianfei Liu,Navid Hasani,Thomas C. Shen,Yingying Zhu,Babak Saboury,Jing Xiao,Ronald M. Summers. 2023
[6]Scatter Correction for Positron Emission Mammography using an Estimation of Trues Method Approach. Luis Martins,Nuno C. Ferreira,Francisco Caramelo. 2013
[7]MRI-guided PET reconstruction using a convergent plug-and-play approach. M. Savanier,V. Gautier,N. J. Pinton,C. Comtat,F. Sureau. 2024
[8]Research and Development of Decision Support System for Regional Agricultural Development Programming. Jiangang Liu,Yongchang Wu,Tingting Tao,Qingquan Chu. 2013
[9]Research and Development of Decision Support System for Regional Agricultural Development Programming. Jiangang Liu,Yongchang Wu,Tingting Tao,Qingquan Chu. 2013
[10]Review of Reinforcement Learning-Based Control Algorithms in Artificial Pancreas Systems for Diabetes Mellitus Management. Lehel Dénes-Fazakas,Gy?z? Dénes Fazakas,Gy?rgy Eigner,Levente Kovács,László Szilágyi. 2024
[11]Online Hyper-evolution of Controllers in Multirobot Systems. Fernando Silva,Luís Correia,Anders Lyhne Christensen. 2016
[12]Long Image Time Series for Crop Extraction Based on the Automatically Generated Samples Algorithm. Nan Jia,Yinshuai Li,Andrés Vi?a,Jie Cheng,Yue Dou,Qian Song,Liuyue He,Jianguo Liu. 2023
[13]Nature Inspired Optimization Algorithms in Fractional Order Controller Design. Eva-H. Dulf,Alexandru George Berciu,Lehel Dénes-Fazakas,Levente Kovacs. 2024
[14]Graph Neural Network-Based Real-Time 3D Tracking for Micro-Agent Control. Yuxin Jin,Franco Pinan Basualdo,Antonio Marino,Yongfeng Mei,Paolo Robuffo Giordano,Claudio Pacchierotti,Sarthak Misra. 2024
[15]Centimeter-Scale Submarine Robot for Monitoring Coral Reef Ecosystem. Zongze Li,Yi Zhang,Shujing He,Xiyu Zhu,Tanyong Wei,Chengzhi Hu. 2024
作者其他论文 更多>>
-
On The Local Geometry of the Pet Reconstruction Problem
作者：Ramy Merabet;Florent Sureau;Alain Trouvé
关键词：Geometry;Deep learning;Uncertainty;Three-dimensional displays;Perturbation methods;Biological system modeling;Phantoms
-
Learning with Fixed Point Condition for Convergent PNP PET Reconstruction
作者：Marion Savanier;Claude Comtat;Florent Sureau
关键词：Deep learning;Training;Image quality;Reconstruction algorithms;Convolutional neural networks;Image reconstruction;Convergence
