Accurate prediction of histological grading of intraductal papillary mucinous neoplasia using deep learning

Abstract

Background Risk stratification and recommendation for surgery for intraductal papillary mucinous neoplasm (IPMN) are currently based on consensus guidelines. Risk stratification from presurgery histology is only potentially decisive owing to the low sensitivity of fine-needle aspiration. In this study, we developed and validated a deep learning-based method to distinguish between IPMN with low grade dysplasia and IPMN with high grade dysplasia/invasive carcinoma using endoscopic ultrasound (EUS) images.

Methods For model training, we acquired a total of 3355 EUS images from 43 patients who underwent pancreatectomy from March 2015 to August 2021. All patients had histologically proven IPMN. We used transfer learning to fine-tune a convolutional neural network and to classify “low grade IPMN” from “high grade IPMN/invasive carcinoma.” Our test set consisted of 1823 images from 27 patients, recruiting 11 patients retrospectively, 7 patients prospectively, and 9 patients externally. We compared our results with the prediction based on international consensus guidelines.

Results Our approach could classify low grade from high grade/invasive carcinoma in the test set with an accuracy of 99.6 % (95 %CI 99.5 %–99.9 %). Our deep learning model achieved superior accuracy in prediction of the histological outcome compared with any individual guideline, which have accuracies between 51.8 % (95 %CI 31.9 %–71.3 %) and 70.4 % (95 %CI 49.8–86.2).

Conclusion This pilot study demonstrated that deep learning in IPMN-EUS images can predict the histological outcome with high accuracy.

Publication History

Received: 01 May 2022

Accepted after revision: 02 November 2022

Accepted Manuscript online:
02 November 2022

Article published online:
22 February 2023

• References

• 1 Kromrey M-L, Bülow R, Hübner J. et al. Prospective study on the incidence, prevalence and 5-year pancreatic-related mortality of pancreatic cysts in a population-based study. Gut 2018; 67: 138
• 2 Carioli G, Malvezzi M, Bertuccio P. et al. European cancer mortality predictions for the year 2021 with focus on pancreatic and female lung cancer. Ann Oncol 2021; 32: 478-487
• 3 Suzuki R, Thosani N, Annangi S. et al. Diagnostic yield of EUS-FNA-based cytology distinguishing malignant and benign IPMNs: a systematic review and meta-analysis. Pancreatology 2014; 14: 380-384
• 4 Vege SS, Ziring B, Jain R. et al. American Gastroenterological Association institute guideline on the diagnosis and management of asymptomatic neoplastic pancreatic cysts. Gastroenterology 2015; 148: 819-822
• 5 Elta GH, Enestvedt BK, Sauer BG. et al. ACG Clinical Guideline: diagnosis and management of pancreatic cysts. Am J Gastroenterol 2018; 113: 464-479
• 6 The European Study Group on Cystic Tumours of the Pancreas. European evidence-based guidelines on pancreatic cystic neoplasms. Gut 2018; 67: 789
• 7 Tanaka M, Fernández-del Castillo C, Kamisawa T. et al. Revisions of international consensus Fukuoka guidelines for the management of IPMN of the pancreas. Pancreatology 2017; 17: 738-753
• 8 Hackert T, Fritz S, Klauss M. et al. Main-duct intraductal papillary mucinous neoplasm: high cancer risk in duct diameter of 5 to 9 mm. Ann Surg 2015; 262: 875-81
• 9 Lee JY, Jeong J, Song EM. et al. Real-time detection of colon polyps during colonoscopy using deep learning: systematic validation with four independent datasets. Sci Rep 2020; 10: 8379
• 10 Wang W, Tian J, Zhang C. et al. An improved deep learning approach and its applications on colonic polyp images detection. BMC Med Imaging 2020; 20: 83
• 11 Ahmad OF. Deep learning for colorectal polyp detection: time for clinical implementation?. Lancet Gastroenterol Hepatol 2020; 5: 330-331
• 12 Hashimoto R, Requa J, Dao T. et al. Artificial intelligence using convolutional neural networks for real-time detection of early esophageal neoplasia in Barrett’s esophagus (with video). Gastrointest Endosc 2020; 91: 1264-1271
• 13 Ebigbo A, Mendel R, Probst A. et al. Real-time use of artificial intelligence in the evaluation of cancer in Barrett’s oesophagus. Gut 2020; 69: 615-616
• 14 van der Sommen F, Zinger S, Curvers WL. et al. Computer-aided detection of early neoplastic lesions in Barrett’s esophagus. Endoscopy 2016; 48: 617-624
• 15 Ikenoyama Y, Hirasawa T, Ishioka M. et al. Detecting early gastric cancer: Comparison between the diagnostic ability of convolutional neural networks and endoscopists. Dig Endosc 2021; 33: 141-150
• 16 Hu H, Gong L, Dong D. et al. Identifying early gastric cancer under magnifying narrow-band images with deep learning: a multicenter study. Gastrointest Endosc 2021; 93: 1333-1341
• 17 Xiao Z, Ji D, Li F. et al. Application of artificial intelligence in early gastric cancer diagnosis. Digestion 2022; 103: 69-75
• 18 Marya NB, Powers PD, Chari ST. et al. Utilisation of artificial intelligence for the development of an EUS-convolutional neural network model trained to enhance the diagnosis of autoimmune pancreatitis. Gut 2021; 70: 1335
• 19 Buerlein RCD, Shami VM. Management of pancreatic cysts and guidelines: what the gastroenterologist needs to know. Ther Adv Gastrointest Endosc 2021; 14 DOI: 10.1177/26317745211045769.
• 20 Yun S, Han D, Oh SJ. et al. Cutmix: regularization strategy to train strong classifiers with localizable features. IEEE/CVF International Conference on Computer Vision (ICCV) 2019; 6023-6032 DOI: 10.1109/ICCV.2019.00612.
• 21 Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. Proc Mach Learn Res 2019; 97: 6105-6114
• 22 Deng J, Dong W, Socher R. et al. Imagenet: a large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition 2009; 248-255 DOI: 10.1109/CVPR.2009.5206848.
• 23 Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv 2014; DOI: 10.48550/arXiv.1412.6980.
• 24 Howard J, Gugger S. Fastai: a layered API for deep learning. Information 2020; 11: 108
• 25 Kimura W, Nagai H, Kuroda A. et al. Analysis of small cystic lesions of the pancreas. Int J Pancreatol 1995; 18: 197-206
• 26 Lippi G, Mattiuzzi C. The global burden of pancreatic cancer. Arch Med Sci 2020; 16: 820-824
• 27 Rahib L, Wehner MR, Matrisian LM. et al. Estimated projection of US cancer incidence and death to 2040. JAMA Network Open 2021; 4: e214708
• 28 Mas L, Lupinacci RM, Cros J. et al. Intraductal papillary mucinous carcinoma versus conventional pancreatic ductal adenocarcinoma: a comprehensive review of clinical-pathological features, outcomes, and molecular insights. Int J Mol Sci 2021; 22: 6756
• 29 Lekkerkerker SJ, Besselink MG, Busch OR. et al. Comparing 3 guidelines on the management of surgically removed pancreatic cysts with regard to pathological outcome. Gastrointest Endosc 2017; 85: 1025-1031
• 30 Tonozuka R, Mukai S, Itoi T. The role of artificial intelligence in endoscopic ultrasound for pancreatic disorders. Diagnostics 2021; 11: 18
• 31 Nguon LS, Seo K, Lim J-H. et al. Deep learning-based differentiation between mucinous cystic neoplasm and serous cystic neoplasm in the pancreas using endoscopic ultrasonography. Diagnostics 2021; 11: 1052
• 32 Kuwahara T, Hara K, Mizuno N. et al. Usefulness of deep learning analysis for the diagnosis of malignancy in intraductal papillary mucinous neoplasms of the pancreas. Clin Transl Gastroenterol 2019; 10: 1-8
• 33 Shallu S, Mehra R. Breast cancer histology images classification: training from scratch or transfer learning?. ICT Express 2018; 4: 247-254
• 34 Barman R, Deshpande S, Agarwal S. et al. Transfer learning for small dataset. Proceedings of the National Conference on Machine Learning, Mumbai, India, 26 March 2019.
• 35 Ribeiro E, Uhl A, Wimmer G. et al. exploring deep learning and transfer learning for colonic polyp classification. Comput Math Methods Med 2016; 2016: 6584725