{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:41:59Z","timestamp":1781534519481,"version":"3.54.5"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>More widespread use of positron emission tomography (PET) imaging is limited by its high cost and radiation dose. Reductions in PET scan time or radiotracer dosage typically degrade diagnostic image quality (DIQ). Deep-learning-based reconstruction may improve DIQ, but such methods have not been clinically evaluated in a realistic multicenter, multivendor environment. In this study, we evaluated the performance and generalizability of a deep-learning-based image-quality enhancement algorithm applied to fourfold reduced-count whole-body PET in a realistic clinical oncologic imaging environment with multiple blinded readers, institutions, and scanner types. We demonstrate that the low-count-enhanced scans were noninferior to the standard scans in DIQ (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.05) and overall diagnostic confidence (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001) independent of the underlying PET scanner used. Lesion detection for the low-count-enhanced scans had a high patient-level sensitivity of 0.94 (0.83\u20130.99) and specificity of 0.98 (0.95\u20130.99). Interscan kappa agreement of 0.85 was comparable to intrareader (0.88) and pairwise inter-reader agreements (maximum of 0.72). SUV quantification was comparable in the reference regions and lesions (lowest <jats:italic>p<\/jats:italic>-value=0.59) and had high correlation (lowest CCC\u2009=\u20090.94). Thus, we demonstrated that deep learning can be used to restore diagnostic image quality and maintain SUV accuracy for fourfold reduced-count PET scans, with interscan variations in lesion depiction, lower than intra- and interreader variations. This method generalized to an external validation set of clinical patients from multiple institutions and scanner types. Overall, this method may enable either dose or exam-duration reduction, increasing safety and lowering the cost of PET imaging.<\/jats:p>","DOI":"10.1038\/s41746-021-00497-2","type":"journal-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T10:40:23Z","timestamp":1629715223000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["Low-count whole-body PET with deep learning in a multicenter and externally validated study"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3667-6796","authenticated-orcid":false,"given":"Akshay S.","family":"Chaudhari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Mittra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5579-6825","authenticated-orcid":false,"given":"Guido A.","family":"Davidzon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praveen","family":"Gulaka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harsh","family":"Gandhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Brown","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shyam","family":"Srinivas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enhao","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5781-8848","authenticated-orcid":false,"given":"Greg","family":"Zaharchuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9455-2484","authenticated-orcid":false,"given":"Hossein","family":"Jadvar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,8,23]]},"reference":[{"key":"497_CR1","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.3390\/cancers6041821","volume":"6","author":"A Gallamini","year":"2014","unstructured":"Gallamini, A., Zwarthoed, C. & Borra, A. Positron emission tomography (PET) in oncology. Cancers 6, 1821\u20131889 (2014).","journal-title":"Cancers"},{"key":"497_CR2","doi-asserted-by":"crossref","unstructured":"Zasadny, K. R. & Wahl, R. L. Standardized uptake values of normal tissues at PET with 2-[fluorine-18]-fluoro-2-deoxy-D-glucose: variations with body weight and a method for correction. Radiology 189, 847\u2013950 (1993).","DOI":"10.1148\/radiology.189.3.8234714"},{"key":"497_CR3","first-page":"623","volume":"32","author":"L Strauss","year":"1991","unstructured":"Strauss, L. & Conti, P. S. The applications of PET in clinical oncology. J. Nucl. Med. 32, 623\u2013650 (1991).","journal-title":"J. Nucl. Med."},{"key":"497_CR4","first-page":"1431","volume":"45","author":"JA Thie","year":"2004","unstructured":"Thie, J. A. Understanding the standardized uptake value, its methods, and implications for usage. J. Nucl. Med. 45, 1431\u20131434 (2004).","journal-title":"J. Nucl. Med."},{"key":"497_CR5","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.1002\/jmri.26000","volume":"48","author":"KT Chen","year":"2018","unstructured":"Chen, K. T. et al. MR-assisted PET motion correction in simultaneous PET\/MRI studies of dementia subjects. J. Magn. Reson. Imaging 48, 1288\u20131296 (2018).","journal-title":"J. Magn. Reson. Imaging"},{"key":"497_CR6","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s13246-011-0109-x","volume":"34","author":"J Callahan","year":"2011","unstructured":"Callahan, J., Binns, D., Dunn, L. & Kron, T. Motion effects on SUV and lesion volume in 3D and 4D PET scanning. Australas. Phys. Eng. Sci. Med. 34, 489\u2013495 (2011).","journal-title":"Australas. Phys. Eng. Sci. Med."},{"key":"497_CR7","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1093\/jnci\/djy104","volume":"111","author":"JM Meulepas","year":"2019","unstructured":"Meulepas, J. M. et al. Radiation exposure from pediatric CT scans and subsequent cancer risk in the Netherlands. J. Natl Cancer Inst. 111, 256\u2013263 (2019).","journal-title":"J. Natl Cancer Inst."},{"key":"497_CR8","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1016\/S0140-6736(12)60815-0","volume":"380","author":"MS Pearce","year":"2012","unstructured":"Pearce, M. S. et al. Radiation exposure from CT scans in childhood and subsequent risk of leukaemia and brain tumours: a retrospective cohort study. Lancet 380, 499\u2013505 (2012).","journal-title":"Lancet"},{"key":"497_CR9","first-page":"44","volume":"33","author":"FO Roberts","year":"2005","unstructured":"Roberts, F. O. et al. Radiation dose to PET technologists and strategies to lower occupational exposure. J. Nucl. Med. Technol. 33, 44\u201347 (2005).","journal-title":"J. Nucl. Med. Technol."},{"key":"497_CR10","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1148\/radiol.2511081300","volume":"251","author":"B Huang","year":"2009","unstructured":"Huang, B., Law, M. W. M. & Khong, P. L. Whole-body PET\/CT scanning: estimation of radiation dose and cancer risk. Radiology 251, 166\u2013174 (2009).","journal-title":"Radiology"},{"key":"497_CR11","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1038\/s41591-019-0447-x","volume":"25","author":"D Ardila","year":"2019","unstructured":"Ardila, D. et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat. Med. 25, 954\u2013961 (2019).","journal-title":"Nat. Med."},{"key":"497_CR12","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","volume":"577","author":"SM McKinney","year":"2020","unstructured":"McKinney, S. M. et al. International evaluation of an AI system for breast cancer screening. Nature 577, 89\u201394 (2020).","journal-title":"Nature"},{"key":"497_CR13","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","volume":"25","author":"G Campanella","year":"2019","unstructured":"Campanella, G. et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat. Med. 25, 1301\u20131309 (2019).","journal-title":"Nat. Med."},{"key":"497_CR14","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115\u2013118 (2017).","journal-title":"Nature"},{"key":"497_CR15","doi-asserted-by":"publisher","first-page":"2524","DOI":"10.1109\/TMI.2017.2715284","volume":"36","author":"H Chen","year":"2017","unstructured":"Chen, H. et al. Low-Dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans. Med. Imaging 36, 2524\u20132535 (2017).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"497_CR16","doi-asserted-by":"publisher","first-page":"2139","DOI":"10.1002\/mrm.27178","volume":"80","author":"AS Chaudhari","year":"2018","unstructured":"Chaudhari, A. S. et al. Super-resolution musculoskeletal MRI using deep learning. Magn. Reson. Med. 80, 2139\u20132154 (2018).","journal-title":"Magn. Reson. Med."},{"key":"497_CR17","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/s10278-018-0150-3","volume":"32","author":"S Kaplan","year":"2019","unstructured":"Kaplan, S. & Zhu, Y. Full-dose PET image estimation from low-dose PET image using deep learning: a pilot study. J. Digit. Imaging 32, 773\u2013778 (2019).","journal-title":"J. Digit. Imaging"},{"key":"497_CR18","doi-asserted-by":"publisher","first-page":"5301","DOI":"10.1118\/1.4928400","volume":"42","author":"J Kang","year":"2015","unstructured":"Kang, J. et al. Prediction of standard-dose brain PET image by using MRI and low-dose brain [18F]FDG PET images. Med. Phys. 42, 5301\u20135309 (2015).","journal-title":"Med. Phys."},{"key":"497_CR19","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1148\/radiol.2018180940","volume":"290","author":"KT Chen","year":"2019","unstructured":"Chen, K. T. et al. Ultra-low-dose 18F-florbetaben amyloid PET imaging using deep learning with multi-contrast MRI inputs. Radiology 290, 649\u2013656 (2019).","journal-title":"Radiology"},{"key":"497_CR20","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1016\/j.neuroimage.2018.03.045","volume":"174","author":"Y Wang","year":"2018","unstructured":"Wang, Y. et al. 3D conditional generative adversarial networks for high-quality PET image estimation at low dose. Neuroimage 174, 550\u2013562 (2018).","journal-title":"Neuroimage"},{"key":"497_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Y. R. (Joyce) et al. Artificial intelligence enables whole-body positron emission tomography scans with minimalradiation exposure. Eur. J. Nucl. Med. Mol. Imaging Aug; 48:2771-2781. (2021).","DOI":"10.1007\/s00259-021-05197-3"},{"key":"497_CR22","doi-asserted-by":"crossref","unstructured":"Recht M. P. et al. Using Deep Learning to Accelerate Knee MRI at 3 T: Results of an Interchangeability Study. AJR Am J Roentgenol 215:1421-1429 (2020).","DOI":"10.2214\/AJR.20.23313"},{"key":"497_CR23","doi-asserted-by":"crossref","unstructured":"Chaudhari, A. S. et al. Diagnostic accuracy of quantitative multi-contrast 5-minute knee MRI using prospective artificial intelligence image quality enhancement title. Am. J. Roentgenol. 216, 1614\u20131625 (2021).","DOI":"10.2214\/AJR.20.24172"},{"key":"497_CR24","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.2967\/jnumed.112.103861","volume":"53","author":"G Akamatsu","year":"2012","unstructured":"Akamatsu, G. et al. Improvement in PET\/CT image quality with a combination of point-spread function and time-of-flight in relation to reconstruction parameters. J. Nucl. Med. 53, 1716\u20131722 (2012).","journal-title":"J. Nucl. Med."},{"key":"497_CR25","first-page":"5948","volume":"2017","author":"B Neyshabur","year":"2017","unstructured":"Neyshabur, B., Bhojanapalli, S., McAllester, D. & Srebro, N. Exploring generalization in deep learning. Adv. Neural Inf. Process. Syst. 2017, 5948\u20135957 (2017).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"497_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pmed.1002683","volume":"15","author":"JR Zech","year":"2018","unstructured":"Zech, J. R. et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med. 15, 1\u201317 (2018).","journal-title":"PLoS Med."},{"key":"497_CR27","doi-asserted-by":"publisher","unstructured":"Paschali, M., Conjeti, S., Navarro, F. & Navab, N. Generalizability vs. robustness: investigating medical imaging networks using adversarial examples. Med. Image Comput. Comput. Assist. Interv. https:\/\/doi.org\/10.1007\/978-3-030-00928-1_56 (2018).","DOI":"10.1007\/978-3-030-00928-1_56"},{"key":"497_CR28","doi-asserted-by":"crossref","unstructured":"Bluemke, D. A. et al. assessing radiology research on artificial intelligence: a brief guide for authors, reviewers, and readers\u2014from the radiology editorial board. Radiology. 294, 487\u2013489 (2019).","DOI":"10.1148\/radiol.2019192515"},{"key":"497_CR29","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.1002\/sim.1783","volume":"23","author":"SA Julious","year":"2004","unstructured":"Julious, S. A. Sample sizes for clinical trials with Normal data. Stat. Med. 23, 1921\u20131986 (2004).","journal-title":"Stat. Med."},{"key":"497_CR30","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1148\/radiol.2017162305","volume":"286","author":"T Sekine","year":"2018","unstructured":"Sekine, T. et al. Reduction of 18 F-FDG dose in clinical PET\/MR imaging by using silicon photomultiplier detectors. Radiology 286, 249\u2013259 (2018).","journal-title":"Radiology"},{"key":"497_CR31","first-page":"15","volume":"19","author":"S Gatidis","year":"2016","unstructured":"Gatidis, S. et al. Towards tracer dose reduction in PET studies: simulation of dose reduction by retrospective randomized undersampling of list-mode data. Hell. J. Nucl. Med. 19, 15\u201318 (2016).","journal-title":"Hell. J. Nucl. Med."},{"key":"497_CR32","doi-asserted-by":"publisher","first-page":"1699","DOI":"10.2967\/jnumed.116.184440","volume":"58","author":"F Seith","year":"2017","unstructured":"Seith, F. et al. Simulation of tracer dose reduction in 18F-FDG PET\/MRI: effects on oncologic reading, image quality, and artifacts. J. Nucl. Med. 58, 1699\u20131705 (2017).","journal-title":"J. Nucl. Med."},{"key":"497_CR33","doi-asserted-by":"publisher","first-page":"399","DOI":"10.2967\/jnumed.116.177592","volume":"58","author":"JD Schaefferkoetter","year":"2017","unstructured":"Schaefferkoetter, J. D. et al. Quantitative accuracy and lesion detectability of low-dose 18F-FDG PET for lung cancer screening. J. Nucl. Med. 58, 399\u2013405 (2017).","journal-title":"J. Nucl. Med."},{"key":"497_CR34","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1002\/jmri.27331","volume":"54","author":"AS Chaudhari","year":"2021","unstructured":"Chaudhari, A. S. et al. Prospective deployment of deep learning in MRI: a framework for important considerations, challenges, and recommendations for best practices. J. Magn. Reson. Imaging 54, 357\u2013371 (2021).","journal-title":"J. Magn. Reson. Imaging"},{"key":"497_CR35","doi-asserted-by":"crossref","unstructured":"Chen, K. T. et al. True ultra-low-dose amyloid PET\/MRI enhanced with deep learning for clinical interpretation. Eur. J. Nucl. Med. Mol. Imaging. 48, 2416\u20132425. (2021).","DOI":"10.1007\/s00259-020-05151-9"},{"key":"497_CR36","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: convolutional networks for biomedical image segmentation. Med. Image Comput. Comput. Assist. Interv. Lecture Notes in Computer Science, vol 9351. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"497_CR37","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1007\/s12350-015-0069-8","volume":"22","author":"S Gholami","year":"2015","unstructured":"Gholami, S., Salavati, A., Houshmand, S., Werner, T. J. & Alavi, A. Assessment of atherosclerosis in large vessel walls: a comprehensive review of FDG-PET\/CT image acquisition protocols and methods for uptake quantification. J. Nucl. Cardiol. 22, 468\u2013479 (2015).","journal-title":"J. Nucl. Cardiol."},{"key":"497_CR38","doi-asserted-by":"publisher","first-page":"122","DOI":"10.2967\/jnumed.108.057307","volume":"50","author":"RL Wahl","year":"2009","unstructured":"Wahl, R. L., Jacene, H., Kasamon, Y. & Lodge, M. A. From RECIST to PERCIST: evolving considerations for PET response criteria in solid tumors. J. Nucl. Med. 50, 122\u2013151 (2009).","journal-title":"J. Nucl. Med."},{"key":"497_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0187995","volume":"12","author":"MA Ahlman","year":"2017","unstructured":"Ahlman, M. A. et al. Internal tissue references for 18Fluorodeoxyglucose vascular inflammation imaging: Implications for cardiovascular risk stratification and clinical trials. PLoS ONE 12, 1\u201312 (2017).","journal-title":"PLoS ONE"},{"key":"497_CR40","doi-asserted-by":"publisher","first-page":"1500","DOI":"10.1007\/s00247-017-3888-8","volume":"47","author":"MJ Paldino","year":"2017","unstructured":"Paldino, M. J. et al. Comparison of the diagnostic accuracy of PET\/MRI to PET\/CT-acquired FDG brain exams for seizure focus detection: a prospective study. Pediatr. Radiol. 47, 1500\u20131507 (2017).","journal-title":"Pediatr. Radiol."},{"key":"497_CR41","first-page":"1342","volume":"46","author":"U Nestle","year":"2005","unstructured":"Nestle, U. et al. Comparison of different methods for delineation of 18F-FDG PET-positive tissue for target volume definition in radiotherapy of patients with non-Small cell lung cancer. J. Nucl. Med. 46, 1342\u20131348 (2005).","journal-title":"J. Nucl. Med."}],"updated-by":[{"DOI":"10.1038\/s41746-021-00512-6","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2021,9,14]],"date-time":"2021-09-14T00:00:00Z","timestamp":1631577600000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00497-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00497-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00497-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T18:58:15Z","timestamp":1670093895000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00497-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["497"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00497-2","relation":{"correction":[{"id-type":"doi","id":"10.1038\/s41746-021-00512-6","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,23]]},"assertion":[{"value":"23 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2021","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41746-021-00512-6","URL":"https:\/\/doi.org\/10.1038\/s41746-021-00512-6","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A.C. is affiliated with Stanford University and Subtle Medical. This work was fully conducted under a consulting relationship for Subtle Medical where A.C. is a shareholder. Activities not related to the present article: consulting services to Skope MR, Culvert Engineering, Edge Analytics, Image Analysis Group, ICM, and Chondrometrics GmbH; and shareholder in LVIS Corp. and Brain Key. E.M. has provided consulting services to Ipsen, Curium, and AAA. G.D. has provided consulting services to Genentech Inc. and receives research support from Kheiron Medical Technologies Inc., Dimensional Mechanics Inc., and GE Healthcare. P.G., H.G., and T.Z. are employees and shareholders of Subtle Medical. A.B. has no disclosures to report. S.S. has provided consulting services to Subtle Medical. Activities not related to the present article: disclosed employment as chief medical officer for approximately one year with Sirtex Medical Inc. E.G. is a cofounder and shareholder of Subtle Medical. G.Z. is a cofounder and shareholder of Subtle Medical. Activities not related to the present article: institutional grant from GE Healthcare. H.J. has received research support from Subtle Medical. Intellectual property: E.G. and G.Z. are coinventors of the following patent \u201cDose Reduction For Medical Imaging Using Deep Convolutional Neural Networks\u201d, with specific details below: Application Number: PCT\/US2018\/029103 Publication Number: WO\/2018\/200493 Applicant: The Board of Trustees of The Leland Stanford Junior University Inventors: Greg Zaharchuk, John M. Pauly and Enhao Gong Aspect Covered: The technology described in this patent was used to perform the low-dose PET-image enhancement described in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"127"}}