{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/iterative-pet-image-reconstruction-using","title":"Iterative PET Image Reconstruction Using Convolutional Neural Network Representation","arxiv_id":"1710.03344","date":"2017-10-09","proceeding":null,"authors":["Kuang Gong","Jiahui Guan","Kyungsang Kim","Xuezhu Zhang","Georges El Fakhri","Jinyi Qi","Quanzheng Li"],"abstract":"PET image reconstruction is challenging due to the ill-poseness of the\ninverse problem and limited number of detected photons. Recently deep neural\nnetworks have been widely and successfully used in computer vision tasks and\nattracted growing interests in medical imaging. In this work, we trained a deep\nresidual convolutional neural network to improve PET image quality by using the\nexisting inter-patient information. An innovative feature of the proposed\nmethod is that we embed the neural network in the iterative reconstruction\nframework for image representation, rather than using it as a post-processing\ntool. We formulate the objective function as a constraint optimization problem\nand solve it using the alternating direction method of multipliers (ADMM)\nalgorithm. Both simulation data and hybrid real data are used to evaluate the\nproposed method. Quantification results show that our proposed iterative neural\nnetwork method can outperform the neural network denoising and conventional\npenalized maximum likelihood methods.","url_abs":"http://arxiv.org/abs/1710.03344v1","url_pdf":"http://arxiv.org/pdf/1710.03344v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"iterative-pet-image-reconstruction-using","repo_url":"https://github.com/zgongkuang/IterativeCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}