Advances and Challenges in Artificial Intelligence and Statistical Methods for the Early Diagnosis of Pancreatic Cancer
DOI:
https://doi.org/10.61173/8jp1tk41Keywords:
Epidemiology, Multi-modal data analysis, Medical image analysis, CDSSAbstract
This study reviews the research progress, current applications, and future challenges of artificial intelligence and statistical methods in the early diagnosis of pancreatic cancer. Dubbed the ‘king of cancers’ due to its insidious early symptoms and rapid metastasis, pancreatic cancer exhibits low early detection rates, with traditional CT, MRI, and biomarker diagnostics demonstrating limited sensitivity. Artificial intelligence demonstrates significant potential in deep learning, machine learning, multimodal data analysis, medical image recognition, and clinical decision support systems, substantially enhancing the detection rate of small lesions and diagnostic accuracy. By integrating multi-source medical imaging, genomic, and clinical data, AI not only improves screening efficiency but also assists clinicians in formulating personalised treatment strategies. However, current limitations include inadequate data standardisation, insufficient explainability, and insufficient external validation. Future efforts should rely on large-scale, multicentre clinical studies to advance the clinical translation and practical application of AI models in pancreatic cancer early screening, thereby providing new avenues for reducing mortality rates.
References
[1] Chen H, Wang L, Fan D, Ma P, Zhang X, Lin K. SERS mapping combined with explainable deep learning for exosome analysis to enhance lung cancer detection. Analyst. https://doi. org/10.1039/D5AN00685F
[2] Zhang L, Sanagapalli S, Stoita A. Challenges in diagnosis of pancreatic cancer. World Journal of Gastroenterology, 2018, 24(19): 2047-2060. https://doi.org/10.3748/wjg.v24.i19.2047
[3] Rahib L, Coffin T, Kenner B. Factors driving pancreatic cancer survival rates. Pancreas, 2025, 54(6): e530-e536. https:// doi.org/10.1097/MPA.0000000000002489
[4] Health Network. National Taiwan University Hospital has launched the AI system “Zhu Pan Jian” to break through the bottleneck in early diagnosis of pancreatic cancer. UHO Health Network, 2025-05-22. https://www.uho.com.tw/article-66684. html
[5] Fornero S. What is ICD-10? Quadrant Health, 2024-07-10. https://blog.quadrant.health/what-is-icd-10
[6] Pancreatic Cancer ICD-10-CM codes. Carepatron. https:// www.carepatron.com/icd/pancreatic-cancer
[7] ICD List. ICD-10-CM diagnosis code C78.89 - Secondary malignant neoplasm of other digestive organs. ICD List. https:// icdlist.com/icd-10/C78.89
[8] Weselá P, Eid M, Moravčík P, Vlažný J, Hlavsa J, Procházka V, Kala Z, Vaňhara P. Artificial intelligence in pancreatic cancer histopathology and diagnostics: Implications for clinical decisions and biomarker discovery? Cell Division, 2025, 20(1). https://doi.org/10.1186/s13008-025-00158-w
[9] Huang B, Huang H, Zhang S, Zhang D, Shi Q, Liu J, Guo J. Artificial intelligence in pancreatic cancer. Theranostics, 2022, 12(16): 6931-6954. https://doi.org/10.7150/thno.77949
[10] Hameed B S, Krishnan U M. Artificial intelligence-driven diagnosis of pancreatic cancer. Cancers, 2022, 14(21): 5382. https://doi.org/10.3390/cancers14215382 Dean&Francis ISSN 2959-409X
[11] Zhang M M, Yang H, Jin Z D, Yu J G, Cai Z Y, Li Z S. Differential diagnosis of pancreatic cancer from normal tissue with digital imaging processing and pattern recognition based on a support vector machine of EUS images. Gastrointestinal Endoscopy, 2010, 72(5): 978-985. https://doi.org/10.1016/ j.gie.2010.06.042
[12] Kim P. MATLAB deep learning. Apress eBooks, 2017. https://doi.org/10.1007/978-1-4842-2845-6
[13] Liu Y H. Feature extraction and image recognition with convolutional neural networks. Journal of Physics Conference Series, 2018, 1087: 062032. https://doi.org/10.1088/1742- 6596/1087/6/062032
[14] Kumar A, Kim J, Lyndon D, Fulham M, Feng D. An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE Journal of Biomedical and Health Informatics, 2016, 21(1): 31-40. https://doi.org/10.1109/ jbhi.2016.2635663
[15] Siddique N, Paheding S, Elkin C P, Devabhaktuni V. U-Net and its variants for medical image segmentation: A review of theory and applications. IEEE Access, 2021, 9: 82031-82057. https://doi.org/10.1109/access.2021.3086020
[16] Coudray N, Ocampo P S, Sakellaropoulos T, Narula N, Snuderl M, Fenyö D, Moreira A L, Razavian N, Tsirigos A. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nature Medicine, 2018, 24(10): 1559-1567. https://doi.org/10.1038/ s41591-018-0177-5
[17] Vashisth V. What is multi-modal data analysis? Analytics Vidhya, 2025-07-25. https://www.analyticsvidhya.com/ blog/2025/07/what-is-multi-modal-data-analysis
[18] Schuurmans M, Saha A, Alves N, Vendittelli P, Yakar D, Sabroso-Lasa S, Xue N, Malats N, Huisman H, Hermans J, Litjens G. End-to-end prognostication in pancreatic cancer by multimodal deep learning: A retrospective, multicenter study. European Radiology, 2025. https://doi.org/10.1007/s00330-025- 11694-y
[19] Xia J, Li J, Wang X, Li Y, Li J. Enhanced cancer classification and critical feature visualization using Raman spectroscopy and convolutional neural networks. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2024, 326: 125242. https://doi.org/10.1016/j.saa.2024.125242
[20] Xin X, Danping H, Shanshan H, Yang S. Research on the diagnosis method of pancreatic lesions by endoscopic ultrasound based on twin network structure. IET Image Processing, 2025, 19(1). https://doi.org/10.1049/ipr2.70063
[21] Francis I R. Pancreatic adenocarcinoma: Diagnosis and staging using multidetector-row computed tomography (MDCT) and magnetic resonance imaging (MRI). Cancer Imaging, 2007, 7(Special issue A): S160-S165. https://doi.org/10.1102/1470- 7330.2007.9010
[22] Ben-Amitay S, Jones D K, Assaf Y. Motion correction and registration of high b-value diffusion weighted images. Magnetic Resonance in Medicine, 2011, 67(6): 1694-1702. https://doi. org/10.1002/mrm.23186
[23] Luo W, Wang J, Chen H, Cao Z, Qiu J, Liu Y, Fu Y, Yang G, Tao J, Weng G, Liu T, Wang Y, Ye L, Ding C, Lu X, Zhang M, Huang H, Xiao J, You L, Zhang T. Advances in screening and early diagnosis of pancreatic cancer. Cancer Screening and Prevention, 2024, 3(3): 154-162. https://doi.org/10.14218/ csp.2024.00006s
[24] Raut C P, Grau A M, Staerkel G A, Kaw M, Tamm E P, Wolff R A, Vauthey J N, Lee J E, Pisters P W T, Evans D B. Diagnostic accuracy of endoscopic ultrasound-guided fineneedle aspiration in patients with presumed pancreatic cancer. Journal of Gastrointestinal Surgery, 2003, 7(1): 118-128. https:// doi.org/10.1016/S1091-255X(02)00150-6
[25] Gheonea D I, Săftoiu A. Beyond conventional endoscopic ultrasound: Elastography, contrast enhancement and hybrid techniques. Current Opinion in Gastroenterology, 2011, 27(5): 423-429. https://doi.org/10.1097/MOG.0b013e328349cfab
[26] Kaur S, Baine M J, Jain M, Sasson A R, Batra S K. Early diagnosis of pancreatic cancer: Challenges and new developments. Biomarkers in Medicine, 2012, 6(5): 597-612. https://doi.org/10.2217/bmm.12.69
[27] Shortliffe E H, Sepúlveda M J. Clinical decision support in the era of artificial intelligence. JAMA, 2018, 320(21): 2199- 2200. https://doi.org/10.1001/jama.2018.17163
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
