{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:08:04Z","timestamp":1767262084791,"version":"build-2065373602"},"reference-count":18,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T00:00:00Z","timestamp":1637712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>We have adapted, implemented and trained the Learned Primal Dual algorithm suggested by Adler and \u00d6ktem and evaluated its performance in reconstructing projection data from our PET scanner. Learned Primal Dual reconstructions are compared to Maximum Likelihood Expectation Maximisation (MLEM) reconstructions. Different strategies for training are also compared. Whenever the noise level of the data to reconstruct is sufficiently represented in the training set, the Learned Primal Dual algorithm performs well on the recovery of the activity concentrations and on noise reduction as compared to MLEM. The algorithm is also shown to be robust against the appearance of artefacts, even when the images that are to be reconstructed present features were not present in the training set. Once trained, the algorithm reconstructs images in few seconds or less.<\/jats:p>","DOI":"10.3390\/jimaging7120248","type":"journal-article","created":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T23:22:28Z","timestamp":1638314548000},"page":"248","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Learned Primal Dual Reconstruction for PET"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5155-2567","authenticated-orcid":false,"given":"Alessandro","family":"Guazzo","sequence":"first","affiliation":[{"name":"Division of Biomedical Imaging, KTH Royal Institute of Technology, 10044 Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2036-1060","authenticated-orcid":false,"given":"Massimiliano","family":"Colarieti-Tosti","sequence":"additional","affiliation":[{"name":"Division of Biomedical Imaging, KTH Royal Institute of Technology, 10044 Stockholm, Sweden"},{"name":"Department of Clinical Science, Intervention and Technology, Karolinska Institutet, 17177 Stockholm, Sweden"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/79.560323","article-title":"Positron-emission tomography","volume":"14","author":"Ollinger","year":"1997","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bailey, D.L., Karp, J.S., and Surti, S. (2005). Physics and instrumentation in PET. Positron Emission Tomography, Springer.","DOI":"10.1007\/1-84628-007-9_2"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TMI.1982.4307558","article-title":"Maximum likelihood reconstruction for emission tomography","volume":"1","author":"Shepp","year":"1982","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_4","first-page":"306","article-title":"EM reconstruction algorithms for emission and transmission tomography","volume":"8","author":"Lange","year":"1984","journal-title":"J. Comput. Assist. Tomogr."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1080\/01621459.1985.10477119","article-title":"A statistical model for positron emission tomography","volume":"80","author":"Vardi","year":"1985","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1109\/42.363108","article-title":"Accelerated image reconstruction using ordered subsets of projection data","volume":"13","author":"Hudson","year":"1994","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1023\/A:1008946426658","article-title":"Statistical approaches in quantitative positron emission tomography","volume":"10","author":"Leahy","year":"2000","journal-title":"Stat. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Defrise, M., and Kinahan, P. (1998). Data acquisition and image reconstruction for 3D PET. The Theory and Practice of 3D PET, Springer.","DOI":"10.1007\/978-94-017-3475-2_2"},{"key":"ref_9","first-page":"110720O","article-title":"MAPEM-Net: An unrolled neural network for fully 3D PET image reconstruction","volume":"Volume 11072","author":"Gong","year":"2019","journal-title":"Proceedings of the 15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1109\/TMI.2018.2869871","article-title":"Iterative PET image reconstruction using convolutional neural network representation","volume":"38","author":"Gong","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"124007","DOI":"10.1088\/1361-6420\/aa9581","article-title":"Solving ill-posed inverse problems using iterative deep neural networks","volume":"33","author":"Adler","year":"2017","journal-title":"Inverse Probl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1109\/TMI.2018.2799231","article-title":"Learned primal-dual reconstruction","volume":"37","author":"Adler","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1948","DOI":"10.2967\/jnumed.115.157677","article-title":"A promising future: Comparable imaging capability of MRI-compatible silicon photomultiplier and conventional photosensor preclinical PET systems","volume":"56","author":"Krizsan","year":"2015","journal-title":"J. Nucl. Med."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Imrek, J., Hegyesi, G., Kalinka, G., Kir\u00e1ly, B., Moln\u00e1r, J., Nagy, F., Valasty\u00e1n, I., Balkay, L., and Szab\u00f3, Z. (November, January 27). Evaluation detector module of the miniPET-3 small animal PET scanner. Proceedings of the 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS\/MIC), Anaheim, CA, USA.","DOI":"10.1109\/NSSMIC.2012.6551870"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1088\/0031-9155\/57\/4\/867","article-title":"STIR: Software for tomographic image reconstruction release 2","volume":"57","author":"Thielemans","year":"2012","journal-title":"Phys. Med. Biol."},{"key":"ref_16","unstructured":"ODL (2018, September 09). Operator Discretization Library. Available online: https:\/\/github.com\/odlgroup\/odl."},{"key":"ref_17","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_18","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/12\/248\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:35:01Z","timestamp":1760168101000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/12\/248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,24]]},"references-count":18,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["jimaging7120248"],"URL":"https:\/\/doi.org\/10.3390\/jimaging7120248","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2021,11,24]]}}}