{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:18:11Z","timestamp":1783790291089,"version":"3.55.0"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T00:00:00Z","timestamp":1681948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T00:00:00Z","timestamp":1681948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009379","name":"Interdisziplin\u00e4res Zentrum f\u00fcr Klinische Forschung, Universit\u00e4tsklinikum W\u00fcrzburg","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009379","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Funding cluster Forum Gesundheitsstandort Baden-W\u00fcrttemberg"},{"DOI":"10.13039\/501100008769","name":"Julius-Maximilians-Universit\u00e4t W\u00fcrzburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100008769","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Colorectal cancer is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is a colonoscopy. However, not all colon polyps have the risk of becoming cancerous. Therefore, polyps are classified using different classification systems. After the classification, further treatment and procedures are based on the classification of the polyp. Nevertheless, classification is not easy. Therefore, we suggest two novel automated classifications system assisting gastroenterologists in classifying polyps based on the NICE\u00a0and Paris\u00a0classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We build two classification systems. One is classifying polyps based on their shape (Paris). The other classifies polyps based on their texture and surface patterns (NICE). A two-step process for the Paris\u00a0classification is introduced: First, detecting and cropping the polyp on the image, and secondly, classifying the polyp based on the cropped area with a transformer network. For the NICE\u00a0classification, we design a few-shot learning algorithm based on the Deep Metric Learning approach. The algorithm creates an embedding space for polyps, which allows classification from a few examples to account for the data scarcity of NICE annotated images in our database.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>For the Paris classification, we achieve an accuracy of 89.35 %, surpassing all papers in the literature and establishing a new state-of-the-art and baseline accuracy for other publications on a public data set. For the NICE classification, we achieve a competitive accuracy of 81.13 % and demonstrate thereby the viability of the few-shot learning paradigm in polyp classification in data-scarce environments. Additionally, we show different ablations of the algorithms. Finally, we further elaborate on the explainability of the system by showing heat maps of the neural network explaining neural activations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Overall we introduce two polyp classification systems to assist gastroenterologists. We achieve state-of-the-art performance in the Paris classification and demonstrate the viability of the few-shot learning paradigm in the NICE classification, addressing the prevalent data scarcity issues faced in medical machine learning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12880-023-01007-4","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T14:50:12Z","timestamp":1682002212000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["Automated classification of polyps using deep learning architectures and few-shot learning"],"prefix":"10.1186","volume":"23","author":[{"given":"Adrian","family":"Krenzer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Heil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Fitting","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Safa","family":"Matti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wolfram G.","family":"Zoller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Hann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Puppe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,20]]},"reference":[{"key":"1007_CR1","doi-asserted-by":"publisher","unstructured":"Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA 2018;68(6), 394\u2013424. https:\/\/doi.org\/10.3322\/caac.21492","DOI":"10.3322\/caac.21492"},{"key":"1007_CR2","doi-asserted-by":"crossref","unstructured":"Liaqat A, Khan MA, Shah JH, Sharif MY, Fernandes SL. Automated ulcer and bleeding classification from wce images using multiple features fusion and selection. J Mech Med Biol 2018;18","DOI":"10.1142\/S0219519418500380"},{"key":"1007_CR3","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.patrec.2019.12.024","volume":"131","author":"MA Khan","year":"2020","unstructured":"Khan MA, Khan MA, Ahmed F, Mittal M, Goyal LM, Hemanth DJ, Satapathy SC. Gastrointestinal diseases segmentation and classification based on duo-deep architectures. Pattern Recogn Lett. 2020;131:193\u2013204. https:\/\/doi.org\/10.1016\/j.patrec.2019.12.024.","journal-title":"Pattern Recogn Lett"},{"key":"1007_CR4","doi-asserted-by":"publisher","unstructured":"Bour A, Castillo-Olea C, Garcia-Zapirain B, Zahia S. Automatic colon polyp classification using convolutional neural network: a case study at basque country. In: 2019 IEEE international symposium on signal processing and information technology (ISSPIT), 2019; pp. 1\u20135 . https:\/\/doi.org\/10.1109\/ISSPIT47144.2019.9001816","DOI":"10.1109\/ISSPIT47144.2019.9001816"},{"key":"1007_CR5","doi-asserted-by":"publisher","first-page":"175628482091065","DOI":"10.1177\/1756284820910659","volume":"13","author":"T Ozawa","year":"2020","unstructured":"Ozawa T, Ishihara S, Fujishiro M, Kumagai Y, Shichijo S, Tada T. Automated endoscopic detection and classification of colorectal polyps using convolutional neural networks. Ther Adv Gastroenterol. 2020;13:175628482091065. https:\/\/doi.org\/10.1177\/1756284820910659.","journal-title":"Ther Adv Gastroenterol"},{"key":"1007_CR6","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1055\/a-0849-9548","volume":"07","author":"T Lui","year":"2019","unstructured":"Lui T, Wong K, Mak L, Ko M, Tsao S, Leung W. Endoscopic prediction of deeply submucosal invasive carcinoma with use of artificial intelligence. Endosc Int Open. 2019;07:514\u201320. https:\/\/doi.org\/10.1055\/a-0849-9548.","journal-title":"Endosc Int Open"},{"issue":"6","key":"1007_CR7","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1055\/s-2005-861352","volume":"37","author":"RF Lambert","year":"2005","unstructured":"Lambert RF. Endoscopic classification review group update on the paris classification of superficial neoplastic lesions in the digestive tract. Endoscopy. 2005;37(6):570\u20138.","journal-title":"Endoscopy"},{"issue":"3","key":"1007_CR8","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1053\/j.gastro.2012.05.006","volume":"143","author":"DG Hewett","year":"2012","unstructured":"Hewett DG, Kaltenbach T, Sano Y, Tanaka S, Saunders BP, Ponchon T, Soetikno R, Rex DK. Validation of a simple classification system for endoscopic diagnosis of small colorectal polyps using narrow-band imaging. Gastroenterology. 2012;143(3):599\u2013607.","journal-title":"Gastroenterology"},{"issue":"1","key":"1007_CR9","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1038\/ajg.2014.326","volume":"110","author":"SC Van Doorn","year":"2015","unstructured":"Van Doorn SC, Hazewinkel Y, East JE, Van Leerdam ME, Rastogi A, Pellis\u00e9 M, Sanduleanu-Dascalescu S, Bastiaansen BA, Fockens P, Dekker E. Polyp morphology: an interobserver evaluation for the paris classification among international experts. Off J Am Coll Gastroenterol ACG. 2015;110(1):180\u20137.","journal-title":"Off J Am Coll Gastroenterol ACG"},{"issue":"03","key":"1007_CR10","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1055\/s-0043-102569","volume":"49","author":"M Ferlitsch","year":"2017","unstructured":"Ferlitsch M, Moss A, Hassan C, Bhandari P, Dumonceau J-M, Paspatis G, Jover R, Langner C, Bronzwaer M, Nalankilli K, et al. Colorectal polypectomy and endoscopic mucosal resection (emr): European society of gastrointestinal endoscopy (esge) clinical guideline. Endoscopy. 2017;49(03):270\u201397.","journal-title":"Endoscopy"},{"key":"1007_CR11","doi-asserted-by":"crossref","unstructured":"Krenzer A, Banck M, Makowski K, Hekalo A, Fitting D, Troya J, Sudarevic B, Zoller WG, Hann A, Puppe F. A real-time polyp detection system with clinical application in colonoscopy using deep convolutional neural networks. 2022;https:\/\/assets.researchsquare.com\/files\/rs-1310139\/v1_covered.pdf?c=1644335078","DOI":"10.21203\/rs.3.rs-1310139\/v1"},{"key":"1007_CR12","doi-asserted-by":"crossref","unstructured":"Foss F, West KP, McGregor AH. Pathology of polyps detected in bowel cancer screening programme. Diagnost Histopathol 2011;17","DOI":"10.1016\/j.mpdhp.2011.08.002"},{"key":"1007_CR13","doi-asserted-by":"crossref","unstructured":"Inoue H, Kashida H, Kudo S, Sasako M, Shimoda T, Watanabe H, Yoshida S, Guelrud M, Lightdale C, Wang K, Riddell R, Di\u00e9bold Lambert R, Rey J, Jung M, Neuhaus H, Axon A, Genta RM, Gonvers J. The paris endoscopic classification of superficial neoplastic lesions: esophagus, stomach, and colon: November 30 to december 1, 2002. Gastrointest Endosc 2003;58(6 Suppl), 3\u201343","DOI":"10.1016\/S0016-5107(03)02159-X"},{"key":"1007_CR14","doi-asserted-by":"crossref","unstructured":"Sano Y, Hirate D, Saito Y. Japan nbi expert team classification: Narrow-band imaging magnifying endoscopic classification of colorectal tumors. Digest Endosc 2018;30","DOI":"10.1111\/den.13072"},{"key":"1007_CR15","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1136\/flgastro-2015-100565","volume":"6","author":"LJ Neilson","year":"2015","unstructured":"Neilson LJ, Rutter MD, Saunders BP, Plumb A, Rees CJ. Assessment and management of the malignant colorectal polpy. Front Gastroenterol. 2015;6:117\u201326.","journal-title":"Front Gastroenterol"},{"key":"1007_CR16","doi-asserted-by":"crossref","unstructured":"Hayashi N, Tanaka S, Hewett DG, Kaltenbach TR, Sano Y, Ponchon T, Saunders BP, Rex DK, Soetikno RM. Endoscopic prediction of deep submucosal invasive carcinoma: validation of the narrow-band imaging internationl colorectal endoscopic (nice) classification. Clin Endosc 2013;78","DOI":"10.1016\/j.gie.2013.04.185"},{"key":"1007_CR17","doi-asserted-by":"crossref","unstructured":"Ferlitsch M, Moss A, Hassan C, Bhandari P, Dumonceau J, Paspatis G, Jover R, Langner C, Bronzwaer M, Nalankilli K, Lockers P, Hazzan R, Gralnek IM, Gschwantler M, Waldmann E, Jeschek P, Penz D, Heresbach D, Moons L, Lemmers A, Paraskeva K, Pohl J, Ponchon T, Regula J, Repici A, Rutter MD, Burgess NG, Bourke MJ. Colorectal polypectomy and endoscopic mucosal resection (emr): European society of gastrointestinal endoscopy (esge) clinical guideline. Endoscopy 2017;49","DOI":"10.1055\/s-0043-102569"},{"key":"1007_CR18","doi-asserted-by":"publisher","unstructured":"Zhang X, Chen F, Yu T, An J, Huang Z, Liu J, hu W, Wang L, Duan H, Si J. Real-time gastric polyp detection using convolutional neural networks. PloS One 2019;14, 0214133 . https:\/\/doi.org\/10.1371\/journal.pone.0214133","DOI":"10.1371\/journal.pone.0214133"},{"key":"1007_CR19","doi-asserted-by":"publisher","unstructured":"Bagheri M, Mohrekesh M, Tehrani M, Najarian K, Karimi N, Samavi S, Reza\u00a0Soroushmehr SM. Deep neural network based polyp segmentation in colonoscopy images using a combination of color spaces. In: 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), 2019;pp. 6742\u20136745 . https:\/\/doi.org\/10.1109\/EMBC.2019.8856793","DOI":"10.1109\/EMBC.2019.8856793"},{"key":"1007_CR20","doi-asserted-by":"publisher","unstructured":"Yuan Y, Meng MQ-H. Deep learning for polyp recognition in wireless capsule endoscopy images. Med Phys 2017;44(4):1379\u201389. https:\/\/doi.org\/10.1002\/mp.12147. https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.12147","DOI":"10.1002\/mp.12147"},{"key":"1007_CR21","unstructured":"Ng A, et al. Sparse autoencoder. CS294A Lecture notes 2011;72(2011), 1\u201319"},{"key":"1007_CR22","doi-asserted-by":"crossref","unstructured":"Zhang Y, Liu H, Hu Q. Transfuse: Fusing transformers and cnns for medical image segmentation. CoRR arXiv:abs\/2102.08005 (2021).","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"1007_CR23","doi-asserted-by":"publisher","unstructured":"Kudo S, Hirota S, Nakajima T, Hosobe S, Kusaka H, Kobayashi T, Himori M, Yagyuu A. Colorectal tumours and pit pattern. J Clin Pathol. 1994;47(10):880\u20135. https:\/\/doi.org\/10.1136\/jcp.47.10.880.https:\/\/jcp.bmj.com\/content\/47\/10\/880.full.pdf","DOI":"10.1136\/jcp.47.10.880"},{"key":"1007_CR24","doi-asserted-by":"publisher","unstructured":"Ribeiro E, Uhl A, H\u00e4fner M. Colonic polyp classification with convolutional neural networks. In: 2016 IEEE 29th international symposium on computer-based medical systems (CBMS), 2016;pp. 253\u2013258 . https:\/\/doi.org\/10.1109\/CBMS.2016.39","DOI":"10.1109\/CBMS.2016.39"},{"key":"1007_CR25","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3558374","author":"S Tanwar","year":"2020","unstructured":"Tanwar S, Goel P, Johri P, Div\u00e1n M. Classification of benign and malignant colorectal polyps using pit pattern classification. SSRN Electron J. 2020. https:\/\/doi.org\/10.2139\/ssrn.3558374.","journal-title":"SSRN Electron J"},{"key":"1007_CR26","doi-asserted-by":"publisher","unstructured":"Zhang R, Zheng Y, Mak W, Yu R, Wong S, Poon C. Automatic detection and classification of colorectal polyps by transferring low-level cnn features from nonmedical domain. IEEE J Biomed Health Inform 2016;pp. 1\u20131 . https:\/\/doi.org\/10.1109\/JBHI.2016.2635662","DOI":"10.1109\/JBHI.2016.2635662"},{"key":"1007_CR27","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1136\/gutjnl-2017-314547","volume":"68","author":"M Byrne","year":"2017","unstructured":"Byrne M, Chapados N, Soudan F, Oertel C, P\u00e9rez M, Kelly R, Iqbal N, Chandelier F, Rex D. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut. 2017;68:2017. https:\/\/doi.org\/10.1136\/gutjnl-2017-314547.","journal-title":"Gut"},{"key":"1007_CR28","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1159\/000481227","volume":"93","author":"Y Komeda","year":"2017","unstructured":"Komeda Y, Handa H, Watanabe T, Nomura T, Kitahashi M, Sakurai T, Okamoto A, Minami T, Kono M, Arizumi T, Takenaka M, Hagiwara S, Matsui S, Nishida N, Kashida H, Kudo M. Computer-aided diagnosis based on convolutional neural network system for colorectal polyp classification: preliminary experience. Oncology. 2017;93:30\u20134. https:\/\/doi.org\/10.1159\/000481227.","journal-title":"Oncology"},{"key":"1007_CR29","doi-asserted-by":"crossref","unstructured":"Hsu C, Hsu C, Hsu Z, Shih F, Chang M, Chen T. Colorectal polyp image detection and classification through grayscale images and deep learning. Sensors 2021;","DOI":"10.3390\/s21185995"},{"key":"1007_CR30","doi-asserted-by":"publisher","unstructured":"Lo C-M, Yeh Y-H, Tang J-H, Chang C-C, Yeh H-J. Rapid polyp classification in colonoscopy using textural and convolutional features. Healthcare 2022;10(8) . https:\/\/doi.org\/10.3390\/healthcare10081494","DOI":"10.3390\/healthcare10081494"},{"key":"1007_CR31","doi-asserted-by":"crossref","unstructured":"Mesejo P, Pizarro D, Abergel A, Rouquette O, Beorchia S, Poincloux L, Bartoli A. Computer-aided classification of gastrointestinal lesions in regular colonoscopy. IEEE Trans Med Imaging 2016;35","DOI":"10.1109\/TMI.2016.2547947"},{"issue":"4","key":"1007_CR32","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1016\/j.gie.2020.07.060","volume":"93","author":"M Misawa","year":"2021","unstructured":"Misawa M, Kudo S-E, Mori Y, Hotta K, Ohtsuka K, Matsuda T, Saito S, Kudo T, Baba T, Ishida F, et al. Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video). Gastrointest Endosc. 2021;93(4):960\u20137.","journal-title":"Gastrointest Endosc"},{"issue":"1","key":"1007_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12938-022-01001-x","volume":"21","author":"A Krenzer","year":"2022","unstructured":"Krenzer A, Makowski K, Hekalo A, Fitting D, Troya J, Zoller WG, Hann A, Puppe F. Fast machine learning annotation in the medical domain: a semi-automated video annotation tool for gastroenterologists. Biomed Eng Online. 2022;21(1):1\u201323.","journal-title":"Biomed Eng Online"},{"key":"1007_CR34","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1055\/a-0828-7541","volume":"07","author":"H Ribeiro","year":"2019","unstructured":"Ribeiro H, Libanio D, Castro R, Ferreira A, Barreiro P, Carvalho P, Capela T, Pimentel-Nunes P, Santos C, Dinis-Ribeiro M. Reliability of paris classification for superficial neoplastic gastric lesions improves with training and narrow band imaging. Endosc Int Open. 2019;07:633\u201340. https:\/\/doi.org\/10.1055\/a-0828-7541.","journal-title":"Endosc Int Open"},{"key":"1007_CR35","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1007_CR36","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y, Yang Z, Zhang Y, Tao D. A Survey on Visual Transformer (2021). arXiv:2012.12556"},{"key":"1007_CR37","unstructured":"Kolesnikov A, Beyer L, Zhai X, Puigcerver J, Yung J, Gelly S, Houlsby N. Large scale learning of general visual representations for transfer. CoRR arXiv:abs\/1912.11370 (2019)."},{"key":"1007_CR38","unstructured":"Tan M, Le QV. Efficientnet: Rethinking model scaling for convolutional neural networks. CoRR arXiv:abs\/1905.11946 (2019)."},{"key":"1007_CR39","doi-asserted-by":"publisher","unstructured":"Wang Y, Quanming Y, Kwok JT, Ni LM. Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv 2020;1 https:\/\/doi.org\/10.1145\/3386252","DOI":"10.1145\/3386252"},{"key":"1007_CR40","unstructured":"Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaption of deep networks. In: Proceedings of the 34th international conference on machine learning, 2017;1126\u20131135"},{"key":"1007_CR41","unstructured":"Edwards H, Storkey A. Towards a neural statistician. In: International conference on learning representations 2017;"},{"key":"1007_CR42","unstructured":"Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D. Matching networks for one shot learning. Adv Neural Inf Process Syst 2016;29"},{"key":"1007_CR43","unstructured":"Snell J, Swersky K, Zemel RS. Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 2017;30"},{"key":"1007_CR44","doi-asserted-by":"crossref","unstructured":"Musgrave K, Belongie S, Lim S. A metric learning reality check 2020;","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"1007_CR45","first-page":"737","volume":"6","author":"J Bromley","year":"1994","unstructured":"Bromley J, Guyon I, LeCun Y, S\u00e4ckinger E, Shah R. Signature verification using a \u201csiamese\u2019\u2019 time delay neural network. Adv Neural Inf Process Syst. 1994;6:737\u201344.","journal-title":"Adv Neural Inf Process Syst"},{"key":"1007_CR46","unstructured":"Koch G. Siamese neural networks for one-shot image recognition. In: Proceedings of the 32nd international conference on machine learning 2015;37"},{"key":"1007_CR47","doi-asserted-by":"crossref","unstructured":"Hoffer E, Ailon N. Deep metric learning using triplet network. In: Similarity-Based Pattern Recognition, 2015;84\u201392","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"1007_CR48","unstructured":"Liu W, Wen Y, Yu Z, Yang M. Large-margin softmax loss for convolutional neural networks. In: Proceedings of the internatinoal conference on machine learning, 2016;507\u2013516"},{"key":"1007_CR49","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Xue N, Zafeiriou S. Arcface: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE conference. on computer vision and pattern recognition 2019","DOI":"10.1109\/CVPR.2019.00482"},{"key":"1007_CR50","doi-asserted-by":"crossref","unstructured":"Kaya M, Bilge H. Deep metric learning: a survey. Symmetry 2019;11","DOI":"10.3390\/sym11091066"},{"key":"1007_CR51","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20:273\u201397.","journal-title":"Mach Learn"},{"key":"1007_CR52","doi-asserted-by":"crossref","unstructured":"Cimpoi M, Maji S, Kokkinos I, Mohamed S, Vedaldi A. Describing textures in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"1007_CR53","doi-asserted-by":"crossref","unstructured":"Harwood B, Kumar B, Carneiro G, Reid I, Drummond T. Smart mining for deep metric learning. In: Proceedings of the IEEE international conference on computer vision, 2017;2821\u20132829","DOI":"10.1109\/ICCV.2017.307"},{"key":"1007_CR54","doi-asserted-by":"crossref","unstructured":"Arnold M, Ghosh A, Ameling S, Lacey G. Automatic segmentation and inpainting of specular highlights for endoscopic imaging. EURASIP J Image Video Process 2010","DOI":"10.1155\/2010\/814319"},{"key":"1007_CR55","unstructured":"Grill J, Strub F, Altch\u00e9 F, Tallec C, Richemond PH, Buchatskaya E, Doersch C, Pires BA, Guo ZD, Azar MG, Piot B, Kavukcuoglu K, Munos R, Valko M. Bootstrap your own latent. a new approach to self-supervised learning. Adv Neural Inf Process Syst 2020;33"},{"key":"1007_CR56","doi-asserted-by":"crossref","unstructured":"Kramer MA. Nonlinear principal component analysis using autoassociative neural networks. AIChE 1991;37","DOI":"10.1002\/aic.690370209"},{"key":"1007_CR57","doi-asserted-by":"publisher","unstructured":"Schoeffmann K, Szkaliczki T, Fabro MD, B\u00f6sz\u00f6rmenyi L. Keyframe exraction in endoscopic video. Multimedia Tools Appl 2014; 74. https:\/\/doi.org\/10.1007\/s11042-014-2224-7","DOI":"10.1007\/s11042-014-2224-7"},{"key":"1007_CR58","unstructured":"Roweis S, Hinton G. Stochastic neighor embedding. Neural Inf Process Syst 2002;15"},{"key":"1007_CR59","doi-asserted-by":"crossref","unstructured":"Huang X, Belongie S. Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the international conference on computer vision (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"1007_CR60","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, 2017; pp. 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"1007_CR61","doi-asserted-by":"crossref","unstructured":"Mongan J, Moy L, Kahn\u00a0Jr CE. Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiol Soc North Am 2020","DOI":"10.1148\/ryai.2020200029"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-023-01007-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-023-01007-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-023-01007-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T14:55:28Z","timestamp":1682002528000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-023-01007-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,20]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["1007"],"URL":"https:\/\/doi.org\/10.1186\/s12880-023-01007-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2106189\/v1","asserted-by":"object"}]},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,20]]},"assertion":[{"value":"26 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study including retrospective and prospective collection of examination videos and reports was approved by the responsible institutional review board (Ethical committee Landes\u00e4rztekammer Baden-W\u00fcrttemberg, 21st of January 2021, F-2020-158). All methods were carried out in accordance with relevant guidelines and regulations. Informed consent was obtained from all subjects and\/or their legal guardian(s).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"59"}}