Next Article in Journal
Evolving Therapeutic Algorithms in Chronic Myeloid Leukemia: Integrating Efficacy, Safety, and Survivorship
Previous Article in Journal
Effects of Treatment with Glucagon-like Peptide-1 Receptor Analogues on the Diabetic Foot
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Biomedicines
Volume 14
Issue 2
10.3390/biomedicines14020407
biomedicines-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Viewpoint

Transforming Gastric Biopsy Diagnostics: Integrating Omics Technologies and Artificial Intelligence

by
Nasar Alwahaibi
Department of Biomedical Science, College of Medicine and Health Sciences, Sultan Qaboos University, P.O. Box 35, Muscat 123, Oman
Biomedicines 2026, 14(2), 407; https://doi.org/10.3390/biomedicines14020407
Submission received: 12 January 2026 / Revised: 2 February 2026 / Accepted: 9 February 2026 / Published: 11 February 2026
(This article belongs to the Section Molecular and Translational Medicine)
Browse Figures
Review Reports Versions Notes

Abstract

Background: Gastric biopsy remains central to diagnosing Helicobacter pylori infection, autoimmune gastritis, intestinal metaplasia, dysplasia, and gastric cancer. However, morphology-based assessment is limited by interobserver variability, sampling constraints, and an incomplete ability to capture molecular heterogeneity and predict progression. Objective: This mini review summarizes how multi-omics technologies and artificial intelligence (AI) are modernizing gastric biopsy diagnostics, enabling precision classification, risk stratification, and workflow improvement. Methods: A narrative synthesis was undertaken across key literature on gastric pathology, multi-omics (genomics, transcriptomics, epigenomics, proteomics, lipidomics, metabolomics, microbiomics, and spatial approaches), and AI in endoscopy and computational pathology. Results: Multi-omics profiling enhances mechanistic understanding and refines disease classification by capturing clonal evolution, pathway dysregulation, immune–microenvironment interactions, and metabolic remodeling, with potential for biomarker discovery and therapy prediction. AI applications demonstrate strong performance across the gastric diagnostic pathway, including improved lesion detection during endoscopy, reduced miss rates, lesion segmentation, classification of precancerous conditions, H. pylori recognition, and near-expert histopathology classification. Evidence from systematic reviews supports robust diagnostic accuracy, while prospective studies highlight real-time feasibility. Conclusions: Integrating AI with multi-omics is shifting gastric biopsy from descriptive histology toward data-driven precision gastroenterology. Key barriers include dataset quality, standardization, interpretability, cost, and regulatory and ethical governance; addressing these will be essential for routine clinical adoption.

Graphical Abstract

1. Introduction

Gastric biopsy is a cornerstone in the diagnosis and management of a wide spectrum of gastrointestinal disorders, including Helicobacter pylori infection, autoimmune gastritis, intestinal metaplasia, dysplasia, and diverse forms of gastric cancer [1,2,3]. Conventional diagnostic practice relies on histomorphology supported by immunohistochemistry to classify disease entities, grade severity, and guide initial clinical decisions [4,5]. Despite its enduring value, this paradigm provides an incomplete view of the biological complexity within the gastric mucosa, where heterogeneous cellular states and dynamic microenvironmental interactions influence disease behavior [6]. Overlapping morphologic features, sampling limitations, and inter- and intra-observer variability can contribute to diagnostic uncertainty, particularly in subtle dysplasia, early neoplasia, and multifocal or heterogeneous lesions, while also limiting prediction of progression and therapeutic responsiveness [7,8,9,10,11,12,13,14,15,16].
Recent advances in omics technologies offer powerful solutions to these challenges by enabling high-resolution interrogation of gastric disease at genomic, transcriptomic, epigenomic, proteomic, metabolomic, lipidomic, microbiomic, single-cell, and spatial levels [17,18,19,20,21]. These approaches capture clonal evolution, pathway dysregulation, metabolic remodeling, and immune–stromal interactions, thereby complementing and, in some con-texts, refining traditional diagnostic categories [19,20,21]. In parallel, artificial intelligence (AI) has emerged as a transformative tool across gastrointestinal diagnostics. Deep learning can detect subtle morphologic patterns and quantify features objectively, while ma-chine learning approaches integrate imaging, molecular data, and clinical variables to support risk stratification and prognostication [22,23,24,25,26,27,28,29,30].
Together, AI and multi-omics are repositioning gastric biopsy from a predominantly morphology-based test toward a comprehensive platform for precision gastroenterology and oncology, with the potential to enhance diagnostic accuracy, personalize management, and improve workflow efficiency [31,32,33,34,35]. Figure 1 provides an overview of how artificial intelligence and multi-omics technologies integrate with gastric biopsy histology to enhance diagnostic accuracy, prognostication, and clinical decision-making.

2. Omics Technologies in Gastric Diagnosis

Multi-omics approaches have expanded gastric diagnostics beyond conventional morphology by enabling integrated analysis of genomic, transcriptomic, epigenomic, proteomic, lipidomic, metabolomic, and microbiomic features underlying disease development and progression [36,37,38,39]. By combining these molecular layers, omics technologies refine diagnostic classification, support risk stratification, enable detection of minimal residual disease, and identify therapeutic vulnerabilities, contributing to precision-oriented gastric pathology [40,41].
Genomic profiling has been central to this shift, facilitating detection of recurrent driver mutations (e.g., TP53, CDH1), inherited susceptibility variants, and molecular determinants of treatment response [42,43,44,45]. Kamio et al. examined genomic differences be-tween early-onset (≤39 years, n = 143) and late-onset (≥65 years, n = 1141) gastric cancer using sequencing data from the Japanese C-CAT database (total n = 1284). The authors compared mutation spectra and examined the impact of TP53 mutation sites on time to treatment failure (TTF) with platinum-based chemotherapy, complementing cohort analyses with in vitro oxaliplatin sensitivity assays stratified by TP53 site. They report distinct genomic profiles by age group, fewer neoantigen-associated alterations in early-onset cases, and differing TP53 hotspot distributions (R175H enriched in early-onset; R273 enriched in late-onset). Notably, R175H-harboring tumors showed greater oxaliplatin sensitivity in vitro, consistent with longer TTF among early-onset patients with TP53 mutations (17.3 vs. 7.0 months; p = 0.013), an outcome suggesting TP53-site informed chemotherapy stratification [44]. Both tissue-based sequencing and liquid biopsy approaches inform molecular stratification, prognosis, and dynamic monitoring of treatment response, illustrating how genomics complements histopathology in gastrointestinal malignancies [46,47,48,49,50,51,52,53]. White et al. characterized circulating tumor DNA (ctDNA) in appendiceal adenocarcinoma using a large commercial cohort (Guardant Health; n = 718) and an institutional series with ctDNA profiling (n = 168), of whom 57 had matched tissue sequencing. The study mapped the plasma mutational landscape, quantified shedding rates and variant allele frequencies, assessed tissue–plasma concordance, and related ctDNA detectability to clinicopathologic features and survival. Results show TP53 as the most frequently mutated gene in ctDNA (46%), lower ctDNA shedding in appendiceal versus colorectal cancer (detectable in 38% of metastatic cases; median VAF 0.4% vs. 1.3%), and associations between detectable ctDNA and adverse histologic features and worse overall survival (HR 2.32). While disease-specific, the paper provides methodological and translational lessons, sensitivity thresholds, concordance challenges, and prognostic value of low-VAF ctDNA that are transferable to gastrointestinal malignancies, including implications for incorporating liquid-biopsy omics into dynamic monitoring and trial designs [47].
Transcriptomics further enhances molecular characterization by capturing tumor-intrinsic programs, immune states, and microenvironmental interactions relevant to gastric carcinogenesis and therapy response [54,55,56]. Pádua et al. synthesize current evidence on epitranscriptomic regulation in gastric cancer stem cells (GCSCs), focusing on N6-methyladenosine (m6A) RNA modifications and the roles of writers (METTL3/METTL14/VIRMA), erasers (FTO/ALKBH5), and readers (YTHDF/YTHDC/IGF2BP families). Drawing on transcriptome-wide m6A profiling studies and functional perturbation experiments, the review highlights how altered m6A dynamics regulate pluripotency factors, oncogenic transcripts and non-coding RNAs to sustain stemness, therapy resistance, and metastatic behavior. The authors discuss candidate m6A signatures as prognostic biomarkers and outline therapeutic strategies targeting m6A machinery [56]. Transcriptome-based immune stratification, including identification of immune “hot” and “cold” phenotypes and IFN-γ–associated signatures, predicts response to immunotherapy, while pathway-level activation patterns refine prognostic assessment [57,58,59,60,61,62,63,64]. Wang et al. used genetic ablation and immune phenotyping to investigate cell-intrinsic PD-L1 functions in the tumor immune microenvironment and their relevance to adoptive T-cell therapy. Through in vivo models and transcriptomic analyses, the authors show that loss of intrinsic PD-L1 in tumor-infiltrating CD8+ T cells sustains effector T-cell states, enhances therapeutic T-cell expansion and function, and operates in part via mTORC1 signaling and BATF3-dependent dendritic cell interactions. The mechanistic findings identify molecular pathways linking intrinsic PD-L1 to T-cell dysfunction and suggest that profiling tumor and immune cell PD-L1 biology (transcriptomic/proteomic readouts) could inform immunotherapy responsiveness [58].
Epigenomic alterations provide additional insight into inflammation-driven carcinogenesis and reversible regulatory mechanisms, with emerging evidence supporting their integration with molecular and inflammatory biomarkers for improved risk stratification [65,66,67,68]. Chigvinadze et al. evaluated circulating protein levels (APC, KRAS, TP53) and inflammatory indices (MLR, PLR, NLR) in a cohort of 40 colorectal cancer patients, integrating mutation analysis (KRAS G12V by real-time PCR) with ELISA-based protein measurements to explore associations with disease stage and prognosis. They observed elevated inflammatory indices in advanced disease, increased plasma TP53 levels in progressive cancer, and an association of KRAS G12V with poorer prognosis and higher PLR, suggesting that combined plasma protein and inflammatory profiling may offer non-invasive insights into tumor biology [68].
Proteomics complements these data by directly profiling functional protein networks, signaling pathways, and post-translational modifications associated with disease progression, resistance mechanisms, and therapeutic response [69,70,71,72,73,74,75,76,77].
Lipidomics and metabolomics capture metabolic reprogramming across the gastric carcinogenesis spectrum, identifying lipid and metabolite signatures associated with early lesions, progression, therapeutic resistance, and prognosis [78,79,80,81,82,83,84,85,86,87,88,89,90,91]. Advances in spatial metabolomics further enable biopsy-level metabolic phenotyping linked to molecular subtypes and treatment response [88,89]. Finally, microbiomics highlights the role of gastric microbial dysbiosis in inflammation, immune modulation, and cancer progression, with integrated microbiome–metabolome analyses supporting biomarker discovery and mechanistic insight [92,93,94].
Collectively, these studies show that multi-omics approaches offer complementary insights into gastric disease biology by integrating molecular, metabolic, and microbial information. This integration improves disease classification, risk stratification, and understanding of tumor heterogeneity and treatment response, supporting translational re-search and the future development of precision diagnostics in gastric and gastrointestinal diseases.

3. Biopsy-Feasible Versus Emerging Omics Approaches

To clarify translational readiness, we distinguish omics methods that are currently feasible on routine gastric biopsy material from those that remain research-grade or future prospects. Biopsy-feasible today: Targeted DNA sequencing panels (oncopanels) and focused gene assays, immunohistochemistry and multiplex immunoassays for protein markers, targeted RNA panels (e.g., NanoString-type assays), and limited targeted proteomics (selected mass spectrometry (MS) or immunoassay panels) can be applied to FFPE biopsies using established workflows and clinically reasonable turnaround times (days–weeks) [44,68]. These assays are suited to near-term clinical uses such as confirmation of driver mutations, detection of actionable alterations, and augmentation of histologic grading [44].
Near-term emerging (translational): Targeted ctDNA assays (blood-based) and limited spatially resolved assays (targeted spatial transcriptomics or imaging mass cytometry panels) are increasingly deployable but generally require specialized platforms, harmonized pre-analytics, and cross-validation against tissue assays [47]. These methods enable dynamic monitoring, detection of minimal residual disease, and spatially contextualized biomarker readouts that can refine risk stratification and therapeutic targeting in the short term [47].
Future/research-grade: Whole-exome or whole-genome sequencing, unbiased bulk or single-cell multi-omics (single-cell RNA-seq, single-cell ATAC-seq), comprehensive untargeted proteomics, high-resolution spatial transcriptomics/proteomics, and large-scale metabolomics/lipidomics offer rich biological insight but currently demand high cost, specialized infrastructure, extensive bioinformatics, and larger tissue inputs [45,69,70,71,72,73,74,75,76,77,88,89]. Routine application on small diagnostic biopsies is therefore currently limited; technical optimization, cost reduction and prospective clinical validation will be required before broad clinical adoption [30].

4. AI in Gastric Biopsy Diagnosis

AI has emerged as a transformative tool in gastric endoscopy and biopsy diagnostics, enabling objective, reproducible, and scalable interpretation of complex visual and histological data [95].
Early studies showed that convolutional neural networks (CNNs) can rapidly analyze endoscopic images with high sensitivity for gastric cancer detection, particularly for invasive lesions, although false positives were observed in inflammatory conditions [96]. Subsequent comparative studies reported that CNNs achieved higher sensitivity than endoscopists and substantially reduced interpretation time, supporting AI as a sensitivity-enhancing diagnostic aid [97]. Strong real-world evidence was provided by a randomized tandem trial showing that AI-assisted white-light endoscopy markedly reduced gastric neoplasm miss rates during routine practice [98].
Advances in lesion localization and segmentation further strengthened AI performance. Deep learning architectures achieved high accuracy and F1-scores for early gastric cancer detection and delineation, while prospective multicenter studies demonstrated robust real-time lesion detection, classification, and invasion depth prediction during endoscopy [99,100]. Zhang et al. developed an Improved Mask R-CNN (IMR-CNN) to detect and segment early gastric cancer (EGC) lesions in gastroscopic images. Using a curated dataset of 1120 EGC images for training and validation, the model incorporated bidirectional feature fusion and feature-purification modules; reported performance metrics versus baseline Mask R-CNN were precision 92.9%, recall 95.3%, accuracy 93.9%, specificity 92.5% and F1-Score 94.1%, outcomes that translate into improved real-time lesion localization and endoscopic targeting [99].
AI systems have also shown expert-level performance in detecting premalignant gastric conditions, including atrophy and intestinal metaplasia, outperforming non-expert endoscopists and enabling early risk stratification [101]. Liu et al. applied a multi-model deep learning approach (five GAM-EfficientNet models) to recognize gastroscopic manifestations defined by the Kyoto Gastritis Score across 29,013 annotated endoscopy images, performing multi-label severity classification for atrophy, diffuse redness, enlarged folds, intestinal metaplasia and nodularity. The ensemble achieved mean accuracy ~78.7%, specificity ~91.9% and F1 ≈ 0.78, significantly outperforming both experienced and less-experienced endoscopists in this retrospective comparison (p < 0.05). The work shows deep learning’s potential as an adjunct for standardized endoscopic phenotyping and risk stratification, though prospective validation and assessment of real-world workflow integration remain necessary [102].
For Helicobacter pylori infection, CNN-based AI achieved pooled diagnostic performance comparable to physicians, with improved standardization and reduced operator dependence [103]. Systematic reviews confirmed high accuracy for gastric precancerous lesions and moderate accuracy for H. pylori detection, while emphasizing heterogeneity and the need for prospective validation [104]. Iizuka et al. trained convolutional and re-current neural networks on whole-slide biopsy images to classify gastric and colonic epithelial tumors (adenocarcinoma, adenoma, non-neoplastic). Evaluated on three independent test sets, models achieved high AUCs (up to 0.97–0.99 across gastric and colonic tasks), indicating strong generalization across datasets [105]. Quantitative AI-based gland segmentation further reduced inter-observer variability in tumor grading [106].
Population-level meta-analyses reinforced the robustness of AI-assisted gastric diagnostics, demonstrating high pooled sensitivity, specificity, and AUC for gastric cancer and intestinal metaplasia detection, with performance comparable or superior to endoscopists [107,108]. Li et al. pooled 12 studies (11,173 patients) assessing AI-assisted endoscopy for detecting gastric intestinal metaplasia. Meta-analysis yielded pooled sensitivity 94% (95% CI 0.92–0.96), specificity 93% (95% CI 0.89–0.95) and AUC 0.97, with AI outperforming endoscopists (sensitivity 95% vs. 79%) [108]. The key studies are summarized thematically in Table 1, illustrating the progression of AI from proof-of-concept image analysis to clinically integrated decision-support systems across the gastric diagnostic pathway.
Despite these advances, AI remains primarily a clinical decision-support tool. Multi-class CNN models achieve good overall accuracy but remain inferior to top experts in prospective validation, reinforcing the need for human oversight [109]. Collectively, these studies establish AI as a powerful enabler of precision gastric endoscopic and biopsy di-agnostics by enhancing detection, standardization, risk stratification, and workflow efficiency across the spectrum of gastric disease.

5. Integrated AI and Multi-Omics Approaches

Integrated AI and multi-omics approaches combine imaging, genomic, transcriptomic, proteomic and/or circulating biomarker data with machine learning models to improve classification and prognostication beyond single-modality analyses. For example, Lu et al. introduced the Highly Trustworthy Multi-omics Learning (HTML) framework to enable patient-centered, sample-adaptive multimodal modeling for personalized cancer diagnosis and prognosis. HTML uses self-adaptive dynamic learning to tailor model architectures and computational flows to each sample’s multi-omics profile, rather than applying a static “one-size-fits-all” architecture. The authors evaluated HTML across a 33-type pan-cancer dataset and 12 cancer-subtype datasets and reported superior performance versus static-architecture baselines, with added benefits in model trustworthiness and interpretability for sample-level decision support. While the study demonstrates the promise of dynamic, uncertainty-aware multimodal models for improved discrimination and biological insight, it is primarily pan-cancer in scope; targeted evaluation in gastric cancer cohorts and prospective clinical validation are still needed before routine diagnostic deployment [110].
This review argues that inflammatory bowel disease (IBD)’s complexity (genetics, immunity, microbiome, exposures) requires multi-omics (genomics, transcriptomics, proteomics, metagenomics) integrated with systems-biology tools and AI to identify patient-level signatures, predict disease trajectories, and support precision medicine. It emphasizes the need for large, well-curated multimodal datasets, robust integration methods, interpretability, and prospective validation, points directly relevant to applying integrated AI and multi-omics approaches in gastric biopsy diagnostics [111]. Another review highlights AI’s potential to transform IBD care by delivering accurate endoscopic and histologic assessments, standardized scoring, outcome prediction, and by enabling an endo-histo-omics paradigm that integrates endoscopy, histology and omics for precision medicine. It notes persistent barriers, data quality/standardization, reproducibility, limited randomized controlled trials, implementation, ethical/legal and regulatory issues, and calls for standardized guidelines and interdisciplinary collaboration to enable clinical translation [112].

6. Clinical Endpoints and Translational Impact

While AUC, sensitivity and specificity are essential for initial model evaluation, clinical adoption depends on demonstrable impact on patient-level and workflow outcomes. Key endpoints include missed-lesion rate, time-to-diagnosis or time-to-report, interobserver agreement, biopsy yield/targeting accuracy, downstream management changes (e.g., altered surveillance intervals or therapy selection), and patient outcomes such as stage at detection and recurrence; health-economic measures (cost per detected case, cost per QALY) are also critical. Randomized and prospective studies demonstrating reduced miss rates and workflow benefit [98], robust WSI/histopathology validation [105], and meta-analytic evidence of diagnostic performance [108] illustrate diagnostic promise but do not by themselves establish clinical utility. Similarly, circulating biomarker studies showing prognostic associations [47] indicate potential for monitoring but require linkage to actionable management changes. We therefore recommend that future AI and multi-omics studies report at least one relevant clinical or workflow endpoint in addition to technical metrics, pursue prospective or randomized designs where feasible, and include external validation and health-economic analyses to inform real-world adoption.

7. Accelerating Diagnosis: Reducing Time to Result

A major, clinically tangible contribution of AI and deployable omics is shorter time to diagnosis and reporting, which can reduce patient suffering and limit disease progression while improving workflow in overstretched pathology and endoscopy services. AI applied to endoscopic imaging and WSI can triage cases, pre-flag suspicious regions, and auto-mate routine screening tasks, thereby reducing image review time and accelerating downstream clinical decisions [99,105]. Comparative studies report reduced interpretation time for CNN-assisted review versus human alone [97], and randomized tandem trials show AI assistance lowers miss rates in real-time endoscopy with potential downstream reductions in diagnostic delays [98]. Rapid molecular assays and targeted omics (targeted NGS panels, focused RNA/protein assays, and ctDNA tests) offer faster turnaround than full discovery workflows and can provide actionable results within clinically relevant windows to inform treatment selection and monitoring [113,114]. Collectively, these modalities can shorten the diagnostic timeline from sample acquisition to actionable result, but real-world time-saving estimates will depend on local lab logistics, integration of AI into reporting workflows, and prospective evaluation of impact on time-to-treatment and patient outcomes [108].

8. Limitations of AI and Omics in Gastric Biopsy Diagnostics

Although AI and omics technologies are transforming gastric biopsy diagnostics, several interconnected limitations continue to hinder routine clinical adoption (Figure 2). AI models require large, well-annotated datasets, which are difficult to obtain due to histological heterogeneity, inter-observer variability, and labor-intensive expert annotation in gastric pathology [115,116,117,118]. Variations in tissue processing, staining, and slide scanning reduce model generalizability across institutions, while the “black-box” nature of many deep learning systems limits interpretability and regulatory acceptance [119,120,121,122]. Rare lesions and underrepresented morphological patterns may also be missed by AI systems [123]. Omics approaches are often costly, technically complex, and dependent on specialized infrastructure and bioinformatics expertise [124,125]. Small gastric biopsy samples and variable tissue quality can compromise molecular data integrity [126], and differences in analytical pipelines reduce reproducibility [127,128,129].
Integrating multi-omics data remains challenging due to biological complexity and lack of standardized interpretation frameworks [130], while the clinical significance of some molecular alterations remains uncertain [131]. Ethical and regulatory challenges further complicate implementation [132,133]. Large-scale molecular and imaging data raise concerns regarding privacy, consent, and data governance, while unequal access may exacerbate healthcare disparities. Regulatory approval of adaptive AI models and high-dimensional omics assays is complex, and accountability for AI-assisted decisions remains unclear [134]. Addressing algorithmic bias, ensuring transparency, and implementing rigorous external validation and post-deployment monitoring are essential for safe and equitable clinical translation [135].

9. Future Directions

The future of gastric biopsy diagnostics lies in the integrated application of omics technologies and AI, enabling a shift from descriptive morphology toward data-driven, precision gastroenterology and oncology [31,136]. Multi-omics profiling will increasingly be applied directly to gastric biopsy specimens to capture the complex molecular architecture of gastric diseases and their microenvironment [137]. These approaches will support refined disease classification, early detection of precursor lesions (e.g., early dysplasia, subtle metaplasia), minimal residual disease monitoring, and improved prediction of therapeutic response, especially for targeted therapies in gastric cancer [39]. AI will play a central role in integrating and interpreting high-dimensional omics data alongside digital histopathology [138]. Deep learning models will increasingly link morphologic patterns in whole-slide images with underlying molecular signatures, enabling virtual molecular profiling from routine H&E or immunohistochemistry [139]. Importantly, future studies should incorporate formal health-economic and cost-effectiveness evaluations alongside diagnostic accuracy and clinical utility to determine the feasibility and value of integrating AI-assisted multi-omics into routine gastroscopic and biopsy workflows.
Spatially resolved omics combined with AI-driven image analysis will allow precise mapping of genetic and proteomic alterations within specific gastric niches, improving understanding of tumor–stroma interactions, immune dysregulation, and treatment resistance [140]. Future workflows are expected to adopt end-to-end computational pathology pipelines, in which AI automates slide quality control, region selection, cell segmentation, and feature extraction, while multi-omics data provide complementary biological context [141,142]. Federated learning and multicenter model training will enhance generalizability, address data-sharing constraints, and support regulatory approval. Additionally, explainable AI approaches will improve transparency, enabling pathologists to understand how morphologic and molecular features drive algorithmic predictions [143,144]. Clinically, these advances will support personalized risk stratification and treatment planning, particularly in complex entities such as high-risk gastritis, advanced intestinal metaplasia, dysplasia, and gastric cancer [145]. As costs decline and standardization improves, AI-integrated multi-omics gastric analysis is expected to transition from a research tool to a routine component of diagnostic and prognostic assessment, positioning the gastric biopsy as a central hub for precision gastroenterology and oncology [146,147].

10. Conclusions

Gastric biopsy diagnostics are being transformed by the integration of multi-omics technologies and AI, extending evaluation beyond morphology to capture molecular alterations, cellular heterogeneity, and microenvironmental interactions. AI enhances detection, standardization, and efficiency across endoscopic and histopathological workflows, while omics profiling refines disease classification, risk stratification, and therapeutic insight. Despite these advances, routine clinical adoption remains limited by technical complexity, cost, data integration, interpretability, and the need for robust prospective validation and regulatory oversight. As standardization improves and multidisciplinary frameworks mature, combining AI-driven analytics with multi-omics data is expected to shift gastric biopsy toward a dynamic platform for precision gastroenterology. This evolution has the potential to improve diagnostic accuracy, prognostication, and individualized patient management, redefining the role of gastric biopsy in modern gastrointestinal care.

Funding

This research received no external funding.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

No new data were created or analyzed in this study.

Conflicts of Interest

The author declares no conflicts of interest.

References

  1. Leung, W.K.; Sung, J.J. Review article: Intestinal metaplasia and gastric carcinogenesis. Aliment. Pharmacol. Ther. 2002, 16, 1209–1216. [Google Scholar] [CrossRef]
  2. Park, Y.H.; Kim, N. Review of atrophic gastritis and intestinal metaplasia as a premalignant lesion of gastric cancer. J. Cancer Prev. 2015, 20, 25–40. [Google Scholar] [CrossRef]
  3. Huang, R.J.; Choi, A.Y.; Truong, C.D.; Yeh, M.M.; Hwang, J.H. Diagnosis and management of gastric intestinal metaplasia: Current status and future directions. Gut Liver 2019, 13, 596–603. [Google Scholar] [CrossRef] [PubMed]
  4. Pennelli, G.; Grillo, F.; Galuppini, F.; Ingravallo, G.; Pilozzi, E.; Rugge, M.; Fiocca, R.; Fassan, M.; Mastracci, L. Gastritis: Update on etiological features and histological practical approach. Pathologica 2020, 112, 153–165. [Google Scholar] [CrossRef]
  5. Livzan, M.A.; Mozgovoi, S.I.; Gaus, O.V.; Shimanskaya, A.G.; Kononov, A.V. Histopathological evaluation of gastric mucosal atrophy for predicting gastric cancer risk: Problems and solutions. Diagnostics 2023, 13, 2478. [Google Scholar] [CrossRef]
  6. Antico, A.; Tampoia, M.; Villalta, D.; Tonutti, E.; Tozzoli, R.; Bizzaro, N. Clinical usefulness of the serological gastric biopsy for the diagnosis of chronic autoimmune gastritis. Clin. Dev. Immunol. 2012, 2012, 520970. [Google Scholar] [CrossRef] [PubMed]
  7. Montgomery, E.; Bronner, M.P.; Goldblum, J.R.; Greenson, J.K.; Haber, M.M.; Hart, J.; Lamps, L.W.; Lauwers, G.Y.; Lazenby, A.J.; Lewin, D.N.; et al. Reproducibility of the diagnosis of dysplasia in Barrett esophagus: A reaffirmation. Hum. Pathol. 2001, 32, 368–378. [Google Scholar] [CrossRef]
  8. Kushima, R.; Kim, K.M. Interobserver variation in the diagnosis of gastric epithelial dysplasia and carcinoma between two pathologists in Japan and Korea. J. Gastric Cancer. 2011, 11, 141–145. [Google Scholar] [CrossRef]
  9. Schlemper, R.J.; Riddell, R.H.; Kato, Y.; Borchard, F.; Cooper, H.S.; Dawsey, S.M.; Dixon, M.F.; Fenoglio-Preiser, C.M.; Fléjou, J.-F.; Geboes, K.; et al. The Vienna classification of gastrointestinal epithelial neoplasia. Gut 2000, 47, 251–255. [Google Scholar] [CrossRef] [PubMed]
  10. Dixon, M.F. Gastrointestinal epithelial neoplasia: Vienna revisited. Gut 2002, 51, 130–131. [Google Scholar] [CrossRef]
  11. Talebkhan, Y.; Mohammadi, M.; Rakhshani, N.; Abdirad, A.; Fayaz Moughadam, K.; Fereidooni, F. Interobserver variations in histopathological assessment of gastric pathology. Pathology 2009, 41, 428–432. [Google Scholar] [CrossRef]
  12. Lee, S.B.; Kang, H.Y.; Kim, K.I.; Ahn, D.H. The diagnostic accuracy of endoscopic biopsy for gastric dysplasia. J. Gastric Cancer 2010, 10, 175–181. [Google Scholar] [CrossRef]
  13. Yakirevich, E.; Resnick, M.B. Pathology of gastric cancer and its precursor lesions. Gastroenterol. Clin. N. Am. 2013, 42, 261–284. [Google Scholar] [CrossRef]
  14. Mamun, T.I.; Younus, S.; Rahman, M.H. Gastric cancer—Epidemiology, modifiable and non-modifiable risk factors, challenges and opportunities: An updated review. Cancer Treat. Res. Commun. 2024, 41, 100845. [Google Scholar] [CrossRef] [PubMed]
  15. Isajevs, S.; Liepniece-Karele, I.; Janciauskas, D.; Moisejevs, G.; Funka, K.; Kikuste, I.; Vanags, A.; Tolmanis, I.; Leja, M. The effect of incisura angularis biopsy sampling on the assessment of gastritis stage. Eur. J. Gastroenterol. Hepatol. 2014, 26, 510–513. [Google Scholar] [CrossRef]
  16. Mao, X.Y.; Xu, S.F.; Liu, Q.; Jiang, J.X.; Zhang, H.H.; Sang, H.M.; Zhang, G.-X. Anatomical predilection of intestinal metaplasia based on 78,335 endoscopic cases. Saudi J. Gastroenterol. 2016, 22, 154–160. [Google Scholar] [CrossRef]
  17. Piroozkhah, M.; Gholinezhad, Y.; Piroozkhah, M.; Shams, E.; Nazemalhosseini-Mojarad, E. The molecular mechanism of actions and clinical utilities of tumor infiltrating lymphocytes in gastrointestinal cancers: A comprehensive review and future prospects toward personalized medicine. Front. Immunol. 2023, 14, 1298891. [Google Scholar] [CrossRef]
  18. Mehrotra, S.; Sharma, S.; Pandey, R.K. A journey from omics to clinicomics in solid cancers: Success stories and challenges. Adv. Protein Chem. Struct. Biol. 2024, 139, 89–139. [Google Scholar] [CrossRef] [PubMed]
  19. Ye, J.; Lin, Y.; Liao, Z.; Gao, X.; Lu, C.; Lu, L.; Huang, J.; Huang, X.; Huang, S.; Yu, H.; et al. Single cell-spatial transcriptomics and bulk multi-omics analysis of heterogeneity and ecosystems in hepatocellular carcinoma. NPJ Precis. Oncol. 2024, 8, 262. [Google Scholar] [CrossRef]
  20. Le, J.; Dian, Y.; Zhao, D.; Guo, Z.; Luo, Z.; Chen, X.; Zeng, F.; Deng, G. Single-cell multi-omics in cancer immunotherapy: From tumor heterogeneity to personalized precision treatment. Mol. Cancer 2025, 24, 221. [Google Scholar] [CrossRef] [PubMed]
  21. Ortega-Batista, A.; Jaén-Alvarado, Y.; Moreno-Labrador, D.; Gómez, N.; García, G.; Guerrero, E.N. Single-cell sequencing: Genomic and transcriptomic approaches in cancer cell biology. Int. J. Mol. Sci. 2025, 26, 2074. [Google Scholar] [CrossRef]
  22. Shrestha, U.K. Emerging role of artificial intelligence in gastroenterology and hepatology. World J. Gastroenterol. 2025, 31, 111495. [Google Scholar] [CrossRef]
  23. Aguilera-Chuchuca, M.J.; Sánchez-Luna, S.A.; González Suárez, B.; Ernest-Suárez, K.; Gelrud, A.; Berzin, T.M. The emerging role of artificial intelligence in gastrointestinal endoscopy: A review. Gastroenterol. Hepatol. 2022, 45, 492–497. [Google Scholar] [CrossRef]
  24. Nagaraju, G.P.; Sandhya, T.; Srilatha, M.; Ganji, S.P.; Saddala, M.S.; El-Rayes, B.F. Artificial intelligence in gastrointestinal cancers: Diagnostic, prognostic, and surgical strategies. Cancer Lett. 2025, 612, 217461. [Google Scholar] [CrossRef]
  25. Naemi, A.; Tashk, A.; Azar, A.S.; Samimi, T.; Tavassoli, G.; Mohasefi, A.B.; Khanshan, E.N.; Najafabad, M.H.; Tarighi, V.; Wiil, U.K.; et al. Applications of artificial intelligence for metastatic gastrointestinal cancer: A systematic literature review. Cancers 2025, 17, 558. [Google Scholar] [CrossRef] [PubMed]
  26. Xia, S.; Xia, Y.; Liu, T.; Luo, Y.; Pang, P.C. Application of deep learning models in gastric cancer pathology image analysis: A systematic scoping review. BMC Cancer 2025, 25, 1257. [Google Scholar] [CrossRef]
  27. Ren, T.; Govindarajan, V.; Bourouis, S.; Wang, X.; Ke, S. An interpretable hybrid deep learning framework for gastric cancer diagnosis using histopathological imaging. Sci. Rep. 2025, 15, 34204. [Google Scholar] [CrossRef] [PubMed]
  28. Ma, J.; Yang, F.; Yang, R.; Li, Y.; Chen, Y. Interpretable deep learning for gastric cancer detection: A fusion of AI architectures and explainability analysis. Front. Immunol. 2025, 16, 1596085. [Google Scholar] [CrossRef] [PubMed]
  29. Ding, P.; Yang, J.; Guo, H.; Wu, J.; Wu, H.; Li, T.; Gu, R.; Zhang, L.; He, J.; Yang, P.; et al. Multimodal artificial intelligence-based virtual biopsy for diagnosing abdominal lavage cytology-positive gastric cancer. Adv. Sci. 2025, 12, e2411490. [Google Scholar] [CrossRef]
  30. Schouten, D.; Nicoletti, G.; Dille, B.; Chia, C.; Vendittelli, P.; Schuurmans, M.; Litjens, G.; Khalili, N. Navigating the landscape of multimodal AI in medicine: A scoping review on technical challenges and clinical applications. Med. Image Anal. 2025, 105, 103621. [Google Scholar] [CrossRef]
  31. Wu, Y.M.; Tang, F.Y.; Qi, Z.X. Multimodal artificial intelligence technology in the precision diagnosis and treatment of gastroenterology and hepatology: Innovative applications and challenges. World J. Gastroenterol. 2025, 31, 109802. [Google Scholar] [CrossRef]
  32. Calvino, G.; Farro, J.; Zampatti, S.; Peconi, C.; Megalizzi, D.; Trastulli, G.; Andreucci, S.; Cascella, R.; Strafella, C.; Caltagirone, C.; et al. From genomics to ai: Revolutionizing precision medicine in oncology. Appl. Sci. 2025, 15, 6578. [Google Scholar] [CrossRef]
  33. Iacucci, M.; Santacroce, G.; Yasuharu, M.; Ghosh, S. Artificial intelligence-driven personalized medicine: Transforming clinical practice in inflammatory bowel disease. Gastroenterology 2025, 169, 416–431. [Google Scholar] [CrossRef]
  34. De Deo, D.; Dal Buono, A.; Gabbiadini, R.; Nardone, O.M.; Ferreiro-Iglesias, R.; Privitera, G.; Bonifacio, C.; Acosta, M.B.-D.; Bezzio, C.; Armuzzi, A. Digital biomarkers and artificial intelligence: A new frontier in personalized management of inflammatory bowel disease. Front. Immunol. 2025, 16, 1637159. [Google Scholar] [CrossRef] [PubMed]
  35. Zhang, L.; Shen, Y.; Gu, W.; Wu, P. Multimodal learning in gastrointestinal diseases. Gastroenterol. Endosc. 2025, 3, 251–258. [Google Scholar] [CrossRef]
  36. Wang, G.; Sun, Z.; Lee, S.Y.; Lai, M.; Wang, X.; An, S. An integrated multi-omics database for gastric diseases. Biology 2025, 14, 1484. [Google Scholar] [CrossRef]
  37. Wang, B.; Luan, J.; Zhao, W.; Yu, J.; Li, A.; Li, X.; Zhong, X.; Cao, H.; Wang, R.; Liu, B.; et al. Comprehensive multiomics analysis of the signatures of gastric mucosal bacteria and plasma metabolites across different stomach microhabitats in the development of gastric cancer. Cell. Oncol. 2025, 48, 139–159. [Google Scholar] [CrossRef]
  38. Jiang, Z.; Zhang, H.; Gao, Y.; Sun, Y. Multi-omics strategies for biomarker discovery and application in personalized oncology. Mol. Biomed. 2025, 6, 115. [Google Scholar] [CrossRef] [PubMed]
  39. Liu, Y.; Gao, F.; Cheng, Y.; Qi, L.; Yu, H. Applications and advances of multi-omics technologies in gastrointestinal tumors. Front. Med. 2025, 12, 1630788. [Google Scholar] [CrossRef]
  40. Jamalinia, M.; Weiskirchen, R. Advances in personalized medicine: Translating genomic insights into targeted therapies for cancer treatment. Ann. Transl. Med. 2025, 13, 18. [Google Scholar] [CrossRef]
  41. Ozaki, Y.; Broughton, P.; Abdollahi, H.; Valafar, H.; Blenda, A.V. Integrating omics data and AI for cancer diagnosis and prognosis. Cancers 2024, 16, 2448. [Google Scholar] [CrossRef]
  42. Roman, S.; Panduro, A. Genomic medicine in gastroenterology: A new approach or a new specialty? World J. Gastroenterol. 2015, 21, 8227–8237. [Google Scholar] [CrossRef] [PubMed]
  43. Cai, H.Q.; Zhang, L.Y.; Fu, L.M.; Xu, B.; Jiao, Y. Mutational landscape of TP53 and CDH1 in gastric cancer. World J. Gastrointest. Surg. 2024, 16, 276–283. [Google Scholar] [CrossRef]
  44. Kamio, T.; Kono, Y.; Hirosuna, K.; Ozato, T.; Yamamoto, H.; Hirasawa, A.; Ennishi, D.; Tomida, S.; Toyooka, S.; Otsuka, M. Genomic differences and distinct TP53 mutation site-linked chemosensitivity in early- and late-onset gastric cancer. Cancer Med. 2025, 14, e70793. [Google Scholar] [CrossRef]
  45. Pei, X.M.; Yeung, M.H.Y.; Wong, A.N.N.; Tsang, H.F.; Yu, A.C.S.; Yim, A.K.Y.; Wong, S.C.C. Targeted sequencing approach and its clinical applications for the molecular diagnosis of human diseases. Cells 2023, 12, 493. [Google Scholar] [CrossRef] [PubMed]
  46. Kim, D.E.; Oh, H.J.; Kim, H.J.; Kim, Y.B.; Kim, S.T.; Yim, H. Synergistic two-step inhibition approach using a combination of trametinib and onvansertib in KRAS and TP53-mutated colorectal adenocarcinoma. Biomed. Pharmacother. 2025, 182, 117796. [Google Scholar] [CrossRef]
  47. White, M.G.; Zeineddine, M.A.; Fallon, E.A.; Zeineddine, F.A.; Dansby, J.; Chowdhury, S.; Hornstein, N.; Yousef, A.; Yousef, M.; Bhutiani, N.; et al. The landscape of ctDNA in appendiceal adenocarcinoma. Clin. Cancer Res. 2025, 31, 551–560. [Google Scholar] [CrossRef]
  48. Nadeem, U.; Drapkin, B.J. Atypical Small Cell Lung Cancer: A new malignancy characterized by chromothripsis, carcinoid tumors, and wild-type RB1 and TP53. Cancer Discov. 2025, 15, 8–10. [Google Scholar] [CrossRef]
  49. Pataky, R.E.; Peacock, S.; Bryan, S.; Sadatsafavi, M.; Regier, D.A. Using genomic heterogeneity to inform therapeutic decisions for metastatic colorectal cancer: An application of the value of heterogeneity framework. Appl. Health Econ. Health Policy 2025, 23, 441–452. [Google Scholar] [CrossRef] [PubMed]
  50. Choi, Y.; Dharia, N.V.; Jun, T.; Chang, J.; Royer-Joo, S.; Yau, K.K.; Assaf, Z.J.; Aimi, J.; Sivakumar, S.; Montesion, M.; et al. Circulating tumor DNA dynamics reveal KRAS G12C mutation heterogeneity and response to treatment with the KRAS G12C inhibitor divarasib in solid tumors. Clin. Cancer Res. 2024, 30, 3788–3797. [Google Scholar] [CrossRef]
  51. Yang, H.; Xiao, X.; Zeng, L.; Zeng, H.; Zheng, Y.; Wang, J.; Li, G.; Dai, W.; He, Y.; Wang, S.; et al. Integrating cfDNA liquid biopsy and organoid-based drug screening reveals PI3K signaling as a promising therapeutic target in colorectal cancer. J. Transl. Med. 2024, 22, 132. [Google Scholar] [CrossRef] [PubMed]
  52. Xie, F.; Luo, S.; Liu, D.; Lu, X.; Wang, M.; Liu, X.; Jia, F.; Pang, Y.; Shen, Y.; Zeng, C.; et al. Genomic and transcriptomic landscape of human gastrointestinal stromal tumors. Nat. Commun. 2024, 15, 9495. [Google Scholar] [CrossRef] [PubMed]
  53. Datta, J.; Bianchi, A.; De Castro Silva, I.; Deshpande, N.U.; Cao, L.L.; Mehra, S.; Singh, S.; Rafie, C.; Sun, X.; Chen, X.; et al. Distinct mechanisms of innate and adaptive immune regulation underlie poor oncologic outcomes associated with KRAS-TP53 co-alteration in pancreatic cancer. Oncogene 2022, 41, 3640–3654. [Google Scholar] [CrossRef] [PubMed]
  54. Lowe, R.; Shirley, N.; Bleackley, M.; Dolan, S.; Shafee, T. Transcriptomics technologies. PLoS Comput. Biol. 2017, 13, e1005457. [Google Scholar] [CrossRef]
  55. Xu, J.; Yu, B.; Wang, F.; Yang, J. Single-cell RNA sequencing to map tumor heterogeneity in gastric carcinogenesis paving roads to individualized therapy. Cancer Immunol. Immunother. 2024, 73, 233. [Google Scholar] [CrossRef]
  56. Pádua, D.; Mesquita, P.; Almeida, R. The epitranscriptomic landscape of gastric cancer stem cells: The emerging role of m6A RNA modifications. Cancers 2025, 17, 3589. [Google Scholar] [CrossRef]
  57. Huang, C.J.; Liu, G.T.; Yeh, Y.C.; Chung, S.Y.; Chang, Y.C.; Chiang, N.J.; Lu, M.-L.; Huang, W.-N.; Chen, M.-H.; Wang, Y.-C. Construction of hot tumor classification models in gastrointestinal cancers. J. Transl. Med. 2025, 23, 218. [Google Scholar] [CrossRef]
  58. Wang, X.; Lu, L.; Hong, X.; Wu, L.; Yang, C.; Wang, Y.; Li, W.; Yang, Y.; Cao, D.; Di, W.; et al. Cell-intrinsic PD-L1 ablation sustains effector CD8+ T cell responses and promotes antitumor T cell therapy. Cell Rep. 2024, 43, 113712. [Google Scholar] [CrossRef]
  59. Yu, X.; Ou, J.; Wang, L.; Li, Z.; Ren, Y.; Xie, L.; Chen, Z.; Liang, J.; Shen, G.; Zou, Z.; et al. Gut microbiota modulate CD8+ T cell immunity in gastric cancer through Butyrate/GPR109A/HOPX. Gut Microbes 2024, 16, 2307542. [Google Scholar] [CrossRef]
  60. Liu, Z.; Li, L.; Liu, L.; Zhu, Z.; Yu, Y.; Zhan, S.; Luo, Z.; Li, Y.; Long, H.; Cai, J.; et al. PDK3 drives colorectal carcinogenesis and immune evasion and is a therapeutic target for boosting immunotherapy. Am. J. Cancer Res. 2024, 14, 3117–3129. [Google Scholar] [CrossRef]
  61. Tang, Q.; Markby, G.R.; MacNair, A.J.; Tang, K.; Tkacz, M.; Parys, M.; Phadwal, K.; MacRae, V.E.; Corcoran, B.M. TGF-β-induced PI3K/AKT/mTOR pathway controls myofibroblast differentiation and secretory phenotype of valvular interstitial cells through the modulation of cellular senescence in a naturally occurring in vitro canine model of myxomatous mitral valve disease. Cell Prolif. 2023, 56, e13435. [Google Scholar] [CrossRef]
  62. Chida, K.; Kawazoe, A.; Suzuki, T.; Kawazu, M.; Ueno, T.; Takenouchi, K.; Nakamura, Y.; Kuboki, Y.; Kotani, D.; Kojima, T.; et al. Transcriptomic Profiling of MSI-H/dMMR Gastrointestinal Tumors to Identify Determinants of Responsiveness to Anti-PD-1 Therapy. Clin. Cancer Res. 2022, 28, 2110–2117. [Google Scholar] [CrossRef] [PubMed]
  63. Zhong, C.; Xie, Z.; Zeng, L.H.; Yuan, C.; Duan, S. MIR4435-2HG Is a potential pan-cancer biomarker for diagnosis and prognosis. Front. Immunol. 2022, 13, 855078. [Google Scholar] [CrossRef]
  64. Hsiehchen, D.; Bucheit, L.; Yang, D.; Beg, M.S.; Lim, M.; Lee, S.S.; Kasi, P.M.; Kaseb, A.O.; Zhu, H. Genetic features and therapeutic relevance of emergent circulating tumor DNA alterations in refractory non-colorectal gastrointestinal cancers. Nat. Commun. 2023, 14, 7621. [Google Scholar] [CrossRef]
  65. Tan, S.Y.X.; Zhang, J.; Tee, W.W. Epigenetic regulation of inflammatory signaling and inflammation-induced cancer. Front. Cell Dev. Biol. 2022, 10, 931493. [Google Scholar] [CrossRef]
  66. Wang, Y.; Liu, H.; Zhang, M.; Xu, J.; Zheng, L.; Liu, P.; Chen, J.; Chen, C. Epigenetic reprogramming in gastrointestinal cancer: Biology and translational perspectives. MedComm 2024, 5, e670. [Google Scholar] [CrossRef] [PubMed]
  67. Zeng, Y.; Rong, H.; Xu, J.; Cao, R.; Li, S.; Gao, Y.; Cheng, B.; Zhou, T. DNA methylation: An important biomarker and therapeutic target for gastric cancer. Front. Genet. 2022, 13, 823905. [Google Scholar] [CrossRef]
  68. Chigvinadze, N.; Pantsulaia, I.; Lejava, T.; Aladashvili, A.; Atamashvili, T.; Khvichia, N.; Rekhviashvili, K. Suppressor protein plasma levels and inflammatory indices in colorectal cancer patients. BMC Cancer 2025, 25, 774. [Google Scholar] [CrossRef] [PubMed]
  69. Jin, Z.; Yuan, L.; Ma, Y.; Ye, Z.; Zhang, Z.; Wang, Y.; Hu, C.; Dong, J.; Zhang, X.; Xu, Z.; et al. A comprehensive proteomic analysis uncovers novel molecular subtypes of gastric signet ring cell carcinoma: Identification of potential prognostic biomarkers and therapeutic targets. Genes Dis. 2025, 13, 101717. [Google Scholar] [CrossRef]
  70. Lee, H.J.; Kwak, Y.; Na, Y.S.; Kim, H.; Park, M.R.; Jo, J.Y.; Kim, J.Y.; Cho, S.-J.; Kim, P. Proteomic heterogeneity of the extracellular matrix identifies histologic subtype-specific fibroblast in gastric cancer. Mol. Cell. Proteom. 2024, 23, 100843. [Google Scholar] [CrossRef]
  71. Maruyama, K.; Shimizu, Y.; Nomura, Y.; Oh-Hara, T.; Takahashi, Y.; Nagayama, S.; Fujita, N.; Katayama, R. Mechanisms of KRAS inhibitor resistance in KRAS-mutant colorectal cancer harboring Her2 amplification and aberrant KRAS localization. NPJ Precis. Oncol. 2025, 9, 4. [Google Scholar] [CrossRef] [PubMed]
  72. Liu, Y.F.; Feng, Z.Q.; Chu, T.H.; Yi, B.; Liu, J.; Yu, H.; Xue, J.; Wang, Y.-J.; Zhang, C.-Z. Andrographolide sensitizes KRAS-mutant colorectal cancer cells to cetuximab by inhibiting the EGFR/AKT and PDGFRβ/AKT signaling pathways. Phytomedicine 2024, 126, 155462. [Google Scholar] [CrossRef]
  73. Shang, C.; Zhang, Y.; Wang, Y.; Zhao, W.; Sun, X.; Dong, X.; Qiao, H. Role of ITGB2 protein structure and molecular mechanism in precancerous lesions of gastric cancer: Influencing the occurrence and development of cancer through the CXCL1-CXCR2 axis. Int. J. Biol. Macromol. 2025, 296, 139772. [Google Scholar] [CrossRef]
  74. Sun, M.; Tong, Y.; Yuan, W.; Wang, Y.; Pu, Y.; Huang, W.; Lv, B.; Xu, C.; Jiang, W.; Luo, R.; et al. Proteomic characterization identifies clinically relevant subgroups of gastrointestinal stromal tumors. Gastroenterology 2024, 166, 450–465.e33. [Google Scholar] [CrossRef]
  75. Li, Y.; Xu, C.; Wang, B.; Xu, F.; Ma, F.; Qu, Y.; Jiang, D.; Li, K.; Feng, J.; Tian, S.; et al. Proteomic characterization of gastric cancer response to chemotherapy and targeted therapy reveals new therapeutic strategies. Nat. Commun. 2022, 13, 5723. [Google Scholar] [CrossRef]
  76. Sun, Z.; Liu, L.; Chen, J. Targeting non-histone methylation in gastrointestinal cancers: From biology to clinic. Eur. J. Med. Chem. 2024, 278, 116802. [Google Scholar] [CrossRef]
  77. Fan, H.; Li, X.; Li, Z.W.; Zheng, N.R.; Cao, L.H.; Liu, Z.C.; Liu, M.-W.; Li, K.; Wu, W.-H.; Li, Z.-X.; et al. Urine proteomic signatures predicting the progression from premalignancy to malignant gastric cancer. eBioMedicine 2022, 86, 104340. [Google Scholar] [CrossRef]
  78. Ahluwalia, K.; Ebright, B.; Chow, K.; Dave, P.; Mead, A.; Poblete, R.; Louie, S.G.; Asante, I. Lipidomics in Understanding pathophysiology and pharmacologic effects in inflammatory diseases: Considerations for drug development. Metabolites 2022, 12, 333. [Google Scholar] [CrossRef]
  79. Wang, H.; Liu, S.; Fei, X.; Fan, W.; Ye, Y.; Xu, X.; Chen, Z.; Gong, X.; Zhou, Y.; Wu, X.; et al. Lipidomics and single-cell transcriptomics uncover aberrant lipid metabolism in metaplasia lesions during gastric carcinogenesis. J. Gastroenterol. 2025, 61, 27–45. [Google Scholar] [CrossRef] [PubMed]
  80. Ding, X.; Zhou, J.; Wang, Z.; Bo, Y.; Abliz, Z.; An, Z.; Yang, F.; Chen, Y. Lipidomic machine learning predictor for progression of gastric cancer. Clin. Chim. Acta 2026, 580, 120731. [Google Scholar] [CrossRef] [PubMed]
  81. Cai, Z.R.; Wang, W.; Chen, D.; Chen, H.; Hu, Y.; Luo, X.; Wang, Y.-T.; Pan, Y.-Q.; Mo, H.-Y.; Luo, S.-Y.; et al. Diagnosis and prognosis prediction of gastric cancer by high-performance serum lipidome fingerprints. EMBO Mol. Med. 2024, 16, 3089–3112. [Google Scholar] [CrossRef]
  82. Chen, M.; Zhang, C.; Li, H.; Zheng, S.; Li, Y.; Yuan, M.; Chen, Y.; Wu, J.; Sun, Q. PLA2G4A and ACHE modulate lipid profiles via glycerophospholipid metabolism in platinum-resistant gastric cancer. J. Transl. Med. 2024, 22, 249. [Google Scholar] [CrossRef]
  83. Zhu, J.; Huang, Y.; Li, X.; Liu, B.; Yuan, L.; Wang, L.; Qian, K.; Mao, Y.; Xu, Y.; Du, L.; et al. Metabolic signatures for gastric cancer diagnosis and mechanistic insights: A multicenter study. EMBO Mol. Med. 2025, 17, 3355–3376. [Google Scholar] [CrossRef]
  84. Shang, Z.; Ma, Z.; Wu, E.; Chen, X.; Tuo, B.; Li, T.; Liu, X. Effect of metabolic reprogramming on the immune microenvironment in gastric cancer. Biomed. Pharmacother. 2024, 170, 116030. [Google Scholar] [CrossRef] [PubMed]
  85. Chen, Y.; Wang, B.; Zhao, Y.; Shao, X.; Wang, M.; Ma, F.; Yang, L.; Nie, M.; Jin, P.; Yao, K.; et al. Metabolomic machine learning predictor for diagnosis and prognosis of gastric cancer. Nat. Commun. 2024, 15, 1657. [Google Scholar] [CrossRef]
  86. Zhao, J.; Zhao, X.; Yu, J.; Gao, S.; Zhang, M.; Yang, T.; Liu, L. A multi-platform metabolomics reveals possible biomarkers for the early-stage esophageal squamous cell carcinoma. Anal. Chim. Acta 2022, 1220, 340038. [Google Scholar] [CrossRef] [PubMed]
  87. Zhao, H.; Zhao, H.; Wang, J.; Ren, J.; Yao, J.; Li, Y.; Zhang, R. Bovine omasum-inspired interfacial carbon-based nanocomposite for saliva metabolic screening of gastric cancer. Anal. Chem. 2023, 95, 11296–11305. [Google Scholar] [CrossRef] [PubMed]
  88. Wang, J.; Kunzke, T.; Prade, V.M.; Shen, J.; Buck, A.; Feuchtinger, A.; Haffner, I.; Luber, B.; Liu, D.H.; Langer, R.; et al. Spatial metabolomics identifies distinct tumor-specific subtypes in gastric cancer patients. Clin. Cancer Res. 2022, 28, 2865–2877. [Google Scholar] [CrossRef]
  89. Liu, X.; Tao, L.; Jiang, X.; Qu, X.; Duan, W.; Yu, J.; Liang, X.; Wu, J. Isoporous membrane mediated imprinting mass spectrometry imaging for spatially-resolved metabolomics and rapid histopathological diagnosis. Small Methods 2024, 8, e2301644. [Google Scholar] [CrossRef]
  90. Mao, T.; Qin, F.; Zhang, M.; Li, J.; Li, J.; Lai, M. Elevated serum β-hydroxybutyrate, a circulating ketone metabolite, accelerates colorectal cancer proliferation and metastasis via ACAT1. Oncogene 2023, 42, 1889–1899. [Google Scholar] [CrossRef]
  91. Liu, S.; Locasale, J.W. Delineating a Role for Methionine Metabolism in Colorectal Cancer. Cancer Res. 2023, 83, 3833–3834. [Google Scholar] [CrossRef]
  92. Lowe, M.S.; Peek, R.M., Jr. Microbial oncogenesis within the gastric niche: How the gastric microbiota influences H. pylori-induced disease progression. Front. Microbiol. 2025, 16, 1691080. [Google Scholar] [CrossRef]
  93. Xie, W.; Wang, N.; Wang, M.; Zhang, Q.; Li, W.; Zhang, H.; Jin, Y.; Du, Y. Gut microbiome modulation by Weifuchun Capsules alleviates chronic atrophic gastritis: A combined microbiota and metabolomics approach. Front. Microbiol. 2025, 16, 1634410. [Google Scholar] [CrossRef]
  94. Kaźmierczak-Siedlecka, K.; Muszyński, D.; Styburski, D.; Makarewicz, J.; Sobocki, B.K.; Ulasiński, P.; Połom, K.; Stachowska, E.; Skonieczna-Żydecka, K.; Kalinowski, L. Untargeted metabolomics in gastric and colorectal cancer patients—Preliminary results. Front. Cell. Infect. Microbiol. 2024, 14, 1394038. [Google Scholar] [CrossRef]
  95. Ali, H.; Muzammil, M.A.; Dahiya, D.S.; Ali, F.; Yasin, S.; Hanif, W.; Gangwani, M.K.; Aziz, M.; Khalaf, M.; Basuli, D.; et al. Artificial intelligence in gastrointestinal endoscopy: A comprehensive review. Ann. Gastroenterol. 2024, 37, 133–141. [Google Scholar] [CrossRef]
  96. Hirasawa, T.; Aoyama, K.; Tanimoto, T.; Ishihara, S.; Shichijo, S.; Ozawa, T.; Ohnishi, T.; Fujishiro, M.; Matsuo, K.; Fujisaki, J.; et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 2018, 21, 653–660. [Google Scholar] [CrossRef] [PubMed]
  97. Ikenoyama, Y.; Hirasawa, T.; Ishioka, M.; Namikawa, K.; Yoshimizu, S.; Horiuchi, Y.; Ishiyama, A.; Yoshio, T.; Tsuchida, T.; Takeuchi, Y.; et al. Detecting early gastric cancer: Comparison between the diagnostic ability of convolutional neural networks and endoscopists. Dig. Endosc. 2021, 33, 141–150. [Google Scholar] [CrossRef]
  98. Wu, L.; Shang, R.; Sharma, P.; Zhou, W.; Liu, J.; Yao, L.; Dong, Z.; Yuan, J.; Zeng, Z.; Yu, Y.; et al. Effect of a deep learning-based system on the miss rate of gastric neoplasms during upper gastrointestinal endoscopy: A single-centre, tandem, randomised controlled trial. Lancet Gastroenterol. Hepatol. 2021, 6, 700–708. [Google Scholar] [CrossRef] [PubMed]
  99. Zhang, K.; Wang, H.; Cheng, Y.; Liu, H.; Gong, Q.; Zeng, Q.; Zhang, T.; Wei, G.; Wei, Z.; Chen, D. Early gastric cancer detection and lesion segmentation based on deep learning and gastroscopic images. Sci. Rep. 2024, 14, 7847, Erratum in Sci. Rep. 2024, 14, 9025. https://doi.org/10.1038/s41598-024-59794-x. [Google Scholar] [CrossRef] [PubMed]
  100. Gong, E.J.; Bang, C.S.; Lee, J.J.; Baik, G.H.; Lim, H.; Jeong, J.H.; Choi, S.W.; Cho, J.; Kim, D.Y.; Bin Lee, K.; et al. Deep learning-based clinical decision support system for gastric neoplasms in real-time endoscopy: Development and validation study. Endoscopy 2023, 55, 701–708. [Google Scholar] [CrossRef]
  101. Xu, M.; Zhou, W.; Wu, L.; Zhang, J.; Wang, J.; Mu, G.; Huang, X.; Li, Y.; Yuan, J.; Zeng, Z.; et al. Artificial intelligence in the diagnosis of gastric precancerous conditions by image-enhanced endoscopy: A multicenter, diagnostic study (with video). Gastrointest. Endosc. 2021, 94, 540–548.e4. [Google Scholar] [CrossRef]
  102. Liu, A.; Zhang, X.; Zhong, J.; Wang, Z.; Ge, Z.; Wang, Z.; Fan, X.; Zhang, J. A deep learning approach for gastroscopic manifestation recognition based on Kyoto Gastritis Score. Ann. Med. 2024, 56, 2418963. [Google Scholar] [CrossRef] [PubMed]
  103. Mohan, B.P.; Khan, S.R.; Kassab, L.L.; Ponnada, S.; Mohy-Ud-Din, N.; Chandan, S.; Dulai, P.S.; Kochhar, G.S. Convolutional neural networks in the computer-aided diagnosis of Helicobacter pylori infection and non-causal comparison to physician endoscopists: A systematic review with meta-analysis. Ann. Gastroenterol. 2021, 34, 20–25. [Google Scholar] [CrossRef]
  104. Dilaghi, E.; Lahner, E.; Annibale, B.; Esposito, G. Systematic review and meta-analysis: Artificial intelligence for the diagnosis of gastric precancerous lesions and Helicobacter pylori infection. Dig. Liver Dis. 2022, 54, 1630–1638. [Google Scholar] [CrossRef] [PubMed]
  105. Iizuka, O.; Kanavati, F.; Kato, K.; Rambeau, M.; Arihiro, K.; Tsuneki, M. Deep learning models for histopathological classification of gastric and colonic epithelial tumours. Sci. Rep. 2020, 10, 1504. [Google Scholar] [CrossRef]
  106. Awan, R.; Sirinukunwattana, K.; Epstein, D.; Jefferyes, S.; Qidwai, U.; Aftab, Z.; Mujeeb, I.; Snead, D.; Rajpoot, N. Glandular morphometrics for objective grading of colorectal adenocarcinoma histology images. Sci. Rep. 2017, 7, 16852. [Google Scholar] [CrossRef]
  107. Xie, F.; Zhang, K.; Li, F.; Ma, G.; Ni, Y.; Zhang, W.; Wang, J.; Li, Y. Diagnostic accuracy of convolutional neural network-based endoscopic image analysis in diagnosing gastric cancer and predicting its invasion depth: A systematic review and meta-analysis. Gastrointest. Endosc. 2022, 95, 599–609.e7. [Google Scholar] [CrossRef]
  108. Li, N.; Yang, J.; Li, X.; Shi, Y.; Wang, K. Accuracy of artificial intelligence-assisted endoscopy in the diagnosis of gastric intestinal metaplasia: A systematic review and meta-analysis. PLoS ONE 2024, 19, e0303421. [Google Scholar] [CrossRef]
  109. Cho, B.J.; Bang, C.S.; Park, S.W.; Yang, Y.J.; Seo, S.I.; Lim, H.; Shin, W.G.; Hong, J.T.; Yoo, Y.T.; Hong, S.H.; et al. Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network. Endoscopy 2019, 51, 1121–1129. [Google Scholar] [CrossRef] [PubMed]
  110. Lu, Y.; Peng, R.; Dong, L.; Xia, K.; Wu, R.; Xu, S.; Wang, J. Multiomics dynamic learning enables personalized diagnosis and prognosis for pancancer and cancer subtypes. Brief. Bioinform. 2023, 24, bbad378. [Google Scholar] [CrossRef]
  111. Cannarozzi, A.L.; Latiano, A.; Massimino, L.; Bossa, F.; Giuliani, F.; Riva, M.; Ungaro, F.; Guerra, M.; Di Brina, A.L.; Biscaglia, G.; et al. Inflammatory bowel disease genomics, transcriptomics, proteomics and metagenomics meet artificial intelligence. United Eur. Gastroenterol. J. 2024, 12, 1461–1480. [Google Scholar] [CrossRef]
  112. Iacucci, M.; Santacroce, G.; Zammarchi, I.; Maeda, Y.; Del Amor, R.; Meseguer, P.; Kolawole, B.B.; Chaudhari, U.; Di Sabatino, A.; Danese, S.; et al. Artificial intelligence and endo-histo-omics: New dimensions of precision endoscopy and histology in inflammatory bowel disease. Lancet Gastroenterol. Hepatol. 2024, 9, 758–772. [Google Scholar] [CrossRef] [PubMed]
  113. Ghoreyshi, N.; Heidari, R.; Farhadi, A.; Chamanara, M.; Farahani, N.; Vahidi, M.; Behroozi, J. Next-generation sequencing in cancer diagnosis and treatment: Clinical applications and future directions. Discov. Oncol. 2025, 16, 578. [Google Scholar] [CrossRef]
  114. Isaic, A.; Motofelea, N.; Hoinoiu, T.; Motofelea, A.C.; Leancu, I.C.; Stan, E.; Gheorghe, S.R.; Dutu, A.G.; Crintea, A. Next-generation sequencing: A review of its transformative impact on cancer diagnosis, treatment, and resistance management. Diagnostics 2025, 15, 2425. [Google Scholar] [CrossRef]
  115. Tizhoosh, H.R.; Pantanowitz, L. Artificial Intelligence and digital pathology: Challenges and opportunities. J. Pathol. Inform. 2018, 9, 38. [Google Scholar] [CrossRef] [PubMed]
  116. Bhinder, B.; Gilvary, C.; Madhukar, N.S.; Elemento, O. Artificial intelligence in cancer research and precision medicine. Cancer Discov. 2021, 11, 900–915. [Google Scholar] [CrossRef]
  117. Tizhoosh, H.R.; Diamandis, P.; Campbell, C.J.V.; Safarpoor, A.; Kalra, S.; Maleki, D.; Riasatian, A.; Babaie, M. Searching Images for Consensus: Can AI Remove Observer Variability in Pathology? Am. J. Pathol. 2021, 191, 1702–1708. [Google Scholar] [CrossRef]
  118. Zhou, S.; Xie, Y.; Feng, X.; Li, Y.; Shen, L.; Chen, Y. Artificial intelligence in gastrointestinal cancer research: Image learning advances and applications. Cancer Lett. 2025, 614, 217555. [Google Scholar] [CrossRef] [PubMed]
  119. Acs, B.; Rantalainen, M.; Hartman, J. Artificial intelligence as the next step towards precision pathology. J. Intern. Med. 2020, 288, 62–81. [Google Scholar] [CrossRef]
  120. Shmatko, A.; Ghaffari Laleh, N.; Gerstung, M.; Kather, J.N. Artificial intelligence in histopathology: Enhancing cancer research and clinical oncology. Nat. Cancer 2022, 3, 1026–1038. [Google Scholar] [CrossRef]
  121. Komura, D.; Ochi, M.; Ishikawa, S. Machine learning methods for histopathological image analysis: Updates in 2024. Comput. Struct. Biotechnol. J. 2024, 27, 383–400. [Google Scholar] [CrossRef]
  122. Amann, J.; Vetter, D.; Blomberg, S.N.; Christensen, H.C.; Coffee, M.; Gerke, S.; Gilbert, T.K.; Hagendorff, T.; Holm, S.; Livne, M.; et al. To explain or not to explain?—Artificial intelligence explainability in clinical decision support systems. PLoS Digit. Health 2022, 1, e0000016. [Google Scholar] [CrossRef]
  123. Deng, Y.; Qin, H.Y.; Zhou, Y.Y.; Liu, H.H.; Jiang, Y.; Liu, J.P.; Bao, J. Artificial intelligence applications in pathological diagnosis of gastric cancer. Heliyon 2022, 8, e12431. [Google Scholar] [CrossRef]
  124. Karahalil, B. Overview of systems biology and omics technologies. Curr. Med. Chem. 2016, 23, 4221–4230. [Google Scholar] [CrossRef] [PubMed]
  125. Magro, D.; Venezia, M.; Balistreri, C.R. The omics technologies and liquid biopsies: Advantages, limitations, applications. Med. Omics 2024, 11, 100039. [Google Scholar] [CrossRef]
  126. Janiesch, C.; Zschech, P.; Heinrich, K. Machine learning and deep learning. Electron. Mark. 2021, 31, 685–695. [Google Scholar] [CrossRef]
  127. Subramanian, I.; Verma, S.; Kumar, S.; Jere, A.; Anamika, K. Multi-omics data integration, interpretation, and its application. Bioinform. Biol. Insights 2020, 14, 1177932219899051. [Google Scholar] [CrossRef]
  128. Vitorino, R. Transforming clinical research: The power of high-throughput omics integration. Proteomes 2024, 12, 25. [Google Scholar] [CrossRef]
  129. Yetgin, A. Revolutionizing multi-omics analysis with artificial intelligence and data processing. Quant. Biol. 2025, 13, e70002. [Google Scholar] [CrossRef]
  130. Mohr, A.E.; Ortega-Santos, C.P.; Whisner, C.M.; Klein-Seetharaman, J.; Jasbi, P. Navigating challenges and opportunities in multi-omics integration for personalized healthcare. Biomedicines 2024, 12, 1496. [Google Scholar] [CrossRef]
  131. Liang, A.; Kong, Y.; Chen, Z.; Qiu, Y.; Wu, Y.; Zhu, X.; Li, Z. Advancements and applications of single-cell multi-omics techniques in cancer research: Unveiling heterogeneity and paving the way for precision therapeutics. Biochem. Biophys. Rep. 2023, 37, 101589. [Google Scholar] [CrossRef]
  132. Carter, S.M.; Rogers, W.; Win, K.T.; Frazer, H.; Richards, B.; Houssami, N. The ethical, legal and social implications of using artificial intelligence systems in breast cancer care. Breast 2020, 49, 25–32. [Google Scholar] [CrossRef] [PubMed]
  133. Farhud, D.D.; Zokaei, S. Ethical Issues of Artificial intelligence in medicine and healthcare. Iran. J. Public Health 2021, 50, i–v. [Google Scholar] [CrossRef] [PubMed]
  134. Serag, A.; Ion-Margineanu, A.; Qureshi, H.; McMillan, R.; Saint Martin, M.-J.; Diamond, J.; O’Reilly, P.; Hamilton, P. Translational AI and deep learning in diagnostic pathology. Front. Med. 2019, 6, 185. [Google Scholar] [CrossRef] [PubMed]
  135. van der Laak, J.; Litjens, G.; Ciompi, F. Deep learning in histopathology: The path to the clinic. Nat. Med. 2021, 27, 775–784. [Google Scholar] [CrossRef]
  136. Clement David-Olawade, A.; Aderinto, N.; Egbon, E.; Olatunji, G.D.; Kokori, E.; Olawade, D.B. Enhancing endoscopic precision: The role of artificial intelligence in modern gastroenterology. J. Gastrointest. Surg. 2025, 29, 102195. [Google Scholar] [CrossRef]
  137. Koo, T.H.; Lee, Y.L.; Leong, X.B.; Hayati, F.; Zakaria, M.H.; Zakaria, A.D. Multi-omics perspectives for gastrointestinal malignancy: A systematic review. World J. Gastrointest. Surg. 2025, 17, 107110. [Google Scholar] [CrossRef]
  138. Chen, H.; Shi, Y.; Yuan, M.; Li, H.; Liu, X. Integrating multi-omics and artificial intelligence fuels advanced target identification and drug discovery. Biotechnol. Adv. 2025, 87, 108785. [Google Scholar] [CrossRef]
  139. Dang, C.; Qi, Z.; Xu, T.; Gu, M.; Chen, J.; Wu, J.; Lin, Y.; Qi, X. Deep Learning-Powered Whole Slide Image Analysis in Cancer Pathology. Lab. Investig. 2025, 105, 104186. [Google Scholar] [CrossRef]
  140. Zhang, Y.; Yang, C.; Chen, X.; Wu, L.; Yuan, Z.; Zhang, F.; Qian, B. Cancer therapy resistance from a spatial-omics perspective. Clin. Transl. Med. 2025, 15, e70396. [Google Scholar] [CrossRef]
  141. Sweileh, M.W. AI-powered histopathology slide image interpretation in oncology: A comprehensive knowledge mapping and bibliometric analysis. Digit. Health 2025, 11, 20552076251393286. [Google Scholar] [CrossRef]
  142. Huo, T.; Wu, W.; Chen, X.; Xue, M.; Liu, P.; Zhang, J.; Xie, Y.; Wang, H.; Zhou, H.; Yan, Z.; et al. Deep learning–based multimodal data fusion in bone tumor management: Advances in clinical decision support. Intell. Oncol. 2025, 1, 204–215. [Google Scholar] [CrossRef]
  143. Abbas, S.R.; Abbas, Z.; Zahir, A.; Lee, S.W. Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration. Healthcare 2024, 12, 2587. [Google Scholar] [CrossRef]
  144. Zheng, Y.; Li, H.; Wang, R.; Jiang, C.S.; Zhao, Y.T. Multi-model applications and cutting-edge advancements of artificial intelligence in hepatology in the era of precision medicine. World J. Gastroenterol. 2025, 31, 111323. [Google Scholar] [CrossRef] [PubMed]
  145. Vernygorodskyi, S.; Tonchev, A.B.; Bratoeva, K.Z. Gastric epithelial cell plasticity and molecular mechanisms of metaplastic transformations in the stomach. J. Mol. Pathol. 2025, 6, 24. [Google Scholar] [CrossRef]
  146. Liatsou, E.; Driva, T.S.; Vergadis, C.; Sakellariou, S.; Lykoudis, P.; Apostolou, K.G.; Tsapralis, D.; Schizas, D. Current role of artificial intelligence in the management of gastric cancer. Biomedicines 2025, 13, 2939. [Google Scholar] [CrossRef]
  147. Ma, D.; Fan, C.; Sano, T.; Kawabata, K.; Nishikubo, H.; Imanishi, D.; Sakuma, T.; Maruo, K.; Yamamoto, Y.; Matsuoka, T.; et al. Beyond Biomarkers: Machine Learning-Driven Multiomics for Personalized Medicine in Gastric Cancer. J. Pers. Med. 2025, 15, 166. [Google Scholar] [CrossRef]
Biomedicines 14 00407 g001
Figure 1. Integration of AI and multi-omics in gastric biopsy diagnostics.
Figure 1. Integration of AI and multi-omics in gastric biopsy diagnostics.
Biomedicines 14 00407 g001
Biomedicines 14 00407 g002
Figure 2. Key limitations of artificial intelligence and multi-omics technologies in gastric biopsy diagnostics.
Figure 2. Key limitations of artificial intelligence and multi-omics technologies in gastric biopsy diagnostics.
Biomedicines 14 00407 g002
Table 1. Thematic roles of artificial intelligence across gastric endoscopy and biopsy diagnostics.
Table 1. Thematic roles of artificial intelligence across gastric endoscopy and biopsy diagnostics.
ThemePrimary AI RoleStudy Design & MethodologyKey Quantitative FindingsRef.
Automated gastric cancer detectionImage-based cancer detectionCNN (SSD architecture) trained on 13,584 endoscopic images; tested on 2296 images from 69 patients with 77 gastric cancersSensitivity 92.2%; PPV 30.6%; detected 98.6% of lesions ≥ 6 mm and all invasive cancers; analysis time 47 s[96]
AI vs. endoscopist performanceHuman–AI diagnostic comparisonCNN trained on 13,584 images; compared with 67 endoscopists using 2940 images from 140 casesCNN sensitivity 58.4% vs. endoscopists 31.9% (Δ +26.5%); diagnostic time 45 s vs. 173 min[97]
Miss rate reductionReal-time second observerSingle-center randomized tandem RCT (n = 1812); AI-assisted vs. routine white-light endoscopyMiss rate reduced from 27.3% to 6.1% (RR 0.224; p = 0.015); no serious AI-related adverse events[98]
Lesion segmentation and localizationBoundary delineationImproved Mask R-CNN trained on 1120 early gastric cancer imagesPrecision 92.9%; recall 95.3%; accuracy 93.9%; F1-score 94.1%[99]
Real-time clinical decision supportDetection, classification, invasion depthDeep learning CDSS; randomized pilot (2524 procedures) + multicenter prospective validation (3976 images)Detection rate 95.6%; four-class classification accuracy 81.5%; invasion depth prediction accuracy 86.4%[100]
Precancerous condition detectionAtrophy & intestinal metaplasia recognitionMulticenter retrospective + prospective video study using CNN (ENDOANGEL) on IEEAccuracy for GA 0.90–0.88; IM 0.91–0.90; AI comparable to experts and superior to non-experts[101]
Gastritis risk stratificationAutomated Kyoto Gastritis ScoreRetrospective deep learning study (29,013 images); multi-label Efficient Net modelsAI accuracy 78.7% vs. experts 72.6% and non-experts 66.6%; significantly higher F1-scores (p < 0.05)[102]
Helicobacter pylori detectionInfection diagnosisSystematic review and meta-analysis of CNN-based endoscopy (five studies)Pooled accuracy 87.1%; sensitivity 86.3%; specificity 87.1%; performance comparable to physicians[103]
AI for gastric precancerous lesionsEvidence synthesisSystematic review and meta-analysis (4 GPL, 9 H. pylori studies)Pooled accuracy: GPL 90.3%; H. pylori 79.6%; high heterogeneity (I2 > 90%)[104]
Histopathology tumor classificationBiopsy-based AI diagnosticsCNN/RNN models trained on gastric and colonic WSIs; three independent test setsAUC up to 0.99 for gastric adenoma and 0.97 for adenocarcinoma[105]
Quantitative histomorphometryObjective tissue gradingCNN gland segmentation + shape metrics (BAM) with SVM classifierAccuracy 97% (normal vs. cancer); 91% (normal/low/high grade); reduced inter-observer variability[106]
Population-level validationDiagnostic accuracy benchmarkingSystematic review and meta-analysis (17 studies; 51,446 images)Pooled sensitivity 89%; specificity 93%; AUC 0.94; performance comparable to expert endoscopists[107]
Gastric intestinal metaplasia detectionAutomated GIM diagnosisPRISMA-DTA meta-analysis (12 studies; 11,173 patients)Sensitivity 94%; specificity 93%; AUC 0.97; AI sensitivity higher than endoscopists (95% vs. 79%)[108]
Multi-class lesion classificationClinical decision-support limitationsCNN models trained on 5017 images; prospective validationFive-class accuracy 84.6%; inferior to top expert endoscopists but comparable to lowest performers[109]
AI, artificial intelligence; AUC, area under the receiver operating characteristic curve; BAM, best alignment metric; CDSS, clinical decision support system; CNN, convolutional neural network; ENDOANGEL, endoscopic artificial intelligence system; F1-score, harmonic mean of precision and recall; GA, gastric atrophy; GIM, gastric intestinal metaplasia; GPL, gastric precancerous lesions; IEE, image-enhanced endoscopy; IM, intestinal metaplasia; PPV, positive predictive value; RCT, randomized controlled trial; RR, relative risk; SVM, support vector ma-chine; SSD, single shot multibox detector; WSI, whole-slide image.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Alwahaibi, N. Transforming Gastric Biopsy Diagnostics: Integrating Omics Technologies and Artificial Intelligence. Biomedicines 2026, 14, 407. https://doi.org/10.3390/biomedicines14020407

AMA Style

Alwahaibi N. Transforming Gastric Biopsy Diagnostics: Integrating Omics Technologies and Artificial Intelligence. Biomedicines. 2026; 14(2):407. https://doi.org/10.3390/biomedicines14020407

Chicago/Turabian Style

Alwahaibi, Nasar. 2026. "Transforming Gastric Biopsy Diagnostics: Integrating Omics Technologies and Artificial Intelligence" Biomedicines 14, no. 2: 407. https://doi.org/10.3390/biomedicines14020407

APA Style

Alwahaibi, N. (2026). Transforming Gastric Biopsy Diagnostics: Integrating Omics Technologies and Artificial Intelligence. Biomedicines, 14(2), 407. https://doi.org/10.3390/biomedicines14020407

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop