{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:38:23Z","timestamp":1759970303860,"version":"build-2065373602"},"reference-count":18,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T00:00:00Z","timestamp":1736726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Background: Capsule endoscopy (CE) improved the digestive tract assessment; yet, its reading burden is substantial. Deep-learning (DL) algorithms were developed for the detection of enteric and gastric lesions. Nonetheless, their application in the esophagus lacks evidence. The study aim was to develop a DL model for esophageal pleomorphic lesion (PL) detection. Methods: A bicentric retrospective study was conducted using 598 CE exams. Three different CE devices provided 7982 esophageal frames, including 2942 PL lesions. The data were divided into the training\/validation and test groups, in a patient-split design. Three runs were conducted, each with unique patient sets. The sensitivity, specificity, accuracy, positive and negative predictive value (PPV and NPV), area under the conventional receiver operating characteristic curve (AUC-ROC), and precision\u2013recall curve (AUC-PR) were calculated per run. The model\u2019s diagnostic performance was assessed using the median and range values. Results: The median sensitivity, specificity, PPV, and NPV were 75.8% (63.6\u201382.1%), 95.8% (93.7\u201397.9%), 71.9% (50.0\u201390.1%), and 96.4% (94.2\u201397.6%), respectively. The median accuracy was 93.5% (91.8\u201393.8%). The median AUC-ROC and AUC-PR were 0.82 and 0.93. Conclusions: This study focused on the automatic detection of pleomorphic esophageal lesions, potentially enhancing the diagnostic yield of this type of lesion, compared to conventional methods. Specific esophageal DL algorithms may provide a significant contribution and bridge the gap for the implementation of minimally invasive CE-enhanced panendoscopy.<\/jats:p>","DOI":"10.3390\/app15020709","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T07:40:08Z","timestamp":1736754008000},"page":"709","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions\u2014A Necessary Step for Minimally Invasive Panendoscopy"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0484-4804","authenticated-orcid":false,"given":"Miguel","family":"Martins","sequence":"first","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0340-0830","authenticated-orcid":false,"given":"Miguel","family":"Mascarenhas","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"},{"name":"Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal"}]},{"given":"Maria Jo\u00e3o","family":"Almeida","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"}]},{"given":"Jo\u00e3o","family":"Afonso","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"}]},{"given":"Tiago","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9427-5635","authenticated-orcid":false,"given":"Pedro","family":"Cardoso","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5890-7049","authenticated-orcid":false,"given":"Francisco","family":"Mendes","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"}]},{"given":"Joana","family":"Mota","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"}]},{"given":"Patr\u00edcia","family":"Andrade","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"},{"name":"Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal"}]},{"given":"H\u00e9lder","family":"Cardoso","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"},{"name":"Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal"}]},{"given":"Miguel","family":"Mascarenhas-Saraiva","sequence":"additional","affiliation":[{"name":"Gastroenterology Department, ManopH, Instituto CUF, 4460-188 Porto, Portugal"}]},{"given":"Jo\u00e3o","family":"Ferreira","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9387-9872","authenticated-orcid":false,"given":"Guilherme","family":"Macedo","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, S\u00e3o Jo\u00e3o University Hospital, 4200-437 Porto, Portugal"},{"name":"WGO Gastroenterology and Hepatology Training Center, 4200-047 Porto, Portugal"},{"name":"Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1055\/a-1973-3796","article-title":"Small-bowel capsule endoscopy and device-assisted enteroscopy for diagnosis and treatment of small-bowel disorders: European Society of Gastrointestinal Endoscopy (ESGE) Guideline\u2014Update 2022","volume":"55","author":"Pennazio","year":"2023","journal-title":"Endoscopy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1177\/2050640619850365","article-title":"Performance measures for small-bowel endoscopy: A European Society of Gastrointestinal Endoscopy (ESGE) Quality Improvement Initiative","volume":"7","author":"Spada","year":"2019","journal-title":"United Eur. Gastroenterol. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"E1860","DOI":"10.1055\/a-1548-6572","article-title":"Colon capsule for panendoscopy: A narrow window of opportunity","volume":"9","author":"Rondonotti","year":"2021","journal-title":"Endosc. Int. Open"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, Y.P., Karmakar, R., Mukundan, A., Tsao, Y.M., Sung, T.C., Lu, C.L., and Wang, H.C. (2024). Spectrum aided vision enhancer enhances mucosal visualization by hyperspectral imaging in capsule endoscopy. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-73387-8"},{"key":"ref_5","unstructured":"Mascarenhas, M., Cardoso, H., and Macedo, G. (2023). Chapter 15\u2014Colon capsule endoscopy and artificial intelligence: A perfect match for panendoscopy. Artificial Intelligence in Capsule Endoscopy, Academic Press."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e00609","DOI":"10.14309\/ctg.0000000000000609","article-title":"Deep Learning and Minimally Invasive Endoscopy: Automatic Classification of Pleomorphic Gastric Lesions in Capsule Endoscopy","volume":"14","author":"Mascarenhas","year":"2023","journal-title":"Clin. Transl. Gastroenterol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"317","DOI":"10.5946\/ce.2018.101","article-title":"Current and Future Use of Esophageal Capsule Endoscopy","volume":"51","author":"Park","year":"2018","journal-title":"Clin. Endosc."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1016\/j.bpg.2016.09.005","article-title":"Complications of diagnostic colonoscopy, upper endoscopy, and enteroscopy","volume":"30","author":"Levy","year":"2016","journal-title":"Best. Pract. Res. Clin. Gastroenterol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1038\/ajg.2009.86","article-title":"A meta-analysis of the diagnostic accuracy of esophageal capsule endoscopy for Barrett\u2019s esophagus in patients with gastroesophageal reflux disease","volume":"104","author":"Bhardwaj","year":"2009","journal-title":"Am. J. Gastroenterol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1097\/MCG.0000000000000589","article-title":"Use of Wireless Capsule Endoscopy for the Diagnosis and Grading of Esophageal Varices in Patients With Portal Hypertension: A Systematic Review and Meta-Analysis","volume":"51","author":"McCarty","year":"2017","journal-title":"J. Clin. Gastroenterol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1055\/a-1950-5694","article-title":"Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement","volume":"54","author":"Messmann","year":"2022","journal-title":"Endoscopy"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mascarenhas, M., Cardoso, H., and Macedo, G. (2023). Chapter 1\u2014Artificial intelligence: Machine learning, deep learning, and applications in gastrointestinal endoscopy. Artificial Intelligence in Capsule Endoscopy, Academic Press.","DOI":"10.1016\/B978-0-323-99647-1.00003-4"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Moutik, O., Sekkat, H., Tigani, S., Chehri, A., Saadane, R., Tchakoucht, T.A., and Paul, A. (2023). Convolutional Neural Networks or Vision Transformers: Who Will Win the Race for Action Recognitions in Visual Data?. Sensors, 23.","DOI":"10.3390\/s23020734"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"E171","DOI":"10.1055\/a-1675-1941","article-title":"Deep learning and colon capsule endoscopy: Automatic detection of blood and colonic mucosal lesions using a convolutional neural network","volume":"10","author":"Mascarenhas","year":"2022","journal-title":"Endosc. Int. Open"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e000753","DOI":"10.1136\/bmjgast-2021-000753","article-title":"Deep learning and capsule endoscopy: Automatic identification and differentiation of small bowel lesions with distinct haemorrhagic potential using a convolutional neural network","volume":"8","author":"Afonso","year":"2021","journal-title":"BMJ Open Gastroenterol."},{"key":"ref_16","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., and Jegou, H. (2021, January 18\u201324). Training data-efficient image transformers & distillation through attention. Proceedings of the 38th International Conference on Machine Learning, Online."},{"key":"ref_17","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosam","year":"2011","journal-title":"J. Mach. Learn."},{"key":"ref_18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/2\/709\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:27:34Z","timestamp":1759919254000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/2\/709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,13]]},"references-count":18,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["app15020709"],"URL":"https:\/\/doi.org\/10.3390\/app15020709","relation":{},"ISSN":["2076-3417"],"issn-type":[{"type":"electronic","value":"2076-3417"}],"subject":[],"published":{"date-parts":[[2025,1,13]]}}}