Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy

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 deve...

Full description

Saved in:
Bibliographic Details
Main Authors: Miguel Martins, Miguel Mascarenhas, Maria João Almeida, João Afonso, Tiago Ribeiro, Pedro Cardoso, Francisco Mendes, Joana Mota, Patrícia Andrade, Hélder Cardoso, Miguel Mascarenhas-Saraiva, João Ferreira, Guilherme Macedo
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/2/709
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589198114160640
author Miguel Martins
Miguel Mascarenhas
Maria João Almeida
João Afonso
Tiago Ribeiro
Pedro Cardoso
Francisco Mendes
Joana Mota
Patrícia Andrade
Hélder Cardoso
Miguel Mascarenhas-Saraiva
João Ferreira
Guilherme Macedo
author_facet Miguel Martins
Miguel Mascarenhas
Maria João Almeida
João Afonso
Tiago Ribeiro
Pedro Cardoso
Francisco Mendes
Joana Mota
Patrícia Andrade
Hélder Cardoso
Miguel Mascarenhas-Saraiva
João Ferreira
Guilherme Macedo
author_sort Miguel Martins
collection DOAJ
description 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–recall curve (AUC-PR) were calculated per run. The model’s diagnostic performance was assessed using the median and range values. Results: The median sensitivity, specificity, PPV, and NPV were 75.8% (63.6–82.1%), 95.8% (93.7–97.9%), 71.9% (50.0–90.1%), and 96.4% (94.2–97.6%), respectively. The median accuracy was 93.5% (91.8–93.8%). 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.
format Article
id doaj-art-8aa0ef6f1595488e86da6579d09c6497
institution Kabale University
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-8aa0ef6f1595488e86da6579d09c64972025-01-24T13:20:33ZengMDPI AGApplied Sciences2076-34172025-01-0115270910.3390/app15020709Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive PanendoscopyMiguel Martins0Miguel Mascarenhas1Maria João Almeida2João Afonso3Tiago Ribeiro4Pedro Cardoso5Francisco Mendes6Joana Mota7Patrícia Andrade8Hélder Cardoso9Miguel Mascarenhas-Saraiva10João Ferreira11Guilherme Macedo12Department of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalGastroenterology Department, ManopH, Instituto CUF, 4460-188 Porto, PortugalDepartment of Mechanical Engineering, Faculty of Engineering, University of Porto, 4200-465 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, 4200-437 Porto, PortugalBackground: 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–recall curve (AUC-PR) were calculated per run. The model’s diagnostic performance was assessed using the median and range values. Results: The median sensitivity, specificity, PPV, and NPV were 75.8% (63.6–82.1%), 95.8% (93.7–97.9%), 71.9% (50.0–90.1%), and 96.4% (94.2–97.6%), respectively. The median accuracy was 93.5% (91.8–93.8%). 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.https://www.mdpi.com/2076-3417/15/2/709capsule endoscopypanendoscopyartificial intelligenceesophageal lesions
spellingShingle Miguel Martins
Miguel Mascarenhas
Maria João Almeida
João Afonso
Tiago Ribeiro
Pedro Cardoso
Francisco Mendes
Joana Mota
Patrícia Andrade
Hélder Cardoso
Miguel Mascarenhas-Saraiva
João Ferreira
Guilherme Macedo
Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy
Applied Sciences
capsule endoscopy
panendoscopy
artificial intelligence
esophageal lesions
title Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy
title_full Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy
title_fullStr Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy
title_full_unstemmed Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy
title_short Deep Learning and Automatic Detection of Pleomorphic Esophageal Lesions—A Necessary Step for Minimally Invasive Panendoscopy
title_sort deep learning and automatic detection of pleomorphic esophageal lesions a necessary step for minimally invasive panendoscopy
topic capsule endoscopy
panendoscopy
artificial intelligence
esophageal lesions
url https://www.mdpi.com/2076-3417/15/2/709
work_keys_str_mv AT miguelmartins deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT miguelmascarenhas deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT mariajoaoalmeida deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT joaoafonso deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT tiagoribeiro deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT pedrocardoso deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT franciscomendes deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT joanamota deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT patriciaandrade deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT heldercardoso deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT miguelmascarenhassaraiva deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT joaoferreira deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy
AT guilhermemacedo deeplearningandautomaticdetectionofpleomorphicesophageallesionsanecessarystepforminimallyinvasivepanendoscopy