{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T04:31:37Z","timestamp":1747801897535,"version":"3.41.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"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":["J Digit Imaging. Inform. med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Techniques are developed for generating uncertainty estimates for convolutional neural network (CNN)-based methods for registering the locations of lesions between the craniocaudal (CC) and mediolateral oblique (MLO) mammographic X-ray image views. Multi-view lesion correspondence is an important task that clinicians perform for characterizing lesions during routine mammographic exams. Automated registration tools can aid in this task, yet if the tools also provide confidence estimates, they can be of greater value to clinicians, especially in cases involving dense tissue where lesions may be difficult to see. A set of deep ensemble-based techniques, which leverage a negative log-likelihood (NLL)-based cost function, are implemented for estimating uncertainties. The ensemble architectures involve significant modifications to an existing CNN dual-view lesion registration algorithm. Three architectural designs are evaluated, and different ensemble sizes are compared using various performance metrics. The techniques are tested on synthetic X-ray data, real 2D X-ray data, and slices from real 3D X-ray data. The ensembles generate covariance-based uncertainty ellipses that are correlated with registration accuracy, such that the ellipse sizes can give a clinician an indication of confidence in the mapping between the CC and MLO views. The results also show that the ellipse sizes can aid in improving computer-aided detection (CAD) results by matching CC\/MLO lesion detects and reducing false alarms from both views, adding to clinical utility. The uncertainty estimation techniques show promise as a means for aiding clinicians in confidently establishing multi-view lesion correspondence, thereby improving diagnostic capability.<\/jats:p>","DOI":"10.1007\/s10278-024-01244-1","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:02:04Z","timestamp":1727110924000},"page":"1829-1845","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty Estimation for Dual View X-ray Mammographic Image Registration Using Deep Ensembles"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7323-6538","authenticated-orcid":false,"given":"William C.","family":"Walton","sequence":"first","affiliation":[]},{"given":"Seung-Jun","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,23]]},"reference":[{"key":"1244_CR1","doi-asserted-by":"crossref","unstructured":"R.\u00a0L. Siegel et al., \u201cCancer Statistics, 2020,\u201d CA: A Cancer Journal for Clinicians 70(1), 7\u201330 (2020).","DOI":"10.3322\/caac.21590"},{"issue":"1102","key":"1244_CR2","doi-asserted-by":"publisher","first-page":"20190057","DOI":"10.1259\/bjr.20190057","volume":"92","author":"Z Gandomkar","year":"2019","unstructured":"Z.\u00a0Gandomkar and C.\u00a0Mello-Thoms, \u201cVisual Search in Breast Imaging,\u201d The British Journal of Radiology 92(1102), 20190057 (2019).","journal-title":"The British Journal of Radiology"},{"key":"1244_CR3","doi-asserted-by":"crossref","unstructured":"G.\u00a0Eklund, \u201cThe Art of Mammographic Positioning,\u201d in Radiological Diagnosis of Breast Diseases, M.\u00a0Friedrich and E.\u00a0A. Sickles, Eds., 75\u201388, Springer (2000).","DOI":"10.1007\/978-3-642-60919-0_6"},{"issue":"11","key":"1244_CR4","doi-asserted-by":"publisher","first-page":"S456","DOI":"10.1016\/j.jacr.2021.09.002","volume":"18","author":"SP Weinstein","year":"2021","unstructured":"S.\u00a0P. Weinstein et al., \u201cACR Appropriateness Criteria\u00ae Supplemental Breast Cancer Screening Based on Breast Density,\u201d Journal of the American College of Radiology 18(11), S456\u2013S473 (2021).","journal-title":"Journal of the American College of Radiology"},{"issue":"1\u20132","key":"1244_CR5","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s11517-005-0016-y","volume":"44","author":"Y Guo","year":"2006","unstructured":"Y.\u00a0Guo et al., \u201cBreast Image Registration Techniques: A Survey,\u201d Medical and Biological Eng. and Comp. 44(1-2), 15\u201326 (2006).","journal-title":"Medical and Biological Eng. and Comp."},{"key":"1244_CR6","doi-asserted-by":"crossref","unstructured":"S.\u00a0Famouri et al., \u201cA Deep Learning Approach for Efficient Registration of Dual View Mammography,\u201d in Proc. Workshop on Art. Neural Networks in Pattern Recogn., 162\u2013172 (2020).","DOI":"10.1007\/978-3-030-58309-5_13"},{"key":"1244_CR7","volume-title":"DV-DCNN: Dual-View Deep Convolutional Neural Network for Matching Detected Masses in Mammograms","author":"M AlGhamdi","year":"2021","unstructured":"M.\u00a0AlGhamdi and M.\u00a0Abdel-Mottaleb, \u201cDV-DCNN: Dual-View Deep Convolutional Neural Network for Matching Detected Masses in Mammograms,\u201d Comp. Methods Prog. Biomed. (2021)."},{"key":"1244_CR8","doi-asserted-by":"publisher","unstructured":"W. C. Walton et al., \u201cAutomated Registration for Dual-View X-Ray Mammography using Convolutional Neural Networks,\u201d IEEE Trans. Biomedical Eng. 69(11), 3538\u20133550 (2022). [https:\/\/doi.org\/10.1109\/TBME.2022.3173182].","DOI":"10.1109\/TBME.2022.3173182"},{"key":"1244_CR9","doi-asserted-by":"crossref","unstructured":"M.\u00a0Samulski and N.\u00a0Karssemeijer, \u201cMatching Mammographic Regions in Mediolateral Oblique and Cranio Caudal Views: A Probabilistic Approach,\u201d in Proc. SPIE Med. Imag., (2008).","DOI":"10.1117\/12.769792"},{"key":"1244_CR10","doi-asserted-by":"crossref","unstructured":"S.\u00a0v. Engeland et al., \u201cFinding Corresponding Regions of Interest in Mediolateral Oblique and Craniocaudal Mammographic Views,\u201d Medical Physics 33(9), 3203\u20133212 (2006).","DOI":"10.1118\/1.2230359"},{"issue":"2","key":"1244_CR11","first-page":"238","volume":"29","author":"S Paquerault","year":"2002","unstructured":"S.\u00a0Paquerault et al., \u201cImprovement of Computerized Mass Detection on Mammograms: Fusion of Two-View Information,\u201d Int. J. Med. Phys. Res. Practice 29(2), 238\u2013247 (2002).","journal-title":"Int. J. Med. Phys. Res. Practice"},{"key":"1244_CR12","doi-asserted-by":"crossref","unstructured":"B.\u00a0N. Taylor and C.\u00a0E. Kuyatt, Guidelines for Evaluating and Expressing the Uncertainty of NIST Measurement Results, vol.\u00a01297, National Institute of Standards (NIST) (1994).","DOI":"10.6028\/NIST.TN.1297"},{"key":"1244_CR13","doi-asserted-by":"crossref","unstructured":"A.\u00a0Possolo, Simple Guide for Evaluating and Expressing the Uncertainty of NIST Measurement Results, vol.\u00a01900, National Institute of Standards (NIST) (2015).","DOI":"10.6028\/NIST.TN.1900"},{"issue":"1","key":"1244_CR14","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1007\/s10462-023-10562-9","volume":"56","author":"J Gawlikowski","year":"2023","unstructured":"J.\u00a0Gawlikowski et al., \u201cA Survey of Uncertainty in Deep Neural Networks,\u201d Artif. Intell. Rev. 56(1), 1513\u20131589 (2023).","journal-title":"Artif. Intell. Rev."},{"key":"1244_CR15","unstructured":"B.\u00a0Lakshminarayanan et al., \u201cSimple and Scalable Predictive Uncertainty Estimation using Deep Ensembles,\u201d in Proc. NeurIPS, 30, (Long Beach, CA. USA) (2017)."},{"key":"1244_CR16","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"M.\u00a0Abdar et al., \u201cA Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges,\u201d Information Fusion 76, 243\u2013297 (2021).","journal-title":"Information Fusion"},{"key":"1244_CR17","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.neuroimage.2017.07.008","volume":"158","author":"X Yang","year":"2017","unstructured":"X.\u00a0Yang et al., \u201cQuicksilver: Fast Predictive Image Registration- A Deep Learning Approach,\u201d NeuroImage 158, 378\u2013396 (2017).","journal-title":"NeuroImage"},{"issue":"1","key":"1244_CR18","volume":"2","author":"J Caldeira","year":"2020","unstructured":"J.\u00a0Caldeira and B.\u00a0Nord, \u201cDeeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms,\u201d Machine Learning: Science and Technology 2(1), 015002 (2020).","journal-title":"Machine Learning: Science and Technology"},{"key":"1244_CR19","unstructured":"Z.\u00a0Ghahramani, \u201cA history of Bayesian neural networks,\u201d in NIPS Workshop on Bayesian Deep Learning, (2016)."},{"key":"1244_CR20","unstructured":"V.\u00a0Kuleshov et al., \u201cAccurate Uncertainties for Deep Learning Using Calibrated Regression,\u201d in Int. Conf. on Machine Learning, 80, 2796\u20132804, PMLR (2018)."},{"key":"1244_CR21","unstructured":"C.\u00a0Guo et al., \u201cOn Calibration of Modern Neural Networks,\u201d in Int. Conf. on Machine Learning, 70, 1321\u20131330, PMLR (2017)."},{"key":"1244_CR22","unstructured":"Y.\u00a0Gal and Z.\u00a0Ghahramani, \u201cDropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning,\u201d in Int. Conf. on Machine Learning, 48, 1050\u20131059, PMLR (2016)."},{"key":"1244_CR23","unstructured":"S.\u00a0M. Zenciroglu, \u201cComparing Non-Bayesian Uncertainty Evaluation Methods in Chromosome Classification by Using Deep Neural Networks,\u201d Master\u2019s thesis, KTH Royal Institute of Technology (2021)."},{"key":"1244_CR24","doi-asserted-by":"crossref","unstructured":"D.\u00a0A. Nix and A.\u00a0S. Weigend, \u201cEstimating the Mean and Variance of the Target Probability Distribution,\u201d in Proc. Int. Conf. on Neural Networks, 1, 55\u201360, IEEE (1994).","DOI":"10.1109\/ICNN.1994.374138"},{"key":"1244_CR25","unstructured":"Y.\u00a0Ovadia et al., \u201cCan You Trust Your Model\u2019s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift,\u201d in Proc. 33rd Conf. Neural Info. Proc. Systems, (2019)."},{"key":"1244_CR26","doi-asserted-by":"crossref","unstructured":"M.\u00a0P. Naeini, G.\u00a0Cooper, and M.\u00a0Hauskrecht, \u201cObtaining Well Calibrated Probabilities Using Bayesian Binning,\u201d in Proc. Twenty-Ninth AAAI Conf. on Art. Intell., 29(1), 2901\u20132907 (2015).","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"1244_CR27","unstructured":"X.\u00a0Yang, Uncertainty Quantification, Image Synthesis and Deformation Prediction for Image Registration. PhD thesis, The University of North Carolina at Chapel Hill (2017)."},{"key":"1244_CR28","unstructured":"T.\u00a0Lotfi\u00a0Mahyari, \u201cUncertainty in Probabilistic Image Registration,\u201d Master\u2019s thesis, Simon Fraser University (2013)."},{"key":"1244_CR29","doi-asserted-by":"crossref","unstructured":"J.\u00a0Luo et al., \u201cOn the Applicability of Registration Uncertainty,\u201d in Proc. MICCAI, 410\u2013419, Springer (2019).","DOI":"10.1007\/978-3-030-32245-8_46"},{"key":"1244_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101557","volume":"59","author":"T Nair","year":"2020","unstructured":"T.\u00a0Nair et al., \u201cExploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation,\u201d Medical Image Analysis 59, 101557 (2020).","journal-title":"Medical Image Analysis"},{"key":"1244_CR31","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Yang et al., \u201cUncertainty Quantification in Medical Image Segmentation with Multi-decoder U-Net,\u201d in Int. MICCAI Brain Lesion Workshop, 570\u2013577, Springer (2021).","DOI":"10.1007\/978-3-031-09002-8_50"},{"key":"1244_CR32","doi-asserted-by":"crossref","unstructured":"F.\u00a0C. Ghesu et al., \u201cQuantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment,\u201d in Proc. MICCAI, 676\u2013684, Springer (2019).","DOI":"10.1007\/978-3-030-32226-7_75"},{"key":"1244_CR33","doi-asserted-by":"publisher","first-page":"182092","DOI":"10.1109\/ACCESS.2020.3027805","volume":"8","author":"P Mojabi","year":"2020","unstructured":"P.\u00a0Mojabi et al., \u201cTissue-Type Classification with Uncertainty Quantification of Microwave and Ultrasound breast imaging: A Deep Learning Approach,\u201d IEEE Access 8, 182092\u2013182104 (2020).","journal-title":"IEEE Access"},{"key":"1244_CR34","doi-asserted-by":"crossref","unstructured":"S.\u00a0Yang and T.\u00a0Fevens, \u201cUncertainty Quantification and Estimation in Medical Image Classification,\u201d in Int. Conf. on Artificial Neural Networks, 671\u2013683, Springer (2021).","DOI":"10.1007\/978-3-030-86365-4_54"},{"key":"1244_CR35","doi-asserted-by":"crossref","unstructured":"S.\u00a0Calderon-Ramirez et al., \u201cImproving Uncertainty Estimations for Mammogram Classification using Semi-Supervised Learning,\u201d in 2021 Int. Joint Conf. on Neural Networks (IJCNN), 1\u20138, IEEE (2021).","DOI":"10.1109\/IJCNN52387.2021.9533719"},{"key":"1244_CR36","doi-asserted-by":"crossref","unstructured":"R.\u00a0Barbano et al., \u201cUncertainty Quantification in Medical Image Synthesis,\u201d in Biomed. Image Synth. and Sim., N.\u00a0Burgos and D.\u00a0Svoboda, Eds., 601\u2013641, Academic Press (2022).","DOI":"10.1016\/B978-0-12-824349-7.00033-5"},{"key":"1244_CR37","doi-asserted-by":"crossref","unstructured":"D.\u00a0Grzech et al., \u201cUncertainty Quantification in Non-Rigid image Registration via Stochastic Gradient Markov Chain Monte Carlo,\u201d arXiv:2110.13289 (2021).","DOI":"10.59275\/j.melba.2021-gfc4"},{"key":"1244_CR38","unstructured":"J.\u00a0Stanley, Quantification of Uncertainty in Stereotactic Radiosurgery. PhD thesis, University of Calgary (2015)."},{"issue":"8","key":"1244_CR39","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1016\/S0301-5629(01)00396-9","volume":"27","author":"WL Smith","year":"2001","unstructured":"W.\u00a0L. Smith et al., \u201cThree-Dimensional Ultrasound-Guided Core Needle Breast Biopsy,\u201d Ultrasound in Medicine & Biology 27(8), 1025\u20131034 (2001).","journal-title":"Ultrasound in Medicine & Biology"},{"key":"1244_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.media.2018.07.002","volume":"49","author":"Y Hu","year":"2018","unstructured":"Y.\u00a0Hu et al., \u201cWeakly-Supervised Convolutional Neural Networks for Multimodal Image Registration,\u201d Med. Imag. Anal. 49, 1\u201313 (2018).","journal-title":"Med. Imag. Anal."},{"issue":"7","key":"1244_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1001\/jamanetworkopen.2018.5474","volume":"1","author":"A Badano","year":"2018","unstructured":"A.\u00a0Badano et al., \u201cEvaluation of Digital Breast Tomosynthesis as Replacement of Full-Field Digital Mammography Using an In Silico Imaging Trial,\u201d JAMA Network Open 1(7), 1\u201312 (2018).","journal-title":"JAMA Network Open"},{"issue":"1","key":"1244_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2017.177","volume":"4","author":"R Lee","year":"2017","unstructured":"R.\u00a0Lee et al., \u201cA Curated Mammography Data Set for Use in Computer-Aided Detection and Diagnosis Research,\u201d Scientific Data 4(1), 1\u20139 (2017).","journal-title":"Scientific Data"},{"key":"1244_CR43","doi-asserted-by":"publisher","first-page":"e2119100","DOI":"10.1001\/jamanetworkopen.2021.19100","volume":"4","author":"M Buda","year":"2021","unstructured":"M.\u00a0Buda et al., \u201cA Data Set and Deep Learning Algorithm for the Detection of Masses and Architectural Distortions in Digital Breast Tomosynthesis Images,\u201d JAMA Network Open 4, e2119100\u2013e2119100 (2021).","journal-title":"JAMA Network Open"},{"key":"1244_CR44","unstructured":"D.\u00a0P. Kingma and J.\u00a0Ba, \u201cAdam: A Method for Stochastic Optimization,\u201d arXiv:1412.6980 (2014)."},{"key":"1244_CR45","volume-title":"Pattern Classification","author":"RO Duda","year":"2001","unstructured":"R.\u00a0O. Duda et al., Pattern Classification, vol.\u00a02, Wiley New York (2001)."},{"key":"1244_CR46","unstructured":"J.\u00a0Sicking et\u00a0al., \u201cApproaching Neural Network Uncertainty Realism,\u201d in Proc. NeurIPS, (2019)."},{"key":"1244_CR47","unstructured":"H.\u00a0Huang et al., \u201cDecomposing Representations for Deterministic Uncertainty Estimation,\u201d in Proc. NeurIPS, (2021)."},{"issue":"3","key":"1244_CR48","first-page":"215","volume":"31","author":"AJ Newman","year":"2013","unstructured":"A.\u00a0J. Newman and G.\u00a0E. Mitzel, \u201cUpstream Data Fusion: History, Technical Overview, and Applications to Critical Challenges,\u201d Johns Hopkins APL Technical Digest 31(3), 215\u2013233 (2013).","journal-title":"Johns Hopkins APL Technical Digest"},{"key":"1244_CR49","unstructured":"J.\u00a0R. Orechovesky, \u201cSingle Source Error Ellpse [ie ellipse] Combination,\u201d Master\u2019s thesis, Naval Postgraduate School, Monterey, California. (1996)."},{"issue":"3","key":"1244_CR50","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.tjem.2018.08.001","volume":"18","author":"H Akoglu","year":"2018","unstructured":"H.\u00a0Akoglu, \u201cUser\u2019s Guide to Correlation Coefficients,\u201d Turkish journal of emergency medicine 18(3), 91\u201393 (2018).","journal-title":"Turkish journal of emergency medicine"},{"issue":"1","key":"1244_CR51","doi-asserted-by":"publisher","first-page":"5979","DOI":"10.1038\/s41598-022-09954-8","volume":"12","author":"SA Hicks","year":"2022","unstructured":"S.\u00a0A. Hicks et al., \u201cOn Evaluation Metrics for Medical Applications of Artificial Intelligence,\u201d Scientific reports 12(1), 5979 (2022).","journal-title":"Scientific reports"},{"key":"1244_CR52","unstructured":"J.\u00a0H. McDonald, Handbook of Biological Statistics, 3rd Ed., vol.\u00a03, Sparky House Publishing, Baltimore, MD (2014)."},{"issue":"S2","key":"1244_CR53","doi-asserted-by":"publisher","first-page":"S22409","DOI":"10.1117\/1.JMI.10.S2.S22409","volume":"10","author":"LA Mullen","year":"2023","unstructured":"L.\u00a0A. Mullen et al., \u201cBreast Cancer Detection with Upstream Data Fusion, Machine Learning, and Automated Registration: Initial Results,\u201d J. Med. Imag. 10(S2), S22409 (2023).","journal-title":"J. Med. Imag."}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-024-01244-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-024-01244-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-024-01244-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T17:27:17Z","timestamp":1747762037000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-024-01244-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":53,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["1244"],"URL":"https:\/\/doi.org\/10.1007\/s10278-024-01244-1","relation":{},"ISSN":["2948-2933"],"issn-type":[{"type":"electronic","value":"2948-2933"}],"subject":[],"published":{"date-parts":[[2024,9,23]]},"assertion":[{"value":"19 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The publicly available CBIS-DDSM\u00a0[] and TCIA X-ray data sets\u00a0[], as well as the JHM X-ray data sets (IRB00185772, 12\/3\/2018), were approved by the respective institutional review boards with a waiver of informed consent. Hence, the use of these real X-ray data sets for our study is compliant with the Health Insurance Portability and Accountability Act.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Some of the technologies described in this paper may be protected under the US Patent Nos. 11,361,868 and 11,657,497.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclaimer"}}]}}