Research progress in the construction and application of digestive system disease organoids and their integration with artificial intelligence

doi:10.3969/j.issn.1674-8115.2026.08.001

Abstract

Abstract:

As a novel in vitro three-dimensional culture model, organoids, with their high self-organizing ability, can recapitulate the morphological structures, pathophysiological functions, genetic variation profiles, and drug treatment responsiveness of their parental tissues. Compared with traditional animal models, organoids have the characteristics of short preparation cycle, low cost, less ethical controversy and high throughput. They are currently widely applied in biomedical research. Patient-derived organoid models retain the heterogeneity of their tissues of origin, can be continuously expanded and passaged in vitro over the long term, and maintain cell viability after cryopreservation and resuscitation. These characteristics provide a valuable platform for human disease modeling and demonstrate significant application value in exploring pathogenesis, screening novel drugs, and predicting drug sensitivity. The intervention of artificial intelligence (AI) has further enhanced the automation and standardization in the construction and application of organoids. This article systematically summarizes the research progress of organoids related to benign and malignant diseases of the digestive system, with particular emphasis on optimization strategies for constructing organoids derived from different organs and tissues. The paper also introduces the collection methods for digestive system tumor samples and the impact of neoadjuvant therapy on organoid construction. In addition, the article summarizes the advances of AI algorithms in organoid construction and applications, including AI-assisted organoid morphological characterization, cell viability assessment, drug sensitivity prediction, and the development of AI-integrated automated organoid platforms. In the future, AI will play a significant role in organoid construction for digestive system disease organoids and their diverse application scenarios, providing strong support for translational applications such as disease modeling, molecular target discovery, drug screening, and elucidation of drug resistance mechanisms.

Key words: digestive system disease, organoid, precision medicine, artificial intelligence (AI), new approach methodology (NAM)

CLC Number:

Yang Ruixin, Yu Yingyan. Research progress in the construction and application of digestive system disease organoids and their integration with artificial intelligence[J]. Journal of Shanghai Jiao Tong University (Medical Science), 2026,(8): 997-1006.

Figures/Tables 3

TrendMD

References 65

[1]	Sato T, Vries R G, Snippert H J, et al. Single Lgr5 stem cells build crypt-villus structures in vitro without a mesenchymal niche[J]. Nature, 2009, 459(7244): 262-265.
[2]	Yang R X, Qi Y, Zhang X Y, et al. Living biobank: standardization of organoid construction and challenges[J]. Chin Med J, 2024, 137(24): 3050-3060.
[3]	Wadman M. FDA no longer has to require animal testing for new drugs[J]. Science, 2023, 379(6628): 127-128.
[4]	Zhou L B, Huang J J, Li C, et al. Organoids and organs-on-chips: recent advances, applications in drug development, and regulatory challenges[J]. Med, 2025, 6(4): 100667.
[5]	Elfatimi E, Lekbach Y, Prakash S, et al. Artificial intelligence-, organoid-, and organ-on-chip-powered models to improve pre-clinical animal testing of vaccines and immunotherapeutics: potential, progress, and challenges[J]. Front Artif Intell, 2025, 8: 1681106.
[6]	Liu H Y, Wang X L. Esophageal organoids: applications and future prospects[J]. J Mol Med, 2023, 101(8): 931-945.
[7]	Jin R U, Xu Y W, Lih T M, et al. SOX2 regulates foregut squamous epithelial homeostasis and is lost during Barrett's esophagus development[J]. J Clin Invest, 2025, 135(16): e190374.
[8]	Yang R X, Du Y T, Kwan W, et al. A quick and reliable image-based AI algorithm for evaluating cellular senescence of gastric organoids[J]. Cancer Biol Med, 2023, 20(7): 519-536.
[9]	McCracken K W, Catá E M, Crawford C M, et al. Modelling human development and disease in pluripotent stem-cell-derived gastric organoids[J]. Nature, 2014, 516(7531): 400-404.
[10]	Son Y S, Kwon Y H, Lee M S, et al. Helicobacter pylori VacA-induced mitochondrial damage in the gastric pit cells of the antrum and therapeutic rescue[J]. Biomaterials, 2025, 314: 122842.
[11]	McGowan K P, Delgado E, Keeley T M, et al. Region-specific Wnt signaling responses promote gastric polyp formation in patients with familial adenomatous polyposis[J]. JCI Insight, 2023, 8(24): e174546.
[12]	Rodriguez Mier N, Cuyx S, De Boeck K, et al. Correlation between patient-derived intestinal organoids and clinical responses to CFTR modulators in people with cystic fibrosis homozygous for F508del[J]. J Cyst Fibros, 2025, 24(5): 939-945.
[13]	Jurickova I, Dreskin B W, Angerman E, et al. Eicosatetraynoic acid regulates profibrotic pathways in an induced pluripotent stem cell-derived macrophage-human intestinal organoid model of Crohn's disease[J]. J Crohns Colitis, 2025,19(2): jjae139.
[14]	Pleguezuelos-Manzano C, Puschhof J, van den Brink S, et al. Establishment and culture of human intestinal organoids derived from adult stem cells[J]. Curr Protoc Immunol, 2020, 130(1): e106.
[15]	Zhang S X, Du S J, Wang Y Y, et al. Rapid establishment of murine gastrointestinal organoids using mechanical isolation method[J]. Biochem Biophys Res Commun, 2022, 608: 30-38.
[16]	Laborde N, Barusseaud A, Quaranta M, et al. Human colonic organoids for understanding early events of familial adenomatous polyposis pathogenesis[J]. J Pathol, 2025, 265(1): 26-40.
[17]	Luce E, Messina A, Duclos-Vallée J C. Hepatic organoids as a platform for liver disease modeling and the development of novel therapies[J]. Clin Res Hepatol Gastroenterol, 2025, 49(7): 102647.
[18]	Chen Y K, Liu Y J, Chen S M, et al. Liver organoids: a promising three-dimensional model for insights and innovations in tumor progression and precision medicine of liver cancer[J]. Front Immunol, 2023, 14: 1180184.
[19]	Lui V C H. Organoids in biliary atresia[J]. World J Pediatr Surg, 2025, 8(2): e001010.
[20]	Liu K, Wang Y N, Li J J, et al. Macrophage-augmented organoids recapitulate the complex pathophysiology of viral diseases and enable development of multitarget therapeutics[J]. Nat Biomed Eng, 2025, 9(11): 1848-1868.
[21]	Reich M, Spomer L, Klindt C, et al. Downregulation of TGR5 (GPBAR1) in biliary epithelial cells contributes to the pathogenesis of sclerosing cholangitis[J]. J Hepatol, 2021, 75(3): 634-646.
[22]	Sampaziotis F, Muraro D, Tysoe O C, et al. Cholangiocyte organoids can repair bile ducts after transplantation in the human liver[J]. Science, 2021, 371(6531): 839-846.
[23]	Huang B, Trujillo M A, Fujikura K, et al. Molecular characterization of organoids derived from pancreatic intraductal papillary mucinous neoplasms[J]. J Pathol, 2020, 252(3): 252-262.
[24]	Beato F, Reverón D, Dezsi K B, et al. Establishing a living biobank of patient-derived organoids of intraductal papillary mucinous neoplasms of the pancreas[J]. Lab Invest, 2021, 101(2): 204-217.
[25]	Wang D Z, Guo Y B, Zhu J C, et al. Hyaluronic acid methacrylate/pancreatic extracellular matrix as a potential 3D printing bioink for constructing islet organoids[J]. Acta Biomater, 2023, 165: 86-101.
[26]	Fernández Á, Casamitjana J, Holguín-Horcajo A, et al. A single-cell atlas of the murine pancreatic ductal tree identifies novel cell populations with potential implications in pancreas regeneration and exocrine pathogenesis[J]. Gastroenterology, 2024, 167(5): 944-960.e15.
[27]	王玉蓉, 汪元元, 翁海燕. 胃肠道平滑肌肉瘤临床病理分析3例报告[J]. 诊断学理论与实践, 2024, 23(5): 537-541.
	Wang Y R, Wang Y Y, Weng H Y. Clinical and pathological analysis of gastrointestinal leiomyosarcoma: report of three cases[J]. Journal of Diagnostics Concepts & Practice, 2024, 23(5): 537-541.
[28]	Mönch D, Thiel J, Dong M, et al. Feasibility of patient-derived 3D gastrointestinal stromal tumour models as alternatives for in vivo mouse models[J]. Int J Mol Sci, 2025, 26(23): 11456.
[29]	苏新程, 林涛, 黄佳烨, 等. 3D类器官在胃肠间质瘤诊治中的研究及临床应用[J]. 临床外科杂志, 2025, 33(6): 568-571.
	Su X C, Lin T, Huang J Y, et al. Research and clinical application of 3D organoids in the diagnosis and treatment of gastrointestinal stromal tumors[J]. Journal of Clinical Surgery, 2025, 33(6): 568-571.
[30]	吴琪, 范伯男, 李岩. 2022全球癌症统计报告分析解读: 中国与世界癌症疾病负担与流行趋势[J]. 诊断学理论与实践, 2025, 24(2): 135-145.
	Wu Q, Fan B N, Li Y. Analysis and interpretation of the 2022 Global Cancer Statistics Report: cancer burden and epidemiological trends in China and the world[J]. Journal of Diagnostics Concepts & Practice, 2025, 24(2): 135-145.
[31]	Seidlitz T, Stange D E. Gastrointestinal cancer organoids-applications in basic and translational cancer research[J]. Exp Mol Med, 2021, 53(10): 1459-1470.
[32]	Yao Y, Xu X Y, Yang L F, et al. Patient-derived organoids predict chemoradiation responses of locally advanced rectal cancer[J]. Cell Stem Cell, 2020, 26(1): 17-26.e6.
[33]	Yang R X, Yu Y Y. Patient-derived organoids in translational oncology and drug screening[J]. Cancer Lett, 2023, 562: 216180.
[34]	Nam S Y, Lee S J, Lim H J, et al. Clinical risk factors and pattern of initial fungal contamination in endoscopic biopsy-derived gastrointestinal cancer organoid culture[J]. Korean J Intern Med, 2021, 36(4): 878-887.
[35]	Sachdeva U M, Shimonosono M, Flashner S, et al. Understanding the cellular origin and progression of esophageal cancer using esophageal organoids[J]. Cancer Lett, 2021, 509: 39-52.
[36]	Li J, Chen Y, Zhang Y Y, et al. Clinical value and influencing factors of establishing stomach cancer organoids by endoscopic biopsy[J]. J Cancer Res Clin Oncol, 2023, 149(7): 3803-3810.
[37]	Wang M J, Gao C, Huang X, et al. Establishing pancreatic cancer organoids from EUS-guided fine-needle biopsy specimens[J]. Cancers, 2025, 17(4): 692.
[38]	Wiessner J R, Orben F, Schäfer A, et al. Comparison of endoscopic ultrasound-guided fine-needle aspiration and fine-needle biopsy to generate pancreatic cancer organoids: randomized trial[J]. Endosc Int Open, 2024, 12(3): E361-E366.
[39]	Huang X Z, Pang M J, Li J Y, et al. Single-cell sequencing of ascites fluid illustrates heterogeneity and therapy-induced evolution during gastric cancer peritoneal metastasis[J]. Nat Commun, 2023, 14(1): 822.
[40]	Siegel R L, Kratzer T B, Giaquinto A N, et al. Cancer statistics, 2025[J]. CA Cancer J Clin, 2025, 75(1): 10-45.
[41]	Chen H N, Shu Y, Liao F, et al. Genomic evolution and diverse models of systemic metastases in colorectal cancer[J]. Gut, 2022, 71(2): 322-332.
[42]	Yang R X, Qi Y, Kwan W, et al. Paired organoids from primary gastric cancer and lymphatic metastasis are useful for personalized medicine[J]. J Transl Med, 2024, 22(1): 754.
[43]	Mo S B, Tang P Y, Luo W Q, et al. Patient-derived organoids from colorectal cancer with paired liver metastasis reveal tumor heterogeneity and predict response to chemotherapy[J]. Adv Sci (Weinh), 2022, 9(31): e2204097.
[44]	Wang F H, Zhang X T, Tang L, et al. The Chinese Society of Clinical Oncology (CSCO): clinical guidelines for the diagnosis and treatment of gastric cancer, 2023[J]. Cancer Commun, 2024, 44(1): 127-172.
[45]	Fuchino T, Kurogi S, Tsukamoto Y, et al. Characterization of residual cancer by comparison of a pair of organoids established from a patient with esophageal squamous cell carcinoma before and after neoadjuvant chemotherapy[J]. Hum Cell, 2024, 37(2): 491-501.
[46]	Demyan L, Habowski A N, Plenker D, et al. Pancreatic cancer patient-derived organoids can predict response to neoadjuvant chemotherapy[J]. Ann Surg, 2022, 276(3): 450-462.
[47]	张子臻, 刘梓航, 曹晖. 精准外科时代人工智能赋能胃癌R0切除的再度审视及未来展望[J]. 中华消化外科杂志, 2025, 24(3): 337-342.
	Zhang Z Z, Liu Z H, Cao H. Re-evaluation and future prospect of artificial intelligence empowered of R0 resection in gastric cancer under the precision surgical era[J]. Chinese Journal of Digestive Surgery, 2025, 24(3): 337-342.
[48]	钱佳乐, 范婧, 朱宏, 等. 深度学习图像重建在虚拟平扫CT尿路成像中的应用价值[J]. 诊断学理论与实践, 2024, 23(2): 139-145.
	Qian J L, Fan J, Zhu H, et al. The application of deep learning image reconstruction in dual⁃energy CT virtual non⁃contrast CT urography[J]. Journal of Diagnostics Concepts & Practice, 2024, 23(2): 139-145.
[49]	杨蕊馨, 于颖彦. 人工智能在消化道肿瘤医学图像数据处理的应用[J]. 诊断学理论与实践, 2025, 24(6): 605-612.
	Yang R X, Yu Y Y. Application of artificial intelligence in medical image data processing for digestive tract tumors[J]. Journal of Diagnostics Concepts & Practice, 2025, 24(6): 605-612.
[50]	Bai L, Wu Y, Li G F, et al. AI-enabled organoids: construction, analysis, and application[J]. Bioact Mater, 2024, 31: 525-548.
[51]	王晓峰, 周璐, 姚乐宇, 等. 深度卷积神经网络模型辅助下结直肠息肉检测系统对初级医师结直肠小息肉检出率的影响[J]. 上海交通大学学报(医学版), 2022, 42(2): 205-210.
	Wang X F, Zhou L, Yao L Y, et al. Effect of DCNN model-assisted colorectal polyp detection system on the detection of colorectal polyps by junior physicians[J]. Journal of Shanghai Jiao Tong University (Medical Science), 2022, 42(2): 205-210.
[52]	Yang R X, Yu Y Y. Artificial convolutional neural network in object detection and semantic segmentation for medical imaging analysis[J]. Front Oncol, 2021, 11: 638182.
[53]	Kassis T, Hernandez-Gordillo V, Langer R, et al. OrgaQuant: human intestinal organoid localization and quantification using deep convolutional neural networks[J]. Sci Rep, 2019, 9(1): 12479.
[54]	Larsen B M, Kannan M, Langer L F, et al. A pan-cancer organoid platform for precision medicine[J]. Cell Rep, 2021, 36(4): 109429.
[55]	Deben C, De La Hoz E C, Compte M L, et al. OrBITS: label-free and time-lapse monitoring of patient derived organoids for advanced drug screening[J]. Cell Oncol (Dordr), 2023, 46(2): 299-314.
[56]	Ferreira N, Kulkarni A, Agorku D, et al. OrganoIDNet: a deep learning tool for identification of therapeutic effects in PDAC organoid-PBMC co-cultures from time-resolved imaging data[J]. Cell Oncol (Dordr), 2025, 48(1): 101-122.
[57]	Okamoto T, Natsume Y, Doi M, et al. Integration of human inspection and artificial intelligence-based morphological typing of patient-derived organoids reveals interpatient heterogeneity of colorectal cancer[J]. Cancer Sci, 2022, 113(8): 2693-2703.
[58]	Mukashyaka P, Kumar P, Mellert D J, et al. High-throughput deconvolution of 3D organoid dynamics at cellular resolution for cancer pharmacology with Cellos[J]. Nat Commun, 2023, 14(1): 8406.
[59]	Boussaad I, Cruciani G, Bolognin S, et al. Integrated, automated maintenance, expansion and differentiation of 2D and 3D patient-derived cellular models for high throughput drug screening[J]. Sci Rep, 2021, 11(1): 1439.
[60]	Mao S S, Xie R Y, Shou J Z, et al. Bioprinting of patient-derived heterogeneous renal cell carcinoma organoids for personalized therapy[J]. Biofabrication, 2025, 17(4): 5008.
[61]	Bai L, Su J C. Artificial intelligence virtual organoids (AIVOs)[J]. Bioact Mater, 2026, 59: 45-68.
[62]	Bunne C, Roohani Y, Rosen Y, et al. How to build the virtual cell with artificial intelligence: priorities and opportunities[J]. Cell, 2024, 187(25): 7045-7063.
[63]	Roohani Y H, Hua T J, Tung P Y, et al. Virtual Cell Challenge: toward a Turing test for the virtual cell[J]. Cell, 2025, 188(13): 3370-3374.
[64]	于颖彦. 类器官应用前景及国内外政策解读[J]. 诊断学理论与实践, 2026, 25(2): 157-164.
	Yu Y Y. Application prospects of organoids and interpretation of domestic and international policies[J]. Journal of Diagnostics Concepts & Practice, 2026, 25(2): 157-164.
[65]	Stucki A O, Barton-Maclaren T S, Bhuller Y, et al. Use of new approach methodologies (NAMs) to meet regulatory requirements for the assessment of industrial chemicals and pesticides for effects on human health[J]. Front Toxicol, 2022, 4: 964553.

Site	Biomarker	Differential diagnosis
Esophagus	KRT5, KRT14	Squamous epithelium: KRT5 Glandular epithelium (such as Barrett esophagus): CDX2, MUC2, KRT20
Stomach	TFF1, MUC5AC, MUC6, MUC2, KRT8	Surface epithelium: TFF1 Fundic and corpus gland: MUC6, PGC, ATP4A Basal stem cell: LGR5 Endocrine cell: CHGA, CHGB, SCG5
Intestine	EPCAM, KRT20, CDX2	Duodenum: SLC5A1, CYP3A4 Jejunum: SLC6A19, LCT Ileum: IL22RA1, SLC10A2 Colon: CA2, MUC4
Liver and bile duct	KRT7, KRT19	Liver: ALB, AAT, TTR, APOA2 Bile duct: KRT7, KRT19, SOX9
Pancreas	Endocrine and exocrine glands have different marker genes	Exocrine gland: PRSS1, CPA1, KRT19 Endocrine gland: CHGA, INS, GCG

Site	Biomarker	Differential diagnosis
Esophagus	KRT5, KRT14	Squamous epithelium: KRT5 Glandular epithelium (such as Barrett esophagus): CDX2, MUC2, KRT20
Stomach	TFF1, MUC5AC, MUC6, MUC2, KRT8	Surface epithelium: TFF1 Fundic and corpus gland: MUC6, PGC, ATP4A Basal stem cell: LGR5 Endocrine cell: CHGA, CHGB, SCG5
Intestine	EPCAM, KRT20, CDX2	Duodenum: SLC5A1, CYP3A4 Jejunum: SLC6A19, LCT Ileum: IL22RA1, SLC10A2 Colon: CA2, MUC4
Liver and bile duct	KRT7, KRT19	Liver: ALB, AAT, TTR, APOA2 Bile duct: KRT7, KRT19, SOX9
Pancreas	Endocrine and exocrine glands have different marker genes	Exocrine gland: PRSS1, CPA1, KRT19 Endocrine gland: CHGA, INS, GCG

Sample origin	Sample size	Sample collection requirement	Note
Surgical resection	200 mg (approximately the size of 2 soybeans)	Selecting vascular-rich, soft tissue; avoiding central necrotic areas tissues with marked fibrosis, large adipose aggregates, hard consistency, electrocoagulation artifacts, or yellowish-gray discoloration	Optimizing enzymatic digestion time for pancreatic cancer organoids to suppress excessive stromal cell growth
Needle biopsy	3 pieces	Maximizing cell retention and minimizing cell damage during sample processing and digestion	Magnifying endoscopy can be employed for sample collection to ensure high tumor purity and avoid necrotic areas in specimens
Malignant ascites	50‒100 mL	Collecting sufficient ascites, harvesting cells via centrifugation, and preparing a single-cell suspension after red blood cell lysis	Excess immunocytes can be removed by Ficoll gradient centrifugation

Sample origin	Sample size	Sample collection requirement	Note
Surgical resection	200 mg (approximately the size of 2 soybeans)	Selecting vascular-rich, soft tissue; avoiding central necrotic areas tissues with marked fibrosis, large adipose aggregates, hard consistency, electrocoagulation artifacts, or yellowish-gray discoloration	Optimizing enzymatic digestion time for pancreatic cancer organoids to suppress excessive stromal cell growth
Needle biopsy	3 pieces	Maximizing cell retention and minimizing cell damage during sample processing and digestion	Magnifying endoscopy can be employed for sample collection to ensure high tumor purity and avoid necrotic areas in specimens
Malignant ascites	50‒100 mL	Collecting sufficient ascites, harvesting cells via centrifugation, and preparing a single-cell suspension after red blood cell lysis	Excess immunocytes can be removed by Ficoll gradient centrifugation