{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T07:57:00Z","timestamp":1773993420240,"version":"3.50.1"},"reference-count":28,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000865","name":"Bill & Melinda Gates Foundation","doi-asserted-by":"crossref","award":["INV-034554"],"award-info":[{"award-number":["INV-034554"]}],"id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Early detection is critical for improving outcomes in gastric cancer, yet lesion recognition in capsule endoscopy is challenged by interference from different gastric anatomical sites, patient posture changes, and gastric peristalsis. This study aims to prompt a robust deep learning model to address these challenges. A dual-network model, named DuDeM (DualNet Detection Model), was developed by integrating a ResNet50-based convolutional branch with a CapsuleNet branch incorporating dynamic routing. The convolutional branch extracts local lesion features that are transmitted to primary capsules, while dynamic routing enables adaptive matching between capsule layers to establish local\u2013global feature associations. An attention-weighted strategy is applied for feature fusion. The model was trained using capsule endoscopy images from nine hospitals in China and public datasets, and its performance was compared with eight representative models, with ablation analyses validating key components. Results showed that DuDeM achieved an area under the curve (AUC) of 0.981 and an F1-score of 0.979, with sensitivity, specificity, and precision all exceeding 97%, and performance degradation limited to within 3% under mild image perturbations. These findings suggest that DuDeM enables reliable early gastric cancer (EGC) recognition and may support large-scale capsule endoscopy screening in clinical practice.<\/jats:p>","DOI":"10.3390\/bioengineering13030356","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T17:12:26Z","timestamp":1773853946000},"page":"356","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DuDeM: A Dual-Network Model for Early Gastric Cancer Detection Based on Capsule Endoscopy"],"prefix":"10.3390","volume":"13","author":[{"given":"Tianyi","family":"Feng","sequence":"first","affiliation":[{"name":"Shanghai Institute of Infectious Disease and Biosecurity, Fudan University, Shanghai 200032, China"},{"name":"China Academy of Information and Communications Technology, Beijing 100191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[{"name":"China Academy of Information and Communications Technology, Beijing 100191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8944-4013","authenticated-orcid":false,"given":"Tianqi","family":"Chen","sequence":"additional","affiliation":[{"name":"China Academy of Information and Communications Technology, Beijing 100191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4497-5251","authenticated-orcid":false,"given":"Weibing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Infectious Disease and Biosecurity, Fudan University, Shanghai 200032, China"},{"name":"Department of Epidemiology, School of Public Health, Fudan University, Shanghai 200032, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"ref_1","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","first-page":"1950","article-title":"The latest clinical practice guidelines for gastric cancer from CSCO and NCCN: A brief review and comparison","volume":"33","author":"Kun","year":"2024","journal-title":"Chin. J. Gen. Surg."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1016\/S0140-6736(17)33326-3","article-title":"Global surveillance of trends in cancer survival 2000-14 (CONCORD-3): Analysis of individual records for 37\u2008513\u2008025 patients diagnosed with one of 18 cancers from 322 population-based registries in 71 countries","volume":"391","author":"Allemani","year":"2018","journal-title":"Lancet"},{"key":"ref_4","unstructured":"National Health Commission of the People\u2019s Republic of China (2024). Lung Cancer Screening and Early Diagnosis and Treatment Program (2024 Edition). Clin. Pract. Educ. Gen. Med., 22, 772."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2911","DOI":"10.1007\/s10620-019-05631-5","article-title":"Clinical Efficiency and Safety of Magnetic-Controlled Capsule Endoscopy for Gastric Diseases in Aging Patients: Our Preliminary Experience","volume":"64","author":"Zhang","year":"2019","journal-title":"Dig. Dis. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1097\/MPG.0000000000002292","article-title":"Magnetically Controlled Capsule Endoscopy in Children: A Single-center, Retrospective Cohort Study","volume":"69","author":"Gu","year":"2019","journal-title":"J. Pediatr. Gastroenterol. Nutr."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1080\/00365521.2019.1638446","article-title":"Magnetically controlled capsule endoscopy as the first-line examination for high-risk patients for the standard gastroscopy: A preliminary study","volume":"54","author":"Hu","year":"2019","journal-title":"Scand. J. Gastroenterol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, X., Gao, F., and Zhang, J. (2018). Screening for Gastric and Small Intestinal Mucosal Injury with Magnetically Controlled Capsule Endoscopy in Asymptomatic Patients Taking Enteric-Coated Aspirin. Gastroenterol. Res. Pract., 2524698.","DOI":"10.1155\/2018\/2524698"},{"key":"ref_9","unstructured":"Big Data Collaboration Group of the Chinese Society of Digestive Endoscopy (2025). Expert Consensus on the Clinical Application of Capsule Endoscopy Artificial Intelligence Systems (2024, Shanghai). Chin. J. Dig. Endosc., 42, 258\u2013265."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"43532","DOI":"10.1109\/ACCESS.2025.3548167","article-title":"Deep Learning-Based Lesion Detection in Endoscopy: A Systematic Literature Review","volume":"13","author":"Rochmawati","year":"2025","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, X., Hu, W., Chen, F., Liu, J., Yang, Y., Wang, L., Duan, H., and Si, J. (2017). Gastric precancerous diseases classification using CNN with a concise model. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0185508"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"17562848231206991","DOI":"10.1177\/17562848231206991","article-title":"A systematic review on diagnosis and treatment of gastrointestinal diseases by magnetically controlled capsule endoscopy and artificial intelligence","volume":"16","author":"Wang","year":"2023","journal-title":"Ther. Adv. Gastroenterol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1016\/j.suc.2011.06.012","article-title":"Gastric motility physiology and surgical intervention","volume":"91","author":"Rostas","year":"2011","journal-title":"Surg. Clin. N. Am."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.gie.2020.05.027","article-title":"Use of artificial intelligence for detection of gastric lesions by magnetically controlled capsule endoscopy","volume":"93","author":"Xia","year":"2021","journal-title":"Gastrointest. Endosc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.igie.2023.04.007","article-title":"Magnetically controlled capsule for assessment of the gastric mucosa in symptomatic patients: A prospective, single-arm, single-center, comparative study","volume":"2","author":"Andrew","year":"2023","journal-title":"iGIE"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"E622","DOI":"10.1055\/a-1724-6958","article-title":"Real-time identification of gastric lesions and anatomical landmarks by artificial intelligence during magnetically controlled capsule endoscopy","volume":"54","author":"Pan","year":"2022","journal-title":"Endoscopy"},{"key":"ref_17","unstructured":"Sabour, S., Frosst, N., and Hinton, G.E. (2017). Dynamic routing between capsules. Proceedings of the 31st International Conference on Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Gu, P., Zhang, Y., Wang, C., and Chen, D.Z. (2023, January 18\u201321). ConvFormer: Combining CNN and Transformer for Medical Image Segmentation. Proceedings of the 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena de Indias, Colombia.","DOI":"10.1109\/ISBI53787.2023.10230838"},{"key":"ref_20","unstructured":"Wightman, R., Touvron, H., and J\u00e9gou, H. (2021). Resnet strikes back: An improved training procedure in timm. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"14634","DOI":"10.1038\/s41598-021-93977-0","article-title":"Efficient-CapsNet: Capsule network with self-attention routing","volume":"11","author":"Mazzia","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_22","unstructured":"Hinton, G.E., Sabour, S., and Frosst, N. (May, January 30). Matrix capsules with EM routing. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_23","unstructured":"Garau, N., and Conci, N. (2023). Capsules as viewpoint learners for human pose estimation. arXiv."},{"key":"ref_24","unstructured":"National Medical Products Administration, and National Health Commission (2025, July 12). Quality Management Standard for Clinical Trials of Medical Devices (No. 28, 2022), Available online: https:\/\/www.nmpa.gov.cn\/xxgk\/ggtg\/ylqxggtg\/ylqxqtggtg\/20220331144903101.html."},{"key":"ref_25","unstructured":"National Medical Products Administration (2025, October 12). Regulation on the Supervision and Administration of Medical Devices, Available online: https:\/\/www.nmpa.gov.cn\/xxgk\/fgwj\/flxzhfg\/20250416172904188.html?type=pc&m=."},{"key":"ref_26","first-page":"302","article-title":"Characteristics analysis of early gastric cancer under white light endoscopy","volume":"51","author":"Liu","year":"2019","journal-title":"Peking Univ. (Health Sci.)"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"7800","DOI":"10.1007\/s00464-022-09319-2","article-title":"A deep learning-based model improves diagnosis of early gastric cancer under narrow band imaging endoscopy","volume":"36","author":"Tang","year":"2022","journal-title":"Surg. Endosc."},{"key":"ref_28","unstructured":"Chinese Society of Digestive Endoscopy (2024). Consensus on the endoscopic diagnosis and treatment for early gastric cancer in China (2023, Taiyuan). Chin. J. Dig. Endosc., 41, 421\u2013442."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/3\/356\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T05:14:58Z","timestamp":1773983698000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/3\/356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["bioengineering13030356"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13030356","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]}}}