Third Eye? The Assistance of Artificial Intelligence (AI) in the Endoscopy of Gastrointestinal Neoplasms

Sep 24, 2026

Uploaded by Ben

Gastrointestinal cancers show high incidence and mortality despite established screening approaches. Endoscopy delivers macroscopic images and enables tissue sampling for histopathological diagnosis, yet exam efficiency depends heavily on patient preparation and the operator’s expertise. This narrative review synthesizes recent reports and randomized clinical trials on artificial intelligence, particularly deep learning and neural network tools, for screening and surveillance of esophageal, gastric, and colorectal cancers, highlighting advantages, limitations, and controversies.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Esophageal and Gastric Cancer

Aim and Scope of the Review

Review Third Eye? The Assistance of Artiﬁcial Intelligence (AI) in the Endoscopy of Gastrointestinal Neoplasms Magdalena Le´sniewska 1, Rafał Patryn 2,*, Agnieszka Kopystecka 1, Ilona Kozioł 1 and Julia Budzy ´nska 1 Citation: Le´sniewska, M.; Patryn, R.; Kopystecka, A.; Kozioł, I.; Budzy ´nska, J. Third Eye? The Assistance of Artiﬁcial Intelligence (AI) in the Endoscopy of Gastrointestinal Neoplasms. J. Clin. Med. 2023, 12, 6721. [https://](https://)[ ](https://)[doi.org/10.3390/jcm12216721](doi.org/10.3390/jcm12216721) Academic Editor: Deliang Liu Received: 4 September 2023 Revised: 19 October 2023 Accepted: 21 October 2023 Published: 24 October 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Students' Scientiﬁc Circle on Medical Law at the Department of Humanities and Social Medicine, Medical University of Lublin, 20-093 Lublin, Poland; [lesniewska.w.magdalena@gmail.com](lesniewska.w.magdalena@gmail.com) (M.L.); [aga.kop@interia.eu](aga.kop@interia.eu) (A.K.); [ilona.koziol9@gmail.com](ilona.koziol9@gmail.com) (I.K.); [julciab42@gmail.com](julciab42@gmail.com) (J.B.) 2 Department of Humanities and Social Medicine, Medical University of Lublin, 20-093 Lublin, Poland * Correspondence: [rafal.patryn@umlub.pl](rafal.patryn@umlub.pl) Abstract: Gastrointestinal cancers are characterized by high incidence and mortality. However, there are well-established methods of screening. The endoscopy exam provides the macroscopical image and enables harvesting the tissue samples for further histopathological diagnosis. The efﬁciency of endoscopies relies not only on proper patient preparation, but also on the skills of the personnel conducting the exam. In recent years, a number of reports concerning the application of artiﬁcial intelligence (AI) in medicine have arisen. Numerous studies aimed to assess the utility of deep learning/ neural network systems supporting endoscopies. In this review, we summarized the most recent reports and randomized clinical trials regarding the application of AI in screening and surveillance of gastrointestinal cancers among patients suffering from esophageal, gastric, and colorectal cancer, along with the advantages, limitations, and controversies of those novel solutions. Keywords: artiﬁcial intelligence; endoscopy; gastrointestinal tract; gastric cancer; colorectal cancer; esophageal cancer 1. Introduction Cancers of the gastrointestinal tract, especially of the stomach and large intestine, area frequent cause of death due to malignant neoplasms. For this reason, there is a need to develop new technologies supporting diagnostics, mainly endoscopic methods in detecting gastrointestinal cancers [1] . The gold standard examination for reducing morbidity and mortality in colorectal cancer (CRC) is a colonoscopy with the detection and removal of adenomatous polyps [2–4] . However, in order to reduce morbidity and mortality in cancers of the upper gastrointestinal tract, endoscopic methods are used, such as: confocal laser endomicroscopy and narrow-band imaging [5–8] . Nevertheless, the method largely depends on the experience of the doctor performing the examination. In recent years, the application of artiﬁcial intelligence (AI) in the medical ﬁeld has expanded [9] . The use of artiﬁcial intelligence can support classical methods by reducing the percentage of overlooked changes [1,10] . AI-assisted endoscopy, which uses facial recognition technologies based on AI, can detect abnormal conditions quickly, based on the analysis of colorectal images, thereby reducing the need for nontumor polypectomy [11] . Furthermore, computer-aided endoscopy has a high degree of

FAQs

Why is endoscopy important for gastrointestinal cancer diagnosis?

Endoscopy provides macroscopic visualization and allows tissue harvesting for histopathological diagnosis, enabling more accurate detection of suspicious lesions.

How can AI-assisted endoscopy improve clinical performance?

AI systems can quickly detect abnormal conditions through image/video analysis and reduce overlooked changes, supporting earlier screening and surveillance.

What are the main advantages and challenges of using AI in gastrointestinal endoscopy?

Reported advantages include accuracy and sensitivity for early colorectal cancer diagnosis, but the review also discusses limitations and controversies, alongside the dependence on proper workflows and implementation.

Sep 24, 2026

Uploaded by Ben