{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:07:34Z","timestamp":1760710054862,"version":"3.37.3"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2019,11,21]],"date-time":"2019-11-21T00:00:00Z","timestamp":1574294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,11,21]],"date-time":"2019-11-21T00:00:00Z","timestamp":1574294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004622","name":"KWF Kankerbestrijding","doi-asserted-by":"publisher","award":["15191"],"award-info":[{"award-number":["15191"]}],"id":[{"id":"10.13039\/501100004622","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In medical imaging, a proper gold-standard ground truth as, e.g., annotated segmentations by assessors or experts is lacking or only scarcely available and suffers from large intervariability in those segmentations. Most state-of-the-art segmentation models do not take inter-observer variability into account and are fully deterministic in nature. In this work, we propose hypersphere encoder\u2013decoder networks in combination with dynamic leaky ReLUs, as a new method to explicitly incorporate inter-observer variability into a segmentation model. With this model, we can then generate multiple proposals based on the inter-observer agreement. As a result, the output segmentations of the proposed model can be tuned to typical margins inherent to the ambiguity in the data. For experimental validation, we provide a proof of concept on a toy data set as well as show improved segmentation results on two medical data sets. The proposed method has several advantages over current state-of-the-art segmentation models such as interpretability in the uncertainty of segmentation borders. Experiments with a medical localization problem show that it offers improved biopsy localizations, which are on average 12% closer to the optimal biopsy location.<\/jats:p>","DOI":"10.1007\/s00521-019-04607-w","type":"journal-article","created":{"date-parts":[[2019,11,21]],"date-time":"2019-11-21T17:03:43Z","timestamp":1574355823000},"page":"10705-10717","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Modeling clinical assessor intervariability using deep hypersphere encoder\u2013decoder networks"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0915-9048","authenticated-orcid":false,"given":"Joost","family":"van der Putten","sequence":"first","affiliation":[]},{"given":"Fons","family":"van der Sommen","sequence":"additional","affiliation":[]},{"given":"Jeroen","family":"de Groof","sequence":"additional","affiliation":[]},{"given":"Maarten","family":"Struyvenberg","sequence":"additional","affiliation":[]},{"given":"Svitlana","family":"Zinger","sequence":"additional","affiliation":[]},{"given":"Wouter","family":"Curvers","sequence":"additional","affiliation":[]},{"given":"Erik","family":"Schoon","sequence":"additional","affiliation":[]},{"given":"Jacques","family":"Bergman","sequence":"additional","affiliation":[]},{"given":"Peter H. N.","family":"de With","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,21]]},"reference":[{"key":"4607_CR1","doi-asserted-by":"crossref","unstructured":"Cheng D, Gong Y, Zhou S, Wang J, Zheng N (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1335\u20131344","DOI":"10.1109\/CVPR.2016.149"},{"issue":"8","key":"4607_CR2","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1016\/S1885-5857(10)70183-3","volume":"63","author":"N Gonzalo","year":"2010","unstructured":"Gonzalo N, Tearney GJ, Serruys PW, van Soest G, Okamura T, Garc\u00eda-Garc\u00eda HM, van Geuns RJ, van\u00a0der Ent M, Ligthart J, Boum BE et al (2010) Second-generation optical coherence tomography in clinical practice. High-speed data acquisition is highly reproducible in patients undergoing percutaneous coronary intervention. Revista Espa\u00f1ola de Cardiolog\u00eda (English Edition) 63(8):893\u2013903","journal-title":"Revista Espa\u00f1ola de Cardiolog\u00eda (English Edition)"},{"issue":"6","key":"4607_CR3","doi-asserted-by":"publisher","first-page":"AB270","DOI":"10.1016\/j.gie.2018.04.1583","volume":"87","author":"J de Groof","year":"2018","unstructured":"de Groof J, van der Putten J, van der Sommen F, Zinger S, Curvers W, Bisschops R, Pech O, Meining A, Neuhaus H, Schoon EJ et al (2018) The argos project: first results of the development of a computer aided detection system for Barrett\u2019s neoplasia. Gastroint Endosc 87(6):AB270","journal-title":"Gastroint Endosc"},{"key":"4607_CR4","unstructured":"Guzman-Rivera A, Batra D, Kohli P (2012) Multiple choice learning: learning to produce multiple structured outputs. In: Advances in neural information processing systems, pp 1799\u20131807"},{"issue":"6","key":"4607_CR5","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1016\/j.cgh.2008.11.024","volume":"7","author":"R Kariv","year":"2009","unstructured":"Kariv R, Plesec TP, Goldblum JR, Bronner M, Oldenburgh M, Rice TW, Falk GW (2009) The Seattle protocol does not more reliably predict the detection of cancer at the time of esophagectomy than a less intensive surveillance protocol. Clin Gastroenterol Hepatol 7(6):653\u2013658","journal-title":"Clin Gastroenterol Hepatol"},{"key":"4607_CR6","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"key":"4607_CR7","unstructured":"Kohl SA, Romera-Paredes B, Meyer C, De\u00a0Fauw J, Ledsam JR, Maier-Hein KH, Eslami S, Rezende DJ, Ronneberger O (2018) A probabilistic u-net for segmentation of ambiguous images. arXiv preprint arXiv:1806.05034"},{"key":"4607_CR8","unstructured":"Lakshminarayanan B, Pritzel A, Blundell C (2017) Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in neural information processing systems, pp 6402\u20136413"},{"key":"4607_CR9","unstructured":"Lee S, Purushwalkam S, Cogswell M, Crandall D, Batra D (2015) Why m heads are better than one: training a diverse ensemble of deep networks. arXiv preprint arXiv:1511.06314"},{"key":"4607_CR10","unstructured":"Loshchilov I, Hutter F (2016) SGDR: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983"},{"key":"4607_CR11","unstructured":"Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of ICML, vol\u00a030"},{"issue":"1","key":"4607_CR12","first-page":"260","volume":"16","author":"C Manning","year":"2010","unstructured":"Manning C, Raghavan P, Sch\u00fctze H (2010) Introduction to information retrieval. Nat Lang Eng 16(1):260","journal-title":"Nat Lang Eng"},{"issue":"2","key":"4607_CR13","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TPAMI.2003.1177156","volume":"25","author":"CR Maurer","year":"2003","unstructured":"Maurer CR, Qi R, Raghavan V (2003) A linear time algorithm for computing exact Euclidean distance transforms of binary images in arbitrary dimensions. IEEE Trans Pattern Anal Mach Intell 25(2):265\u2013270","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4607_CR14","doi-asserted-by":"crossref","unstructured":"van\u00a0der Putten J, van\u00a0der Sommen F, Struyvenberg M, de\u00a0Groof J, Curvers W, SchoonSchoon E, Bergman J, de\u00a0With P (2019) Tissue segmentation in volumetric laser endomicroscopy data using FusionNet and a domain-specific loss function. SPIE Medical Imaging","DOI":"10.1117\/12.2512192"},{"issue":"11","key":"4607_CR15","doi-asserted-by":"publisher","first-page":"3089","DOI":"10.1111\/j.1572-0241.2000.03182.x","volume":"95","author":"BJ Reid","year":"2000","unstructured":"Reid BJ, Blount PL, Feng Z, Levine DS (2000) Optimizing endoscopic biopsy detection of early cancers in Barrett\u2019s high-grade dysplasia. Am J Gastroenterol 95(11):3089","journal-title":"Am J Gastroenterol"},{"key":"4607_CR16","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, Springer, New York, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"4607_CR17","doi-asserted-by":"crossref","unstructured":"Rupprecht C, Laina I, DiPietro R, Baust M, Tombari F, Navab N, Hager GD (2017) Learning in an uncertain world: representing ambiguity through multiple hypotheses. In: International conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.388"},{"issue":"3","key":"4607_CR18","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1053\/j.gastro.2015.11.037","volume":"150","author":"P Sharma","year":"2016","unstructured":"Sharma P, Bergman JJ, Goda K, Kato M, Messmann H, Alsop BR, Gupta N, Vennalaganti P, Hall M, Konda V et al (2016) Development and validation of a classification system to identify high-grade dysplasia and esophageal adenocarcinoma in Barrett\u2019s esophagus using narrow-band imaging. Gastroenterology 150(3):591\u2013598","journal-title":"Gastroenterology"},{"key":"4607_CR19","unstructured":"Sohn K, Lee H, Yan X (2015) Learning structured output representation using deep conditional generative models. In: Advances in neural information processing systems, pp 3483\u20133491"},{"issue":"4","key":"4607_CR20","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1038\/bjc.1993.140","volume":"67","author":"J S\u00f8rensen","year":"1993","unstructured":"S\u00f8rensen J, Klee M, Palshof T, Hansen H (1993) Performance status assessment in cancer patients. an inter-observer variability study. Br J Cancer 67(4):773","journal-title":"Br J Cancer"},{"key":"4607_CR21","doi-asserted-by":"crossref","unstructured":"Tang Y, Harrison AP, Bagheri M, Xiao J, Summers RM (2018) Semi-automatic RECIST labeling on CT scans with cascaded convolutional neural networks. In: International conference on medical image computing and computer-assisted intervention. Springer, Berlin, pp 405\u2013413","DOI":"10.1007\/978-3-030-00937-3_47"},{"issue":"9","key":"4607_CR22","first-page":"1242","volume":"39","author":"SR Williamson","year":"2018","unstructured":"Williamson SR, Rao P, Hes O, Epstein JI, Smith SC, Picken MM, Zhou M, Tretiakova MS, Tickoo SK, Chen YB et al (2018) Challenges in pathologic staging of renal cell carcinoma: a study of interobserver variability among urologic pathologists. Am J Surg Pathol 39(9):1242\u20131249","journal-title":"Am J Surg Pathol"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04607-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-019-04607-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04607-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T03:31:23Z","timestamp":1605843083000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-019-04607-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,21]]},"references-count":22,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["4607"],"URL":"https:\/\/doi.org\/10.1007\/s00521-019-04607-w","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2019,11,21]]},"assertion":[{"value":"12 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"For the VLE data set, written informed consent was obtained from all patients and they were included under protocol NTR 6728, registered at . Official approval was obtained by the Institutional Review Board of the Amsterdam University Medical Centers. In the case of the ARGOS data set, only anonymized imagery was used. The Medical Research Involving Human Subjects Act did not apply to this study. Official approval of this study was therefore waived by the Medical Ethics Review Committees of the participating centers.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}