Ding JC, Zhang J. Endoscopic image analysis assisted by machine learning: Algorithmic advancements and clinical uses. Artif Intell Gastrointest Endosc 2025; 6(3): 108281 [DOI: 10.37126/aige.v6.i3.108281]
Reader's ID:
08447206
Submitted on:
September 10, 2025, 17:34
Reader Expertise:
Reader’s expertise on the topic of the manuscript
Conflicts-of-Interest Statement:
Does the reader have a conflict of interest?
Reader Comment Standards for Published Articles:
1 Title
Does the title reflect the main subject/hypothesis of the manuscript?
2 Abstract
Does the abstract summarize and reflect the work described in the manuscript?
3 Key Words
Do the key words reflect the focus of the manuscript?
4 Background
Does the manuscript adequately describe the background, present status and significance of the study?
5 Methods
Does the manuscript describe methods (e.g., experiments, data analysis, surveys, and clinical trials, etc.) in adequate detail?
6 Results
Are the research objectives achieved by the experiments used in this study?
Has the study made meaningful contributions towards research progress in this field?
7 Discussion
Does the manuscript interpret the findings adequately and appropriately, highlighting the key points concisely, clearly and logically?
Are the findings and their applicability/relevance to the literature stated in a clear and definite manner?
Is the Discussion accurate and does it discuss the paper’s scientific significance and/or relevance to clinical practice sufficiently?
8 Illustrations and Tables
Are the figures, diagrams and tables sufficient, good quality and appropriately illustrative of the paper contents?
Do figures require labeling with arrows, asterisks, etc., or better legends?
9 Biostatistics
Does the manuscript meet the requirements of biostatistics?
10 Units
Does the manuscript meet the requirements of use of SI units?
11 References
Does the manuscript appropriately cite the latest, important and authoritative references in the Introduction and Discussion sections?
Does the author self-cite, omit, incorrectly cite and/or over-cite references?
12 Quality of manuscript organization and presentation
Is the manuscript concisely and coherently organized and presented?
Are the style, language and grammar accurate and appropriate?
13 Ethics statements
For all manuscripts involving human studies and/or animal experiments, author(s) must submit the related formal ethics documents that were reviewed and approved by their local ethical review committee. Did the manuscript meet the requirements of ethics?
Scientific Quality:
The overall quality of the manuscript, based on the above-listed criteria, should be evaluated and classified according to the following five categories
Language Quality:
Language quality (style, grammar, and spelling) should be evaluated and classified according to the following five categories.
Reader Comments:
With the aid of deep learning, specifically the convolutional neural network, the paradigm of operator dependent endoscopy shifts towards operator independence, being one of the most important/impactful aspects of AI – assisted endoscopic analysis that this minireview focuses on. As stated in this review, there are 3 most common used models of machine learning in clinical applications. So, in order for them to perform at its’ highest capacity, one must master the ability of choosing between them for the clinical applications. Regarding image enhancement, algorithms such as GANs, U-Net variants and DnCNN, have revolutionized endoscopy. Moreover, the shift from 2D to 3D reconstruction technology, allows for on-site evaluations of disease status, therefore providing and enhanced clinical diagnosis. A probably more impactful aid AI provided in endoscopy, is the early diagnosis of malignant tumors, decrease the rate of missed diagnoses, specifically gastric cancer. Trials conducted by Shi et al (1), Arai et al (2), and Chen et al (3), reported remarkable sensitivity and specifity integrated with risk factors, thus providing providing personalized follow up strategies post upper endoscopy.
However, regarding both detecting and classifying colon polyps, Namikawa et al revealed that AI showed superior sensitivity, outperforming experts, albeit with slighty less specificity in a study comparing the capabilities of AI against human experts. Having that in mind, a thorough evaluation and then integration of AI in the decision making process algorithm.
As for non malignant diseases, the most importanat challenge is data heterogeneity and insufficient clinical validation. However, the application of machine learning in inflammatory bowel disease (IBD) shows promise in objective grading of IBD, in reshaping the monitoring paradigm, converging into an “active early warning” system. Moreover, AI models, benefit the IBD clinical trials, by improved endoscopy quality, consistent, valid, real -time assessment of IBD severity at site level, improved patient recruitment, increased sensitivity to responde and patient response to treatment (4).
As with all important innovations, limitations arise, specifically data privacy and annotation quality that hinder model traninig. A study conducted by Buedgens et al (5) reported that weakly supervised AI systems can achieve a high performance and maintain explainability in end-to-end image analysis in GI endoscopy. This shows that manual annotations are not necessarily a bottleneck for future clinical applications of AI.
Finally, in order to provide a much smoother clinical translation of machine learning, expert bodies, such as ASGE and ESGE have provided position statements as for priorities for artificial intelligence in GI endoscopy and expected value of artificial intelligence in gastrointestinal endoscopy, respectively (6,7), therefore offering standardization.
Reply from the Editorial Office:
First, thank you very much for your professional comments on the article published in Artificial Intelligence in Gastrointestinal Endoscopy.
Second, we read your comments with great interest. You are welcome to format your valuable comments into a Letter to the Editor and submit it online to Artificial Intelligence in Gastrointestinal Endoscopy at https://www.f6publishing.com. There are no restrictions on the number of words, figures (color, B/W) or authors for a Letter to the Editor. In addition, the article processing charge will be exempted for this Letter to the Editor. As with all articles published by the Baishideng Publishing Group, the Letter to the Editor will be published online after completing peer review. The guidelines for a Letter to the Editor can be found at: https://www.wjgnet.com/bpg/GerInfo/219.
Finally, we look forward to receiving your high-quality Letter to the Editor, which will promote academic communication and lead the development of this discipline.