Abstract
Background
Patients with pancreatic cancer (PC) have poor prognosis and a high incidence of recurrence. Since further treatment is applicable for specific recurrent events, it is important to predict recurrence patterns after surgery. This study aimed to identify and predict early and late recurrence patterns of PC using a histology-based machine learning model.
Patients and Methods
Patients who underwent upfront curative surgery for PC between 2001 and 2014 were included. The timing of recurrence and prognosis of each first recurrence site were examined. A histology-based supervised machine learning method, which combined convolutional neural networks and random forest, was used to predict the recurrence and respective sites of metastasis. Accuracy was evaluated using area under the receiver operating characteristic curve (AUC).
Results
In total, 524 patients were included. Recurrence in the liver accounted for 47.8% of all recurrence events in the first year after surgery. Meanwhile, recurrence in the lung occurred later and could become apparent more than 5 years post-surgery, with indications for further surgery. In terms of substantial distant organ metastases, liver and lung metastases were identified as representative early and late recurrence events. The predictive AUCs of the machine learning model for training and test data were 1.000 and 0.861, respectively, and for predicting nonrecurrence were 1.000 for both.
Conclusions
We identified the liver and lung as early and late recurrence sites, which could be distinguished with high probability using a machine learning model. Prediction of recurrence sites using this model may be useful for further treatment of patients with PC.
Similar content being viewed by others
References
Siegel RL, Miller KD, Jemal A. Cancer statistics, 2020. CA Cancer J Clin. 2020;70(1):7–30.
Uesaka K, Boku N, Fukutomi A, et al. Adjuvant chemotherapy of S-1 versus gemcitabine for resected pancreatic cancer: a phase 3, open-label, randomised, non-inferiority trial (JASPAC 01). Lancet. 2016;388(10041):248–57.
Tanaka M, Mihaljevic AL, Probst P, et al. Meta-analysis of recurrence pattern after resection for pancreatic cancer. Br J Surg. 2019;106(12):1590–601.
Groot VP, Rezaee N, Wu W, et al. Patterns, timing, and predictors of recurrence following pancreatectomy for pancreatic ductal adenocarcinoma. Ann Surg. 2018;267(5):936–45.
Groot VP, Gemenetzis G, Blair AB, et al. Implications of the pattern of disease recurrence on survival following pancreatectomy for pancreatic ductal adenocarcinoma. Ann Surg Oncol. 2018;25(8):2475–83.
Oba A, Inoue Y, Ono Y, et al. Radiologically occult metastatic pancreatic cancer: how can we avoid unbeneficial resection? Langenbecks Arch Surg. 2020;405(1):35–41.
Zheng B, Ohuchida K, Yan Z, Okumura T, Ohtsuka T, Nakamura M. Primary recurrence in the lung is related to favorable prognosis in patients with pancreatic cancer and postoperative recurrence. World J Surg. 2017;41(11):2858–66.
Lovecek M, Skalicky P, Chudacek J, et al. Different clinical presentations of metachronous pulmonary metastases after resection of pancreatic ductal adenocarcinoma: retrospective study and review of the literature. World J Gastroenterol. 2017;23(35):6420–8.
Matsuda R, Miyasaka Y, Ohishi Y, et al. Concomitant intraductal papillary mucinous neoplasm in pancreatic ductal adenocarcinoma is an independent predictive factor for the occurrence of new cancer in the remnant pancreas. Ann Surg. 2020;271(5):941–8.
Hashimoto D, Chikamoto A, Masuda T, et al. Pancreatic cancer arising from the remnant pancreas: is it a local recurrence or new primary lesion? Pancreas. 2017;46(9):1083–90.
Gotoh Y, Ohtsuka T, Nakamura S, et al. Genetic assessment of recurrent pancreatic high-risk lesions in the remnant pancreas: metachronous multifocal lesion or local recurrence? Surgery. 2019;165(4):767–74.
Komura D, Ishikawa S. Machine learning methods for histopathological image analysis. Comput Struct Biotechnol J. 2018;16:34–42.
Skrede O-J, De Raedt S, Kleppe A, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet. 2020;395(10221):350–60.
Takamatsu M, Yamamoto N, Kawachi H, et al. Prediction of early colorectal cancer metastasis by machine learning using digital slide images. Comput Methods Programs Biomed. 2019;178:155–61.
Kather JN, Pearson AT, Halama N, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med. 2019;25(7):1054–6.
Inoue Y, Saiura A, Oba A, et al. Neoadjuvant gemcitabine and nab-paclitaxel for borderline resectable pancreatic cancers: intention-to-treat analysis compared with upfront surgery. J Hepatobiliary Pancreat Sci. 2021;28(2):143–55.
Tempero MA, Malafa MP, Chiorean EG, et al. Pancreatic adenocarcinoma, version 1. J Natl Compr Canc Netw. 2019;17(3):202–10.
Inoue Y, Saiura A, Yoshioka R, et al. Pancreatoduodenectomy with systematic mesopancreas dissection using a supracolic anterior artery-first approach. Ann Surg. 2015;262(6):1092–101.
Inoue Y, Saiura A, Oba A, et al. Optimal extent of superior mesenteric artery dissection during pancreaticoduodenectomy for pancreatic cancer: balancing surgical and oncological safety. J Gastrointest Surg. 2019;23(7):1373–83.
Sato T, Inoue Y, Takahashi Y, et al. Distal pancreatectomy with celiac axis resection combined with reconstruction of the left gastric artery. J Gastrointest Surg. 2017;21(5):910–7.
Bassi C, Marchegiani G, Dervenis C, et al. The 2016 update of the International Study Group (ISGPS) definition and grading of postoperative pancreatic fistula: 11 Years After. Surgery. 2017;161(3):584–91.
Wente MN, Bassi C, Dervenis C, et al. Delayed gastric emptying (DGE) after pancreatic surgery: a suggested definition by the International Study Group of Pancreatic Surgery (ISGPS). Surgery. 2007;142(5):761–8.
Dindo D, Demartines N, Clavien P-A. Classification of surgical complications. Ann Surg. 2004;240(2):205–13.
Brierley JD, Union for International Cancer Control. TNM classification of malignant tumours. Eighth edition. ed: https://yale.idm.oclc.org/login?URL=https://ebookcentral.proquest.com/lib/yale-ebooks/detail.action?docID=4792667.
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. Mobilenetv2: inverted residuals and linear bottlenecks. In: Paper presented at: Proceedings of the IEEE conference on computer vision and pattern recognition2018.
Breiman L. Random forests. Mach Learn. 2001;45(1):5–32.
Ariake K, Motoi F, Ohtsuka H, et al. Predictive risk factors for peritoneal recurrence after pancreatic cancer resection and strategies for its prevention. Surg Today. 2017;47(12):1434–42.
Yoshioka R, Saiura A, Koga R, et al. The implications of positive peritoneal lavage cytology in potentially resectable pancreatic cancer. World J Surg. 2012;36(9):2187–91.
Shibata K, Matsumoto T, Yada K, Sasaki A, Ohta M, Kitano S. Factors predicting recurrence after resection of pancreatic ductal carcinoma. Pancreas. 2005;31(1):69–73.
Sugiura T, Uesaka K, Mihara K, et al. Margin status, recurrence pattern, and prognosis after resection of pancreatic cancer. Surgery. 2013;154(5):1078–86.
Gnerlich JL, Luka SR, Deshpande AD, et al. Microscopic margins and patterns of treatment failure in resected pancreatic adenocarcinoma. Arch Surg. 2012;147(8):753–60.
Van den Broeck A, Sergeant G, Ectors N, Van Steenbergen W, Aerts R, Topal B. Patterns of recurrence after curative resection of pancreatic ductal adenocarcinoma. Eur J Surg Oncol. 2009;35(6):600–4.
Nakayama Y, Sugimoto M, Gotohda N, Konishi M, Takahashi S. Efficacy of completion pancreatectomy for recurrence of adenocarcinoma in the remnant pancreas. J Surg Res. 2018;221:15–23.
Tan KK, Lopes Gde L Jr, Sim R. How uncommon are isolated lung metastases in colorectal cancer? A review from database of 754 patients over 4 years. J Gastrointest Surg. Apr 2009;13(4):642–8.
Suenaga M, Fujii T, Kanda M, et al. Pattern of first recurrent lesions in pancreatic cancer: hepatic relapse is associated with dismal prognosis and portal vein invasion. Hepatogastroenterology. 2014;61(134):1756–61.
Arnaoutakis GJ, Rangachari D, Laheru DA, et al. Pulmonary resection for isolated pancreatic adenocarcinoma metastasis: an analysis of outcomes and survival. J Gastrointest Surg. 2011;15(9):1611–7.
Kruger S, Haas M, Burger PJ, et al. Isolated pulmonary metastases define a favorable subgroup in metastatic pancreatic cancer. Pancreatology. 2016;16(4):593–8.
Groot VP, Blair AB, Gemenetzis G, et al. Isolated pulmonary recurrence after resection of pancreatic cancer: the effect of patient factors and treatment modalities on survival. HPB (Oxford). 2019;21(8):998–1008.
Tani M, Kawai M, Miyazawa M, et al. Liver metastasis as an initial recurrence has no impact on the survival of patients with resectable pancreatic adenocarcinoma. Langenbecks Arch Surg. 2009;394(2):249–53.
Bychkov D, Linder N, Turkki R, et al. Deep learning based tissue analysis predicts outcome in colorectal cancer. Sci Rep. 2018;8(1):3395.
Mobadersany P, Yousefi S, Amgad M, et al. Predicting cancer outcomes from histology and genomics using convolutional networks. Proc Natl Acad Sci USA. 2018;115(13):E2970–9.
Cheng L, Li L, Wang L, Li X, Xing H, Zhou J. A random forest classifier predicts recurrence risk in patients with ovarian cancer. Mol Med Rep. 2018;18(3):3289–97.
Groot VP, Gemenetzis G, Blair AB, et al. Defining and predicting early recurrence in 957 patients with resected pancreatic ductal adenocarcinoma. Ann Surg. 2019;269(6):1154–62.
Tempero MA. NCCN guidelines updates: pancreatic cancer. J Natl Compr Canc Netw. 2019;17(55):603–5.
O’Reilly D, Fou L, Hasler E, et al. Diagnosis and management of pancreatic cancer in adults: a summary of guidelines from the UK National Institute for health and care excellence. Pancreatology. 2018;18(8):962–70.
Acknowledgement
The authors would like to thank Hiroshi Yoko-o and Tomoyo Kakita for their excellent technical assistance. We also like to thank Editage (www.editage.com) for English language editing.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Disclosure
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Hayashi, K., Ono, Y., Takamatsu, M. et al. Prediction of Recurrence Pattern of Pancreatic Cancer Post-Pancreatic Surgery Using Histology-Based Supervised Machine Learning Algorithms: A Single-Center Retrospective Study. Ann Surg Oncol 29, 4624–4634 (2022). https://doi.org/10.1245/s10434-022-11471-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1245/s10434-022-11471-x