Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniv Klinikum Augsburg-
Autor(es): dc.contributorOstbayer TH Regensburg-
Autor(es): dc.contributorUniv British Columbia-
Autor(es): dc.contributorOstalb Klinikum Aalen-
Autor(es): dc.contributorUniversidade Federal de São Carlos (UFSCar)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorEbigbo, Alanna-
Autor(es): dc.creatorMendel, Robert-
Autor(es): dc.creatorScheppach, Markus W.-
Autor(es): dc.creatorProbst, Andreas-
Autor(es): dc.creatorShahidi, Neal-
Autor(es): dc.creatorPrinz, Friederike-
Autor(es): dc.creatorFleischmann, Carola-
Autor(es): dc.creatorRoemmele, Christoph-
Autor(es): dc.creatorGoelder, Stefan Karl-
Autor(es): dc.creatorBraun, Georg-
Autor(es): dc.creatorRauber, David-
Autor(es): dc.creatorRueckert, Tobias-
Autor(es): dc.creatorSouza Jr, Luis A. de-
Autor(es): dc.creatorPapa, Joao-
Autor(es): dc.creatorByrne, Michael-
Autor(es): dc.creatorPalm, Christoph-
Autor(es): dc.creatorMessmann, Helmut-
Data de aceite: dc.date.accessioned2025-08-21T15:47:43Z-
Data de disponibilização: dc.date.available2025-08-21T15:47:43Z-
Data de envio: dc.date.issued2022-11-29-
Data de envio: dc.date.issued2022-11-29-
Data de envio: dc.date.issued2022-09-15-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1136/gutjnl-2021-326470-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/237698-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/237698-
Descrição: dc.descriptionIn this study, we aimed to develop an artificial intelligence clinical decision support solution to mitigate operator-dependent limitations during complex endoscopic procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy, for example, bleeding and perforation. A DeepLabv3-based model was trained to delineate vessels, tissue structures and instruments on endoscopic still images from such procedures. The mean cross-validated Intersection over Union and Dice Score were 63% and 76%, respectively. Applied to standardised video clips from third-space endoscopic procedures, the algorithm showed a mean vessel detection rate of 85% with a false-positive rate of 0.75/min. These performance statistics suggest a potential clinical benefit for procedure safety, time and also training.-
Descrição: dc.descriptionUniv Klinikum Augsburg, Dept Gastroenterol, D-86156 Augsburg, Bayern, Germany-
Descrição: dc.descriptionOstbayer TH Regensburg, Regensburg Med Image Comp ReMIC, Regensburg, Germany-
Descrição: dc.descriptionUniv British Columbia, Dept Med, Vancouver, BC, Canada-
Descrição: dc.descriptionOstalb Klinikum Aalen, Dept Gastroenterol, Aalen, Germany-
Descrição: dc.descriptionUniv Fed Sao Carlos, Dept Comp, Sao Carlos, Brazil-
Descrição: dc.descriptionSao Paulo State Univ, Dept Comp, Botucatu, SP, Brazil-
Descrição: dc.descriptionUniv British Columbia, Vancouver Gen Hosp, Vancouver, BC, Canada-
Descrição: dc.descriptionSao Paulo State Univ, Dept Comp, Botucatu, SP, Brazil-
Formato: dc.format3-
Idioma: dc.languageen-
Publicador: dc.publisherBmj Publishing Group-
Relação: dc.relationGut-
???dc.source???: dc.sourceWeb of Science-
Palavras-chave: dc.subjectEndoscopic procedures-
Palavras-chave: dc.subjectEndoscopy-
Palavras-chave: dc.subjectSurgical oncology-
Título: dc.titleVessel and tissue recognition during third-space endoscopy using a deep learning algorithm-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.