Pancreatic cancer is a lethal disease characterized by a poor prognosis for patients, making early diagnosis crucial for improving patient survival rates. Artificial intelligence (AI), particularly exemplified by deep learning and radiomics, has provided new directions for the early diagnosis of this disease. This paper reviews the progress of AI based on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Endoscopic Ultrasound (EUS) in the early diagnosis of pancreatic cancer. It specifically focuses on the value of end-to-end deep learning models and radiomics-based machine learning in differentiating pancreatic cancer from normal pancreatic tissue. Models such as Convolutional Neural Networks (CNNs), nnU-Net, and Vision Transformers have demonstrated pancreatic tumor detection rates ranging from 86.2% to 95.8%. Furthermore, by integrating mass signs with indirect imaging features like pancreatic duct dilation, the detection sensitivity for pancreatic cancers smaller than 2 cm has been improved to 70.7%-96%. Additionally, radiomics has shown potential in predicting tumor occurrence using CT images obtained 3 to 36 months prior to clinical diagnosis. Future research on image-based AI for early pancreatic cancer diagnosis should focus on multicenter prospective studies. The ultimate goal is to build intelligent diagnostic systems that are high-performing, robust, and interpretable, while seamlessly integrating into clinical workflows.

Lei Wang, Chao Ma, Jianping Lu. AI-Driven Early Diagnosis of Pancreatic Cancer: Current Status and Future Perspectives. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 3: 1-10. https://doi.org/10.25236/AJCIS.2026.090301.

[1] Farinella R, Felici A, Peduzzi G, et al. From classical approaches to artificial intelligence, old and new tools for PDAC risk stratification and prediction[J]. Seminars in cancer biology, 2025, 112: 71.

[2] Siegel R L, Giaquinto A N, Jemal A. Cancer statistics, 2024[J]. CA: a cancer journal for clinicians, 2024, 74(01): 12.

[3] Renjifo-Correa M E, Fanni S C, Bustamante-Cristancho L A, et al. Diagnostic accuracy of radiomics in the early detection of pancreatic cancer: a systematic review and qualitative assessment using the methodological radiomics score (METRICS)[J]. Cancers, 2025, 17(05): 803.

[4] Grossberg A J, Chu L C, Deig C R, et al. Multidisciplinary standards of care and recent progress in pancreatic ductal adenocarcinoma[J]. CA: a cancer journal for clinicians, 2020, 70(05): 375.

[5] Pereira S P, Oldfield L, Ney A, et al. Early detection of pancreatic cancer[J]. The lancet. Gastroenterology & hepatology, 2020, 5(07): 698.

[6] Haeberle L, Esposito I. Pathology of pancreatic cancer[J]. Translational gastroenterology and hepatology, 2019, 4: 50.

[7] Antony A, Mukherjee S, Bhinder K, et al. Artificial intelligence-augmented imaging for early pancreatic cancer detection[J]. Visceral medicine, 2025: 1.

[8] Singhi A D, Koay E J, Chari S T, et al. Early detection of pancreatic cancer: opportunities and challenges[J]. Gastroenterology, 2019, 156(07): 2024.

[9] Zhang L, Sanagapalli S, Stoita A. Challenges in diagnosis of pancreatic cancer[J]. World journal of gastroenterology, 2018, 24(19): 2047.

[10] Yang J, Xu R, Wang C, et al. Early screening and diagnosis strategies of pancreatic cancer: a comprehensive review[J]. Cancer communications (London, England), 2021, 41(12): 1257.

[11] Chu L C, Goggins M G, Fishman E K. Diagnosis and detection of pancreatic cancer[J]. Cancer journal (Sudbury, Mass.), 2017, 23(06): 333.

[12] Liao X, Zhang D. The 8th edition American Joint Committee on Cancer staging for hepato-pancreato-biliary cancer: a review and update[J]. Archives of pathology & laboratory medicine, 2021, 145(05): 543.

[13] Hoogenboom S A, Engels M M L, Chuprin A V, et al. Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case-control study[J]. Abdominal radiology (New York), 2022, 47(12): 4160.

[14] Lin Z, Adeniran E A, Cai Y, et al. Early detection of pancreatic cancer: current advances and future opportunities[J]. Biomedicines, 2025, 13(07): 1733.

[15] Stoffel E M, Brand R E, Goggins M. Pancreatic cancer: changing epidemiology and new approaches to risk assessment, early detection, and prevention[J]. Gastroenterology, 2023, 164(05): 752.

[16] Kang J D, Clarke S E, Costa A F. Factors associated with missed and misinterpreted cases of pancreatic ductal adenocarcinoma[J]. European radiology, 2021, 31(04): 2422.

[17] Ozawa M, Sone M, Hijioka S, et al. Deep learning-based automatic detection of pancreatic ductal adenocarcinoma ≤ 2 cm with high-resolution computed tomography: impact of the combination of tumor mass detection and indirect indicator evaluation[J]. Japanese journal of radiology, 2025, 43(11): 1870.

[18] Garvey C J, Hanlon R. Computed tomography in clinical practice[J]. BMJ (Clinical research ed.), 2002, 324(7345): 1077.

[19] Ramachandra H V, Chavan P, Ali A, et al. Ensemble machine learning techniques for pancreatic cancer detection[C]. 2023 International Conference on Applied Intelligence and Sustainable Computing (ICAISC), 2023: 1.

[20] Ahmed S, Elazab N, El-Gayar M M, et al. Multi-scale vision transformer with optimized feature fusion for mammographic breast cancer classification[J]. Diagnostics (Basel, Switzerland), 2025, 15(11): 1361.

[21] Aburass S, Dorgham O, Al Shaqsi J, et al. Vision transformers in medical imaging: a comprehensive review of advancements and applications across multiple diseases[J]. Journal of imaging informatics in medicine, 2025, 38(06): 3928.

[22] Jin S, Yu S, Peng J, et al. A novel medical image segmentation approach by using multi-branch segmentation network based on local and global information synchronous learning[J]. Scientific reports, 2023, 13(01): 6762.

[23] Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. European journal of cancer (Oxford, England : 1990), 2012, 48(04): 441.

[24] Tixier F, Hatt M, Le Rest C C, et al. Reproducibility of tumor uptake heterogeneity characterization through textural feature analysis in 18F-FDG PET[J]. Journal of nuclear medicine, 2012, 53(05): 693.

[25] Yang E, Kim J H, Min J H, et al. nnU-Net-based pancreas segmentation and volume measurement on CT imaging in patients with pancreatic cancer[J]. Academic radiology, 2024, 31(07): 2784.

[26] Kawamoto S, Zhu Z, Chu L C, et al. Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies[J]. Abdominal radiology (New York), 2024, 49(02): 501.

[27] Ma H, Liu Z X, Zhang J J, et al. Construction of a convolutional neural network classifier developed by computed tomography images for pancreatic cancer diagnosis[J]. World journal of gastroenterology, 2020, 26(34): 5156.

[28] Chen P T, Wu T, Wang P, et al. Pancreatic cancer detection on CT scans with deep learning: a nationwide population-based study[J]. Radiology, 2023, 306(01): 172.

[29] Abi Nader C, Vetil R, Wood L K, et al. Automatic detection of pancreatic lesions and main pancreatic duct dilatation on portal venous CT scans using deep learning[J]. Investigative radiology, 2023, 58(11): 791.

[30] Saraiva M M, González-Haba M, Widmer J, et al. Deep learning and automatic differentiation of pancreatic lesions in endoscopic ultrasound: a transatlantic study[J]. Clinical and translational gastroenterology, 2024, 15(11): e00771.

[31] Tonozuka R, Itoi T, Nagata N, et al. Deep learning analysis for the detection of pancreatic cancer on endosonographic images: a pilot study[J]. Journal of hepato-biliary-pancreatic sciences, 2021, 28(01): 95.

[32] Ni J K, Ling Z L, Liang X, et al. A convolutional neural network-based system for identifying neuroendocrine neoplasms and multiple types of lesions in the pancreas using EUS (with videos)[J]. Gastrointestinal endoscopy, 2025, 101(05): 1020.

[33] Ichikawa Y, Kanii Y, Yamazaki A, et al. The usefulness of low-kiloelectron volt virtual monochromatic contrast-enhanced computed tomography with deep learning image reconstruction technique in improving the delineation of pancreatic ductal adenocarcinoma[J]. Journal of imaging informatics in medicine, 2025, 38(02): 1236.

[34] Chen P T, Chang D, Yen H, et al. Radiomic features at CT can distinguish pancreatic cancer from noncancerous pancreas[J]. Radiology. Imaging cancer, 2021, 3(04): e210010.

[35] Chu L C, Park S, Kawamoto S, et al. Utility of CT radiomics features in differentiation of pancreatic ductal adenocarcinoma from normal pancreatic tissue[J]. AJR. American journal of roentgenology, 2019, 213(02): 349.

[36] Ren S, Qian L C, Cao Y Y, et al. Computed tomography-based radiomics diagnostic approach for differential diagnosis between early- and late-stage pancreatic ductal adenocarcinoma[J]. World journal of gastrointestinal oncology, 2024, 16(04): 1256.

[37] Wang S, Lin C, Kolomaya A, et al. Compute tomography radiomics analysis on whole pancreas between healthy individual and pancreatic ductal adenocarcinoma patients: uncertainty analysis and predictive modeling[J]. Technology in cancer research & treatment, 2022, 21: 15330338221126869.

[38] Javed S, Qureshi T A, Gaddam S, et al. Risk prediction of pancreatic cancer using AI analysis of pancreatic subregions in computed tomography images[J]. Frontiers in oncology, 2022, 12: 1007990.

[39] Mukherjee S, Patra A, Khasawneh H, et al. Radiomics-based machine-learning models can detect pancreatic cancer on prediagnostic computed tomography scans at a substantial lead time before clinical diagnosis[J]. Gastroenterology, 2022, 163(05): 1435.

[40] Koch V, Weitzer N, Dos Santos D P, et al. Multiparametric detection and outcome prediction of pancreatic cancer involving dual-energy CT, diffusion-weighted MRI, and radiomics[J]. Cancer Imaging, 2023, 23(01): 38.

[41] Gotta J, Gruenewald L D, Martin S S, et al. Unmasking pancreatic cancer: advanced biomedical imaging for its detection in native versus arterial dual-energy computed tomography (DECT) scans[J]. International Journal of Imaging Systems and Technology, 2024, 34(02): e23037. 

[42] Chang D, Chen P T, Wang P, et al. Detection of pancreatic cancer with two- and three-dimensional radiomic analysis in a nationwide population-based real-world dataset[J]. BMC cancer, 2023, 23(01): 58.

[43] Mukherjee S, Korfiatis P, Patnam N G, et al. Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods[J]. Abdominal radiology (New York), 2024, 49(03): 964.

[44] Chu L C, Solmaz B, Park S, et al. Diagnostic performance of commercially available vs. in-house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls[J]. Abdominal radiology (New York), 2020, 45(08): 2469.

[45] Cao K, Xia Y, Yao J, et al. Large-scale pancreatic cancer detection via non-contrast CT and deep learning[J]. Nature medicine, 2023, 29(12): 3033.

[46] Esteva A, Kuprel B, Novoa R A, et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 542(7639): 115.

[47] De Fauw J, Ledsam J R, Romera-Paredes B, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease[J]. Nature medicine, 2018, 24(09): 1342.

[48] Ardila D, Kiraly A P, Bharadwaj S, et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography[J]. Nature medicine, 2019, 25(06): 954.

[49] Topol E J. High-performance medicine: the convergence of human and artificial intelligence[J]. Nature medicine, 2019, 25(01): 44.

[50] McKinney S M, Sieniek M, Godbole V, et al. International evaluation of an AI system for breast cancer screening[J]. Nature, 2020, 577(7788): 89.

[51] Lotter W, Diab A R, Haslam B, et al. Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach[J]. Nature medicine, 2021, 27(02): 244.

[52] Bakas S, Reyes M, Jakab A, et al. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge[J]. Computing Research Repository, 2018.