{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:12:02Z","timestamp":1789517522028,"version":"build-2803163510"},"reference-count":24,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["DEN Open"],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Objectives<\/jats:title><jats:p>Localized autoimmune pancreatitis is difficult to differentiate from pancreatic ductal adenocarcinoma on endoscopic ultrasound images. In recent years, deep learning methods have improved the diagnosis of diseases. Hence, we developed a special cross\u2010validation framework to search for effective methodologies of deep learning in distinguishing autoimmune pancreatitis from pancreatic ductal adenocarcinoma on endoscopic ultrasound images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Data from 24 patients diagnosed with localized autoimmune pancreatitis\u00a0(8751 images) and 61 patients diagnosed with pancreatic ductal adenocarcinoma (20,584 images) were collected from 2016 to 2022. We applied transfer learning to a convolutional neural network called ResNet152, together with our innovative imaging method contributing to data augmentation and temporal data process. We divided patients into five groups according to different factors for 5\u2010fold cross\u2010validation, where the ordered and balanced datasets were created for the performance evaluations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>ResNet152 surpassed the endoscopists in all evaluation metrics with almost all datasets. Interestingly, when the dataset is balanced according to the factor of the endoscopists\u2019 diagnostic accuracy, the area under the receiver operating characteristic curve and accuracy were highest at 0.85 and 0.80, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>It is deduced that image features useful for ResNet152 correlate with those used by endoscopists for their diagnoses. This finding may contribute to sample\u2010efficient dataset preparation to train convolutional neural networks for endoscopic ultrasonography\u2010imaging diagnosis.<\/jats:p><\/jats:sec>","DOI":"10.1002\/deo2.344","type":"journal-article","created":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T13:45:30Z","timestamp":1709387130000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning"],"prefix":"10.1002","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4617-8385","authenticated-orcid":false,"given":"Hitomi","family":"Nakamura","sequence":"first","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Motohisa","family":"Fukuda","sequence":"additional","affiliation":[{"name":"Department of Science Faculty of Science Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akiko","family":"Matsuda","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naohiko","family":"Makino","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirohito","family":"Kimura","sequence":"additional","affiliation":[{"name":"Institute of Well\u2010Being Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Ohtaki","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshihito","family":"Nawa","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soushi","family":"Oyama","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuya","family":"Suzuki","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshikazu","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tetsuya","family":"Ishizawa","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuharu","family":"Kakizaki","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshiyuki","family":"Ueno","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology Faculty of Medicine Yamagata University  Yamagata Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,3,2]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21708"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2020.10.007"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/MPA.0b013e3182142fd2"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11091653"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2020.01.034"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2010.10.045"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0031-1291716"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10121005"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021203555"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2033909"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2018.04.003"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2020-322821"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.14309\/ctg.0000000000000045"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/jhbp.825"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/ajg.2012.20"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1590\/s0004-2803.202000000-27"},{"key":"e_1_2_7_19_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ(eds.)Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 27\u201330 Jun 2016 Las Vegas NV 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_7_20_1","unstructured":"PaszkeA GrossS MassaFet\u00a0al.PyTorch: An imperative style high\u2010performance deep learning library. In: NeurIPS 2019. 33rd Conference on Neural Information Processing Systems; 8\u201314 Dec 2019 Vancouver Canada 2019; 8026\u201337."},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_2_7_22_1","unstructured":"KokhlikyanN MiglaniV MartinMet\u00a0al.Captum: A unified and generic model interpretability library for PyTorch.2020."},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101714"},{"key":"e_1_2_7_25_1","volume-title":"Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning","author":"Basu S","year":"2022"}],"container-title":["DEN Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/deo2.344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T06:49:30Z","timestamp":1755067770000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/deo2.344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,2]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["10.1002\/deo2.344"],"URL":"https:\/\/doi.org\/10.1002\/deo2.344","archive":["Portico"],"relation":{},"ISSN":["2692-4609","2692-4609"],"issn-type":[{"value":"2692-4609","type":"print"},{"value":"2692-4609","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,2]]},"assertion":[{"value":"2023-11-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e344"}}