Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities

This study investigates the application of artificial intelligence (AI) for the automatic detection of pathological abnormalities in gastrointestinal endoscopic images. Specifically, it evaluates the performance of an AI tool in identifying and classifying lesions such as polyps and other irregular...

Full description

Saved in:
Bibliographic Details
Main Authors: Weronika Jarych, Elżbieta Tokarczyk, Patryk Iglewski, Daria Ziemińska, Karina Motolko, Rafał Burczyk, Konrad Duszyński, Michał Kociński, Jan Reinald Wendt
Format: Article
Language:English
Published: Nicolaus Copernicus University in Toruń 2025-05-01
Series:Quality in Sport
Subjects:
Online Access:https://apcz.umk.pl/QS/article/view/60070
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850189689933266944
author Weronika Jarych
Elżbieta Tokarczyk
Patryk Iglewski
Daria Ziemińska
Karina Motolko
Rafał Burczyk
Konrad Duszyński
Michał Kociński
Jan Reinald Wendt
author_facet Weronika Jarych
Elżbieta Tokarczyk
Patryk Iglewski
Daria Ziemińska
Karina Motolko
Rafał Burczyk
Konrad Duszyński
Michał Kociński
Jan Reinald Wendt
author_sort Weronika Jarych
collection DOAJ
description This study investigates the application of artificial intelligence (AI) for the automatic detection of pathological abnormalities in gastrointestinal endoscopic images. Specifically, it evaluates the performance of an AI tool in identifying and classifying lesions such as polyps and other irregularities, including inflammatory changes, within real-time endoscopic procedures. The primary objective is to assess the tool's diagnostic accuracy and its potential to improve lesion detection, thereby reducing the likelihood of overlooked abnormalities. Leveraging advanced machine learning techniques, particularly convolutional neural networks (CNNs), the AI system aims to enhance diagnostic precision and support clinicians in making prompt, evidence-based decisions. Key advantages of AI integration in endoscopy include improved sensitivity, minimized detection errors, and the potential to optimize clinical workflow efficiency. However, the study also addresses significant challenges, including the necessity for large, heterogeneous datasets for model validation, the need for standardized AI applications, and the ethical implications of AI-assisted clinical decision-making. Additionally, the potential benefits of combining AI with complementary imaging technologies, such as fluorescence imaging and spectroscopy, are explored to further enhance diagnostic capabilities. In conclusion, the study highlights the promising role of AI in gastrointestinal endoscopy while underscoring the importance of continued research, algorithmic refinement, and the establishment of regulatory frameworks to fully harness its clinical potential.
format Article
id doaj-art-d60c04afc5cb40a4b22646bfdc2ad378
institution OA Journals
issn 2450-3118
language English
publishDate 2025-05-01
publisher Nicolaus Copernicus University in Toruń
record_format Article
series Quality in Sport
spelling doaj-art-d60c04afc5cb40a4b22646bfdc2ad3782025-08-20T02:15:33ZengNicolaus Copernicus University in ToruńQuality in Sport2450-31182025-05-014110.12775/QS.2025.41.60070Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other IrregularitiesWeronika Jarych0https://orcid.org/0009-0009-1335-8072Elżbieta Tokarczyk1https://orcid.org/0009-0003-9683-7699Patryk Iglewski2https://orcid.org/0009-0004-6611-2168Daria Ziemińska3https://orcid.org/0009-0001-8240-2593Karina Motolko4https://orcid.org/0009-0001-9971-6687Rafał Burczyk5https://orcid.org/0000-0002-1650-1534Konrad Duszyński6https://orcid.org/0009-0006-5524-8857Michał Kociński7https://orcid.org/0009-0007-7651-7929Jan Reinald Wendt8https://orcid.org/0009-0009-6163-7041Szpital Morski im. PCK w Gdyni, Powstania Styczniowego 1, 81-519 Gdynia, PolandSzpital św. Wincentego a Paulo w Gdyni, ul. Wójta Radtkego 1, 81-348 GdyniaWojewódzki Szpital Zespolony im. L. Rydygiera w ToruniuSzpital Św. Wincentego a Paulo w Gdyni, ul. Wójta Radtkego 1, 81-348 GdyniaSpecjalistyczny Szpital Miejski im. M. Kopernika w Toruniu, ul. Stefana Batorego 17/19, 87-100 ToruńSzpital Uniwersytecki nr 2 im. dr J. Biziela, ul. Ujejskiego 75, 85-168 BydgoszczStudenckie Koło Naukowe Okulistyki, Gdański Uniwersytet Medyczny, ul. Marii Skłodowskiej-Curie 3a, 80-210 GdańskCollegium Medicum in Bydgoszcz: Bydgoszcz, Kujawsko-Pomorskie, PLSzpital Św. Wincentego a Paulo w Gdyni, ul. Wójta Radtkego 1, 81-348 Gdynia This study investigates the application of artificial intelligence (AI) for the automatic detection of pathological abnormalities in gastrointestinal endoscopic images. Specifically, it evaluates the performance of an AI tool in identifying and classifying lesions such as polyps and other irregularities, including inflammatory changes, within real-time endoscopic procedures. The primary objective is to assess the tool's diagnostic accuracy and its potential to improve lesion detection, thereby reducing the likelihood of overlooked abnormalities. Leveraging advanced machine learning techniques, particularly convolutional neural networks (CNNs), the AI system aims to enhance diagnostic precision and support clinicians in making prompt, evidence-based decisions. Key advantages of AI integration in endoscopy include improved sensitivity, minimized detection errors, and the potential to optimize clinical workflow efficiency. However, the study also addresses significant challenges, including the necessity for large, heterogeneous datasets for model validation, the need for standardized AI applications, and the ethical implications of AI-assisted clinical decision-making. Additionally, the potential benefits of combining AI with complementary imaging technologies, such as fluorescence imaging and spectroscopy, are explored to further enhance diagnostic capabilities. In conclusion, the study highlights the promising role of AI in gastrointestinal endoscopy while underscoring the importance of continued research, algorithmic refinement, and the establishment of regulatory frameworks to fully harness its clinical potential. https://apcz.umk.pl/QS/article/view/60070Artificial intelligenceendoscopygastrointestinal imagingpolyps detectioncomputer-aided detectionconvolutional neural networks
spellingShingle Weronika Jarych
Elżbieta Tokarczyk
Patryk Iglewski
Daria Ziemińska
Karina Motolko
Rafał Burczyk
Konrad Duszyński
Michał Kociński
Jan Reinald Wendt
Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities
Quality in Sport
Artificial intelligence
endoscopy
gastrointestinal imaging
polyps detection
computer-aided detection
convolutional neural networks
title Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities
title_full Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities
title_fullStr Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities
title_full_unstemmed Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities
title_short Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities
title_sort automated recognition of abnormalities in gastrointestinal endoscopic images evaluation of an ai tool for identifying polyps and other irregularities
topic Artificial intelligence
endoscopy
gastrointestinal imaging
polyps detection
computer-aided detection
convolutional neural networks
url https://apcz.umk.pl/QS/article/view/60070
work_keys_str_mv AT weronikajarych automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT elzbietatokarczyk automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT patrykiglewski automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT dariazieminska automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT karinamotolko automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT rafałburczyk automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT konradduszynski automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT michałkocinski automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities
AT janreinaldwendt automatedrecognitionofabnormalitiesingastrointestinalendoscopicimagesevaluationofanaitoolforidentifyingpolypsandotherirregularities