基于人工智能技术在胰腺肿瘤早期诊断中的应用与前景
Application and Prospect of Early Diagnosis of Pancreatic Tumors Based on Artificial Intelligence Technology
摘要: 胰腺癌(Pancreatic Cancer, PC)是一种具有高度恶性特征的消化系统肿瘤,以其极低的生存率、不良的预后特性而臭名昭著,素有“癌中之王”之称。目前,PC因其缺乏典型的早期临床表现及高度侵袭性的生长特性而面临重大挑战,导致绝大多数患者在确诊时已处于疾病的中晚期阶段,进而使得该病的预后相较于其他恶性肿瘤更为严峻。近年来,随着人工智能(Artificial Intelligence, AI)技术的崛起与迅猛发展,其在各行各业中得到了广泛应用,并成功解决了诸多难题。尤其在医疗领域,AI技术取得了突破性进展。尽管PC的发病率相对较低,但其死亡率极高,多数患者在初次诊断时已步入疾病晚期。若能在早期阶段检测到肿瘤病变,患者将极有可能早期接受手术治疗,从而获得更佳的预后。胰腺癌前病变主要包括胰腺上皮内瘤变(PanIN)和粘液性囊性肿瘤(MCN),其中导管内乳头状粘液性肿瘤(IPMN)是最常见的诊断类型。本文简要概述了AI技术在胰腺肿瘤早期诊断中的当前应用状况及创新成果,通过运用无创技术与人工智能(AI)手段,识别PC的早期迹象并进行预测,为胰腺肿瘤的早期诊断带来了全新的曙光,并对PC的研究提供参考依据。
Abstract: Pancreatic cancer (PC) is a highly malignant tumor of the digestive system, infamous for its extremely low survival rate and poor prognosis, and known as the “king of cancers”. Currently, PC faces significant challenges due to its lack of typical early clinical manifestations and highly aggressive growth characteristics, resulting in the majority of patients being diagnosed in the middle to late stages of the disease, which makes the prognosis of the disease more severe compared to other malignant tumors. In recent years, with the rise and rapid development of Artificial Intelligence (AI) technology, it has been widely used in various industries and successfully solved many problems. Especially in the medical field, AI technology has made breakthrough progress. Although the incidence of PC is relatively low, its mortality rate is extremely high, and most patients are already in the advanced stages of the disease when they are first diagnosed. However, if a tumor lesion can be detected at an early stage, the patient will most likely undergo surgical treatment, resulting in the best prognosis. Pancreatic precancerous lesions mainly include pancreatic intraepithelial neoplasia (PanIN) and mucinous cystic neoplasia (MCN), with intraductal papillary mucinous neoplasia (IPMN) being the most commonly diagnosed type. Our research team is dedicated to identifying early signs of PC and predicting them through the use of non-invasive techniques and artificial intelligence (AI) tools. This paper briefly outlines the current application status and innovative achievements of AI technology in the early diagnosis of pancreatic tumors, which brings a new light to the early diagnosis of pancreatic tumors, and presents a broad development blueprint with optimism for its future prospects.
文章引用:王伟, 鲁希国, 许强, 陈涛, 闫晓琨. 基于人工智能技术在胰腺肿瘤早期诊断中的应用与前景[J]. 医学诊断, 2025, 15(6): 547-555. https://doi.org/10.12677/md.2025.156074

参考文献

[1] Siegel, R.L., Miller, K.D., Fuchs, H.E. and Jemal, A. (2021) Cancer Statistics, 2021. CA: A Cancer Journal for Clinicians, 71, 7-33. [Google Scholar] [CrossRef] [PubMed]
[2] Rahib, L., Smith, B.D., Aizenberg, R., Rosenzweig, A.B., Fleshman, J.M. and Matrisian, L.M. (2014) Projecting Cancer Incidence and Deaths to 2030: The Unexpected Burden of Thyroid, Liver, and Pancreas Cancers in the United States. Cancer Research, 74, 2913-2921. [Google Scholar] [CrossRef] [PubMed]
[3] Zheng, Z.Y., Chen, T. and Liu, Y.B. (2023) Application and Prospect of Artificial Intelligence in Pancreatic Cancer. Chinese Journal of Surgery, 61, 76-80.
[4] LeCun, Y., Bengio, Y. and Hinton, G. (2015) Deep Learning. Nature, 521, 436-444. [Google Scholar] [CrossRef] [PubMed]
[5] Mollberg, N., Rahbari, N.N., Koch, M., Hartwig, W., Hoeger, Y., Büchler, M.W., et al. (2011) Arterial Resection during Pancreatectomy for Pancreatic Cancer. Annals of Surgery, 254, 882-893. [Google Scholar] [CrossRef] [PubMed]
[6] Kwon, J., Shin, S.H., Yoo, D., Hong, S., Lee, J.W., Youn, W.Y., et al. (2020) Arterial Resection during Pancreatectomy for Pancreatic Ductal Adenocarcinoma with Arterial Invasion: A Single-Center Experience with 109 Patients. Medicine, 99, e22115. [Google Scholar] [CrossRef] [PubMed]
[7] Campbell, N.M., Katz, S.S., Escalon, J.G. and Do, R.K. (2015) Imaging Patterns of Intraductal Papillary Mucinous Neoplasms of the Pancreas: An Illustrated Discussion of the International Consensus Guidelines for the Management of IPMN. Abdominal Imaging, 40, 663-677. [Google Scholar] [CrossRef] [PubMed]
[8] Kuwahara, T., Hara, K., Mizuno, N., Okuno, N., Matsumoto, S., Obata, M., et al. (2019) Usefulness of Deep Learning Analysis for the Diagnosis of Malignancy in Intraductal Papillary Mucinous Neoplasms of the Pancreas. Clinical and Translational Gastroenterology, 10, e00045. [Google Scholar] [CrossRef] [PubMed]
[9] Sharma, A., Kandlakunta, H., Nagpal, S.J.S., Feng, Z., Hoos, W., Petersen, G.M., et al. (2018) Model to Determine Risk of Pancreatic Cancer in Patients with New-Onset Diabetes. Gastroenterology, 155, 730-739.e3. [Google Scholar] [CrossRef] [PubMed]
[10] Hsieh, M.H., Sun, L., Lin, C., Hsieh, M., Hsu, C. and Kao, C. (2018) Development of a Prediction Model for Pancreatic Cancer in Patients with Type 2 Diabetes Using Logistic Regression and Artificial Neural Network Models. Cancer Management and Research, 10, 6317-6324. [Google Scholar] [CrossRef] [PubMed]
[11] Boursi, B., Finkelman, B., Giantonio, B.J., Haynes, K., Rustgi, A.K., Rhim, A.D., et al. (2017) A Clinical Prediction Model to Assess Risk for Pancreatic Cancer among Patients with New-Onset Diabetes. Gastroenterology, 152, 840-850.e3. [Google Scholar] [CrossRef] [PubMed]
[12] Cui, J., Jiao, F., Li, Q., Wang, Z., Fu, D., Liang, J., et al. (2022) Chinese Society of Clinical Oncology (CSCO): Clinical Guidelines for the Diagnosis and Treatment of Pancreatic Cancer. Journal of the National Cancer Center, 2, 205-215. [Google Scholar] [CrossRef] [PubMed]
[13] Javed, N., Ghazanfar, H., Balar, B. and Patel, H. (2024) Role of Artificial Intelligence in Endoscopic Intervention: A Clinical Review. Journal of Community Hospital Internal Medicine Perspectives, 14, 37-43. [Google Scholar] [CrossRef] [PubMed]
[14] Seufferlein, T., Bachet, J.B., Van Cutsem, E. and Rougier, P. (2012) Pancreatic Adenocarcinoma: ESMO-ESDO Clinical Practice Guidelines for Diagnosis, Treatment and Follow-Up. Annals of Oncology, 23, vii33-vii40. [Google Scholar] [CrossRef] [PubMed]
[15] Bartoli, M., Barat, M., Dohan, A., Gaujoux, S., Coriat, R., Hoeffel, C., et al. (2020) CT and MRI of Pancreatic Tumors: An Update in the Era of Radiomics. Japanese Journal of Radiology, 38, 1111-1124. [Google Scholar] [CrossRef] [PubMed]
[16] Si, K., Xue, Y., Yu, X., Zhu, X., Li, Q., Gong, W., et al. (2021) Fully End-to-End Deep-Learning-Based Diagnosis of Pancreatic Tumors. Theranostics, 11, 1982-1990. [Google Scholar] [CrossRef] [PubMed]
[17] Ma, H., Liu, Z., Zhang, J., Wu, F., Xu, C., Shen, Z., et al. (2020) Construction of a Convolutional Neural Network Classifier Developed by Computed Tomography Images for Pancreatic Cancer Diagnosis. World Journal of Gastroenterology, 26, 5156-5168. [Google Scholar] [CrossRef] [PubMed]
[18] Marya, N.B., Powers, P.D., Chari, S.T., Gleeson, F.C., Leggett, C.L., Abu Dayyeh, B.K., et al. (2021) Utilisation of Artificial Intelligence for the Development of an EUS-Convolutional Neural Network Model Trained to Enhance the Diagnosis of Autoimmune Pancreatitis. Gut, 70, 1335-1344. [Google Scholar] [CrossRef] [PubMed]
[19] Karunakaran, M. and Barreto, S.G. (2021) Surgery for Pancreatic Cancer: Current Controversies and Challenges. Future Oncology, 17, 5135-5162. [Google Scholar] [CrossRef] [PubMed]
[20] Augustinus, S., Schafrat, P.J.M., Janssen, B.V., Bonsing, B.A., Brosens, L.A.A., Busch, O.R., et al. (2023) Nationwide Impact of Centralization, Neoadjuvant Therapy, Minimally Invasive Surgery, and Standardized Pathology Reporting on R0 Resection and Overall Survival in Pancreatoduodenectomy for Pancreatic Cancer. Annals of Surgical Oncology, 30, 5051-5060. [Google Scholar] [CrossRef] [PubMed]
[21] Janssen, B.V., Theijse, R., van Roessel, S., de Ruiter, R., Berkel, A., Huiskens, J., et al. (2021) Artificial Intelligence-Based Segmentation of Residual Tumor in Histopathology of Pancreatic Cancer after Neoadjuvant Treatment. Cancers, 13, Article 5089. [Google Scholar] [CrossRef] [PubMed]
[22] Nasief, H., Zheng, C., Schott, D., Hall, W., Tsai, S., Erickson, B., et al. (2019) A Machine Learning Based Delta-Radiomics Process for Early Prediction of Treatment Response of Pancreatic Cancer. npj Precision Oncology, 3, Article No. 25. [Google Scholar] [CrossRef] [PubMed]
[23] Fang, C., Zhu, W., Wang, H., Xiang, N., Fan, Y., Yang, J., et al. (2012) A New Approach for Evaluating the Resectability of Pancreatic and Periampullary Neoplasms. Pancreatology, 12, 364-371. [Google Scholar] [CrossRef] [PubMed]
[24] Volonté, F., Pugin, F., Bucher, P., Sugimoto, M., Ratib, O. and Morel, P. (2011) Augmented Reality and Image Overlay Navigation with Osirix in Laparoscopic and Robotic Surgery: Not Only a Matter of Fashion. Journal of Hepato-Biliary-Pancreatic Sciences, 18, 506-509. [Google Scholar] [CrossRef] [PubMed]
[25] Tang, R., Yang, W., Hou, Y., Yu, L., Wu, G., Tong, X., et al. (2021) Augmented Reality-Assisted Pancreaticoduodenectomy with Superior Mesenteric Vein Resection and Reconstruction. Gastroenterology Research and Practice, 2021, Article ID: 9621323. [Google Scholar] [CrossRef] [PubMed]
[26] Pulvirenti, A., Ramera, M. and Bassi, C. (2017) Modifications in the International Study Group for Pancreatic Surgery (ISGPS) Definition of Postoperative Pancreatic Fistula. Translational Gastroenterology and Hepatology, 2, 107-107. [Google Scholar] [CrossRef] [PubMed]
[27] Callery, M.P., Pratt, W.B., Kent, T.S., Chaikof, E.L. and Vollmer, C.M. (2013) A Prospectively Validated Clinical Risk Score Accurately Predicts Pancreatic Fistula after Pancreatoduodenectomy. Journal of the American College of Surgeons, 216, 1-14. [Google Scholar] [CrossRef] [PubMed]
[28] Han, I.W., Cho, K., Ryu, Y., Shin, S.H., Heo, J.S., Choi, D.W., et al. (2020) Risk Prediction Platform for Pancreatic Fistula after Pancreatoduodenectomy Using Artificial Intelligence. World Journal of Gastroenterology, 26, 4453-4464. [Google Scholar] [CrossRef] [PubMed]
[29] Zhang, Y., Zhu, S., Yuan, Z., Li, Q., Ding, R., Bao, X., et al. (2020) Risk Factors and Socio-Economic Burden in Pancreatic Ductal Adenocarcinoma Operation: A Machine Learning Based Analysis. BMC Cancer, 20, Article No. 1161. [Google Scholar] [CrossRef] [PubMed]
[30] Lee, K., Jang, J., Yu, Y., Heo, J.S., Han, H., Yoon, Y., et al. (2021) Usefulness of Artificial Intelligence for Predicting Recurrence Following Surgery for Pancreatic Cancer: Retrospective Cohort Study. International Journal of Surgery, 93, Article 106050. [Google Scholar] [CrossRef] [PubMed]
[31] Tong, Z., Liu, Y., Ma, H., Zhang, J., Lin, B., Bao, X., et al. (2020) Development, Validation and Comparison of Artificial Neural Network Models and Logistic Regression Models Predicting Survival of Unresectable Pancreatic Cancer. Frontiers in Bioengineering and Biotechnology, 8, Article No. 196. [Google Scholar] [CrossRef] [PubMed]
[32] Shin, H., Roth, H.R., Gao, M., Lu, L., Xu, Z., Nogues, I., et al. (2016) Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Transactions on Medical Imaging, 35, 1285-1298. [Google Scholar] [CrossRef] [PubMed]
[33] Shah, P., Mishra, D., Shanmugam, M., Doshi, B., Jayaraj, H. and Ramanjulu, R. (2020) Validation of Deep Convolutional Neural Network-Based Algorithm for Detection of Diabetic Retinopathy—Artificial Intelligence versus Clinician for Screening. Indian Journal of Ophthalmology, 68, 398-405. [Google Scholar] [CrossRef] [PubMed]
[34] Liu, H., Seedat, N. and Ive, J. (2024) Modeling Disagreement in Automatic Data Labeling for Semi-Supervised Learning in Clinical Natural Language Processing. Frontiers in Artificial Intelligence, 7, Article ID: 1374162. [Google Scholar] [CrossRef] [PubMed]
[35] Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., et al. (2017) Artificial Intelligence in Healthcare: Past, Present and Future. Stroke and Vascular Neurology, 2, 230-243. [Google Scholar] [CrossRef] [PubMed]
[36] Manickam, P., Mariappan, S.A., Murugesan, S.M., Hansda, S., Kaushik, A., Shinde, R., et al. (2022) Artificial Intelligence (AI) and Internet of Medical Things (IoMT) Assisted Biomedical Systems for Intelligent Healthcare. Biosensors, 12, Article 562. [Google Scholar] [CrossRef] [PubMed]