{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:50:38Z","timestamp":1792601438954,"version":"4.5.0"},"reference-count":56,"publisher":"IOP Publishing","issue":"15","license":[{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100007923","name":"University of Wisconsin Carbone Cancer Center","doi-asserted-by":"crossref","award":["P30 CA014520"],"award-info":[{"award-number":["P30 CA014520"]}],"id":[{"id":"10.13039\/100007923","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100014039","name":"DOD Prostate Cancer Research Program","doi-asserted-by":"crossref","award":["W81XWH-17-0020"],"award-info":[{"award-number":["W81XWH-17-0020"]}],"id":[{"id":"10.13039\/100014039","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2024,8,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>\n                  <jats:italic>Objective.<\/jats:italic> Deep learning models that aid in medical image assessment tasks must be both accurate and reliable to be deployed within clinical settings. While deep learning models have been shown to be highly accurate across a variety of tasks, measures that indicate the reliability of these models are less established. Increasingly, uncertainty quantification (UQ) methods are being introduced to inform users on the reliability of model outputs. However, most existing methods cannot be augmented to previously validated models because they are not post hoc, and they change a model\u2019s output. In this work, we overcome these limitations by introducing a novel post hoc UQ method, termed <jats:italic>Local Gradients UQ<\/jats:italic>, and demonstrate its utility for deep learning-based metastatic disease delineation. <jats:italic>Approach.<\/jats:italic> This method leverages a trained model\u2019s localized gradient space to assess sensitivities to trained model parameters. We compared the Local Gradients UQ method to non-gradient measures defined using model probability outputs. The performance of each uncertainty measure was assessed in four clinically relevant experiments: (1) response to artificially degraded image quality, (2) comparison between matched high- and low-quality clinical images, (3) false positive (FP) filtering, and (4) correspondence with physician-rated disease likelihood. <jats:italic>Main results.<\/jats:italic> (1) Response to artificially degraded image quality was enhanced by the Local Gradients UQ method, where the median percent difference between matching lesions in non-degraded and most degraded images was consistently higher for the Local Gradients uncertainty measure than the non-gradient uncertainty measures (e.g. 62.35% vs. 2.16% for additive Gaussian noise). (2) The Local Gradients UQ measure responded better to high- and low-quality clinical images (<jats:italic>p<\/jats:italic> &lt; 0.05 vs <jats:italic>p<\/jats:italic> &gt; 0.1 for both non-gradient uncertainty measures). (3) FP filtering performance was enhanced by the Local Gradients UQ method when compared to the non-gradient methods, increasing the area under the receiver operating characteristic curve (ROC AUC) by 20.1% and decreasing the false positive rate by 26%. (4) The Local Gradients UQ method also showed more favorable correspondence with physician-rated likelihood for malignant lesions by increasing ROC AUC for correspondence with physician-rated disease likelihood by 16.2%. <jats:italic>Significance<\/jats:italic>. In summary, this work introduces and validates a novel gradient-based UQ method for deep learning-based medical image assessments to enhance user trust when using deployed clinical models.<\/jats:p>","DOI":"10.1088\/1361-6560\/ad611d","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T23:23:47Z","timestamp":1720567427000},"page":"155015","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Uncertainty quantification via localized gradients for deep learning-based medical image assessments"],"prefix":"10.1088","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3326-1854","authenticated-orcid":true,"given":"Brayden","family":"Schott","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitry","family":"Pinchuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6965-0448","authenticated-orcid":false,"given":"Victor","family":"Santoro-Fernandes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3409-7771","authenticated-orcid":false,"given":"\u017dan","family":"Klane\u010dek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0738-7485","authenticated-orcid":false,"given":"Luciano","family":"Rivetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4525-1327","authenticated-orcid":true,"given":"Alison","family":"Deatsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9744-7105","authenticated-orcid":false,"given":"Scott","family":"Perlman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3479-4323","authenticated-orcid":false,"given":"Yixuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2192-2931","authenticated-orcid":true,"given":"Robert","family":"Jeraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,7,19]]},"reference":[{"key":"pmbad611dbib1","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-87735-4_12","article-title":"Confidence-based out-of-distribution detection: a comparative study and analysis","volume":"vol 12959","author":"Berger","year":"2021"},{"key":"pmbad611dbib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102680","article-title":"The Liver Tumor Segmentation Benchmark (LiTS)","volume":"84","author":"Bilic","year":"2023","journal-title":"Med. Image Anal."},{"key":"pmbad611dbib3","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1126\/science.1203543","article-title":"A perspective on cancer cell metastasis","volume":"331","author":"Chaffer","year":"2011","journal-title":"Science"},{"key":"pmbad611dbib4","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.media.2019.07.006","article-title":"Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces","volume":"57","author":"Dalca","year":"2019","journal-title":"Med. Image Anal."},{"key":"pmbad611dbib5","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1001\/archsurg.133.5.510","article-title":"Evaluation of benign vs malignant hepatic lesions with positron emission tomography","volume":"133","author":"Delbeke","year":"1998","journal-title":"Arch. Surg."},{"key":"pmbad611dbib6","article-title":"Leveraging Uncertainty Estimates for Predicting Segmentation Quality","author":"DeVries","year":"2018"},{"key":"pmbad611dbib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108739","article-title":"A unified uncertainty network for tumor segmentation using uncertainty cross entropy loss and prototype similarity","volume":"246","author":"Diao","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"pmbad611dbib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12885-018-5257-x","article-title":"Tumor growth rate as a metric of progression, response, and prognosis in pancreatic and intestinal neuroendocrine tumors","volume":"19","author":"Dromain","year":"2019","journal-title":"BMC Cancer"},{"key":"pmbad611dbib9","first-page":"287","article-title":"The detection of bone metastases in patients with high-risk prostate cancer: 99m Tc-MDP planar bone scintigraphy, single-and multi-field-of-view SPECT, 18 F-fluoride PET, and 18 F-fluoride PET\/CT","volume":"47","author":"Even-Sapir","year":"2006","journal-title":"J. Nucl. Med."},{"key":"pmbad611dbib10","article-title":"Dropout as a Bayesian approximation: representing model uncertainty in deep learning Zoubin Ghahramani","author":"Gal","year":"2016"},{"key":"pmbad611dbib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101855","article-title":"Quantifying and leveraging predictive uncertainty for medical image assessment","volume":"68","author":"Ghesu","year":"2021","journal-title":"Med. Image Anal."},{"key":"pmbad611dbib12","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1109\/TMI.2018.2806309","article-title":"Automatic multi-organ segmentation on abdominal CT with dense V-networks","volume":"37","author":"Gibson","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad611dbib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102596","article-title":"Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation","volume":"82","author":"Gonz\u00e1lez","year":"2022","journal-title":"Med. Image Anal."},{"key":"pmbad611dbib14","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017"},{"key":"pmbad611dbib15","doi-asserted-by":"publisher","first-page":"2829","DOI":"10.1200\/JCO","article-title":"Quantitative assessment of early [18 F]sodium fluoride positron emission tomography\/computed tomography response to treatment in men with metastatic prostate cancer to bone","volume":"35","author":"Harmon","year":"2017","journal-title":"J. Clin. Oncol."},{"key":"pmbad611dbib16","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2017"},{"key":"pmbad611dbib17","article-title":"Using self-supervised learning can improve model robustness and uncertainty","author":"Hendrycks","year":"2019"},{"key":"pmbad611dbib18","article-title":"On the importance of gradients for detecting distributional shifts in the wild","author":"Huang","year":"2021"},{"key":"pmbad611dbib19","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/s11307-011-0486-2","article-title":"Prospective evaluation of 99mTc MDP scintigraphy, 18F NaF PET\/CT, and 18F FDG PET\/CT for detection of skeletal metastases","volume":"14","author":"Iagaru","year":"2012","journal-title":"Mol. Imaging Biol."},{"key":"pmbad611dbib20","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"pmbad611dbib21","doi-asserted-by":"publisher","author":"Jallow","year":"2014","DOI":"10.1016\/j.ijrobp.2014.02.016"},{"key":"pmbad611dbib22","doi-asserted-by":"publisher","first-page":"282","DOI":"10.3389\/fnins.2020.00282","article-title":"Analyzing the quality and challenges of uncertainty estimations for brain tumor segmentation","volume":"14","author":"Jungo","year":"2020","journal-title":"Front. Neurosci."},{"key":"pmbad611dbib23","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acd221","article-title":"Uncertainty estimation for deep learning-based pectoral muscle segmentation via Monte Carlo dropout","volume":"68","author":"Klanecek","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbad611dbib24","article-title":"Accurate uncertainties for deep learning using calibrated regression","author":"Kuleshov","year":"2018"},{"key":"pmbad611dbib25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-16452-1_49","article-title":"Layer ensembles: a single-pass uncertainty estimation in deep learning for segmentation","author":"Kushibar","year":"2022"},{"key":"pmbad611dbib26","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/s12149-013-0718-4","article-title":"Physiological and tumoral uptake of 68Ga-DOTATATE: standardized uptake values and challenges in interpretation","volume":"27","author":"Kuyumcu","year":"2013","journal-title":"Ann. Nucl. Med."},{"key":"pmbad611dbib27","doi-asserted-by":"publisher","first-page":"3662","DOI":"10.1200\/JCO.20","article-title":"Exploring spatial-temporal changes in 18 F-sodium fluoride PET\/CT and circulating tumor cells in metastatic castration-resistant prostate cancer treated with enzalutamide","volume":"38","author":"Kyriakopoulos","year":"2020","journal-title":"J. Clin. Oncol."},{"key":"pmbad611dbib28","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"Lakshminarayanan","year":"2017"},{"key":"pmbad611dbib29","article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","author":"Lee","year":"2018"},{"key":"pmbad611dbib30","doi-asserted-by":"publisher","first-page":"8004","DOI":"10.1109\/ACCESS.2019.2963254","article-title":"DenseX-Net: an end-to-end model for lymphoma segmentation in whole-body PET\/CT images","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"pmbad611dbib31","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.2967\/jnumed.116.177295","article-title":"Repeatability of quantitative 18F-NaF PET: a multicenter study","volume":"57","author":"Lin","year":"2016","journal-title":"J. Nucl. Med."},{"key":"pmbad611dbib32","doi-asserted-by":"publisher","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","article-title":"A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis","volume":"1","author":"Liu","year":"2019","journal-title":"Lancet Digit. Health"},{"key":"pmbad611dbib33","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.773299","article-title":"Detection and segmentation of pelvic bones metastases in MRI images for patients with prostate cancer based on deep learning","volume":"11","author":"Liu","year":"2021","journal-title":"Front. Oncol."},{"key":"pmbad611dbib34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00259-024-06764-0","article-title":"Quantitative evaluation of lesion response heterogeneity for superior prognostication of clinical outcome","author":"Lokre","year":"2024","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbad611dbib35","doi-asserted-by":"publisher","first-page":"67","DOI":"10.3389\/fninf.2019.00067","article-title":"Knowing what you know in brain segmentation using Bayesian deep neural networks","volume":"13","author":"McClure","year":"2019","journal-title":"Front. Neuroinform."},{"key":"pmbad611dbib36","doi-asserted-by":"publisher","first-page":"3868","DOI":"10.1109\/TMI.2020.3006437","article-title":"Confidence calibration and predictive uncertainty estimation for deep medical image segmentation","volume":"39","author":"Mehrtash","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad611dbib37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101557","article-title":"Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation","volume":"59","author":"Nair","year":"2020","journal-title":"Med. Image Anal."},{"key":"pmbad611dbib38","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1109\/TBME.2022.3232730","article-title":"Estimating uncertainty in neural networks for cardiac MRI segmentation: a benchmark study","volume":"70","author":"Ng","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmbad611dbib39","doi-asserted-by":"publisher","first-page":"1994","DOI":"10.1148\/rg.220056","article-title":"Liver metastases: correlation between imaging features and pathomolecular environments","volume":"42","author":"Ozaki","year":"2022","journal-title":"Radiographics"},{"key":"pmbad611dbib40","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaebd0","article-title":"Automated classification of benign and malignant lesions in 18F-NaF PET\/CT images using machine learning","volume":"63","author":"Perk","year":"2018a","journal-title":"Phys. Med. Biol."},{"key":"pmbad611dbib41","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaebba","article-title":"A statistically optimized regional thresholding method (SORT) for bone lesion detection in 18F-NaF PET\/CT imaging","volume":"63","author":"Perk","year":"2018b","journal-title":"Phys. Med. Biol."},{"key":"pmbad611dbib42","doi-asserted-by":"publisher","first-page":"31","DOI":"10.2967\/jnmt.108.055004","article-title":"Prospective evaluation of physiologic uptake detected with true whole-body 18F-FDG PET\/CT in healthy subjects","volume":"37","author":"Reinking","year":"2009","journal-title":"J. Nucl. Med. Technol."},{"key":"pmbad611dbib43","doi-asserted-by":"publisher","first-page":"5534","DOI":"10.1002\/cam4.1697","article-title":"Clinical landscape of cancer metastases","volume":"7","author":"Riihim\u00e4ki","year":"2018","journal-title":"Cancer Med."},{"key":"pmbad611dbib44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"pmbad611dbib45","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00176","article-title":"Uncertainty measures and prediction quality rating for the semantic segmentation of nested multi resolution street scene images","author":"Rottmann","year":"2019"},{"key":"pmbad611dbib46","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad31c6","article-title":"An automated methodology for whole-body, multimodality tracking of individual cancer lesions","volume":"69","author":"Santoro Fernandes","year":"2024","journal-title":"Phys. Med. Biol."},{"key":"pmbad611dbib47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00259-024-06767-x","article-title":"Models using comprehensive, lesion-level, longitudinal [68Ga]Ga-DOTA-TATE PET-derived features lead to superior outcome prediction in neuroendocrine tumor patients treated with [177Lu]Lu-DOTA-TATE","author":"Santoro-Fernandes","year":"2024","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbad611dbib48","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acaf22","article-title":"Comparison of automated full-body bone metastases delineation methods and their corresponding prognostic power","volume":"68","author":"Schott","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbad611dbib49","article-title":"Test-time data augmentation for estimation of heteroscedastic aleatoric uncertainty in deep neural networks","author":"Se\u00e7kin Ayhan","year":"2018"},{"key":"pmbad611dbib50","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s12149-019-01343-y","article-title":"18 F-NaF-PET\/CT for the detection of bone metastasis in prostate cancer: a meta-analysis of diagnostic accuracy studies","volume":"33","author":"Sheikhbahaei","year":"2019","journal-title":"Ann. Nucl. Med."},{"key":"pmbad611dbib51","doi-asserted-by":"publisher","first-page":"691","DOI":"10.2214\/ajr.174.3.1740691","article-title":"CT and MR imaging of hepatic metastases","volume":"174","author":"Sica","year":"2000","journal-title":"Am. J. Roentgenol."},{"key":"pmbad611dbib52","first-page":"10124","article-title":"Post-hoc uncertainty calibration for domain drift scenarios","author":"Tomani","year":"2021"},{"key":"pmbad611dbib53","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neucom.2019.01.103","article-title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","volume":"338","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"key":"pmbad611dbib54","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1002\/acm2.13121","article-title":"A review on medical imaging synthesis using deep learning and its clinical applications","volume":"22","author":"Wang","year":"2021","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbad611dbib55","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1007\/s00259-021-05270-x\/Published","article-title":"Just another \u201cclever hans\u201d? Neural networks and FDG PET-CT to predict the outcome of patients with breast cancer","volume":"48","author":"Weber","year":"2021","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbad611dbib56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1148\/ryai.2020200016","article-title":"Convolutional neural networks for automated PET\/CT detection of diseased lymph node burden in patients with lymphoma","volume":"2","author":"Weisman","year":"2020","journal-title":"Radiol.: Artif. Intell."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T10:52:05Z","timestamp":1721386325000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad611d"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,19]]},"references-count":56,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,7,19]]},"published-print":{"date-parts":[[2024,8,7]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ad611d","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,19]]},"assertion":[{"value":"Uncertainty quantification via localized gradients for deep learning-based medical image assessments","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-03-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-09","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}