Abstract
Purpose
To develop and validate an automated magnetic resonance imaging (MRI)-based model to preoperatively differentiate pancreatic adenosquamous carcinoma (PASC) from pancreatic ductal adenocarcinoma (PDAC).
Methods
This retrospective study included patients with surgically resected, histopathologically confirmed PASC or PDAC who underwent MRI between January 2011 and December 2020. According to time of treatment, they were divided into training and validation sets. Automated deep-learning-based artificial intelligence was used for pancreatic tumor segmentation. Linear discriminant analysis was performed with conventional MRI and radiomic features to develop clinical, radiomics, and mixed models in the training set. The models’ performances were determined from their discrimination and clinical utility. Kaplan–Meier and log-rank tests were used for survival analysis.
Results
Overall, 389 and 123 patients with PDAC (age, 61.37 ± 9.47 years; 251 men) and PASC (age, 61.99 ± 9.82 years; 78 men) were included, respectively; they were split into the training (n = 358) and validation (n = 154) sets. The mixed model showed good performance in the training and validation sets (area under the curve: 0.94 and 0.96, respectively). The sensitivity, specificity, and accuracy were 76.74%, 93.38%, and 89.39% for the training set, respectively, and 67.57%, 97.44%, and 90.26% for the validation set, respectively. The mixed model outperformed the clinical (p = 0.001) and radiomics (p = 0.04) models in the validation set. Log-rank test revealed significantly longer survival in the predicted PDAC group than in the predicted PASC group (p = 0.003), according to the mixed model.
Conclusion
Our mixed model, which combined MRI and radiomic features, can be used to differentiate PASC from PDAC.
Graphical abstract
Similar content being viewed by others
References
Hoshimoto S, Hoshi N, Hishinuma S, et al. Clinical implications of the proliferative ability of the squamous component regarding tumor progression of adenosquamous carcinoma of the pancreas: A preliminary report. Pancreatology. 2017; 17(5):788-94.
Zhao X, Li H, Lyu S, et al. Single-cell transcriptomics reveals heterogeneous progression and EGFR activation in pancreatic adenosquamous carcinoma. Int J Biol Sci. 2021; 17(10):2590-605.
Boyd CA, Benarroch-Gampel J, Sheffield KM, Cooksley CD, Riall TS. 415 patients with adenosquamous carcinoma of the pancreas: a population-based analysis of prognosis and survival. J Surg Res. 2012; 174(1):12-9.
Wild AT, Dholakia AS, Fan KY, et al. Efficacy of platinum chemotherapy agents in the adjuvant setting for adenosquamous carcinoma of the pancreas. J Gastrointest Oncol. 2015; 6(2):115-25.
De Souza AL, Saif MW. Platinum-based therapy in adenosquamous pancreatic cancer: experience at two institutions. Jop. 2014; 15(2):144-6.
Silvestris N, Brunetti O, Pinto R, et al. Immunological mutational signature in adenosquamous cancer of pancreas: an exploratory study of potentially therapeutic targets. Expert Opin Ther Targets. 2018; 22(5):453-61.
Silvestris N, Danza K, Longo V, et al. Angiogenesis in adenosquamous cancer of pancreas. Oncotarget. 2017; 8(56):95773-9.
Su W, Zhao S, Chen Y, et al. (18)F-FDG PET/CT feature of pancreatic adenosquamous carcinoma with pathological correlation. Abdom Radiol (NY). 2020; 45(3):743-9.
Matsubayashi H, Matsui T, Yabuuchi Y, et al. Endoscopic ultrasonography guided-fine needle aspiration for the diagnosis of solid pancreaticobiliary lesions: Clinical aspects to improve the diagnosis. World J Gastroenterol. 2016; 22(2):628-40.
Lee YN, Moon JH, Kim HK, et al. A triple approach for diagnostic assessment of endoscopic ultrasound-guided fine needle aspiration in pancreatic solid masses and lymph nodes. Dig Dis Sci. 2014; 59(9):2286-93.
Yasuda I, Iwashita T, Doi S. Tips for endoscopic ultrasound-guided fine needle aspiration of various pancreatic lesions. J Hepatobiliary Pancreat Sci. 2014; 21(5):E29-33.
Olson MT, Siddiqui MT, Ali SZ. The differential diagnosis of squamous cells in pancreatic aspirates: from contamination to adenosquamous carcinoma. Acta Cytol. 2013; 57(2):139-46.
Ding Y, Zhou J, Sun H, et al. Contrast-enhanced multiphasic CT and MRI findings of adenosquamous carcinoma of the pancreas. Clin Imaging. 2013; 37(6):1054-60.
Toshima F, Inoue D, Yoshida K, et al. Adenosquamous carcinoma of pancreas: CT and MR imaging features in eight patients, with pathologic correlations and comparison with adenocarcinoma of pancreas. Abdom Radiol (NY). 2016; 41(3):508-20.
Imaoka H, Shimizu Y, Mizuno N, et al. Ring-enhancement pattern on contrast-enhanced CT predicts adenosquamous carcinoma of the pancreas: a matched case-control study. Pancreatology. 2014; 14(3):221-6.
Imaoka H, Shimizu Y, Mizuno N, et al. Clinical characteristics of adenosquamous carcinoma of the pancreas: a matched case-control study. Pancreas. 2014; 43(2):287-90.
Schawkat K, Tsai LL, Jaramillo-Cardoso A, et al. Use of ring-enhancement and focal necrosis to differentiate pancreatic adenosquamous carcinoma from pancreatic ductal adenocarcinoma on CT and MRI. Clin Imaging. 2021; 73:134-8.
Ren S, Zhao R, Cui W, et al. Computed Tomography-Based Radiomics Signature for the Preoperative Differentiation of Pancreatic Adenosquamous Carcinoma From Pancreatic Ductal Adenocarcinoma. Front Oncol. 2020; 10:1618.
Moons KG, Altman DG, Reitsma JB, et al. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015; 162(1):W1-73.
Hansen TM, Nilsson M, Gram M, Frøkjær JB. Morphological and functional evaluation of chronic pancreatitis with magnetic resonance imaging. World J Gastroenterol. 2013; 19(42):7241-6.
Hester CA, Augustine MM, Choti MA, et al. Comparative outcomes of adenosquamous carcinoma of the pancreas: An analysis of the National Cancer Database. J Surg Oncol. 2018; 118(1):21-30.
Feng YF, Chen JY, Chen HY, et al. 110 Patients with adenosquamous carcinomas of the pancreas (PASC): imaging differentiation of small (≤ 3 cm) versus large (> 3 cm) tumors. Abdom Radiol (NY). 2019; 44(7):2466-73.
Iemura A, Yano H, Mizoguchi A, Kojiro M. A cholangiocellular carcinoma nude mouse strain showing histologic alteration from adenocarcinoma to squamous cell carcinoma. Cancer. 1992; 70(2):415-22.
Gao J, Han F, Jin Y, Wang X, Zhang J. A Radiomics Nomogram for the Preoperative Prediction of Lymph Node Metastasis in Pancreatic Ductal Adenocarcinoma. Front Oncol. 2020; 10:1654.
Liang Y, Schott D, Zhang Y, et al. Auto-segmentation of pancreatic tumor in multi-parametric MRI using deep convolutional neural networks. Radiother Oncol. 2020; 145:193-200.
Voong KR, Davison J, Pawlik TM, et al. Resected pancreatic adenosquamous carcinoma: clinicopathologic review and evaluation of adjuvant chemotherapy and radiation in 38 patients. Hum Pathol. 2010; 41(1):113-22.
Lee L, Ito T, Jensen RT. Imaging of pancreatic neuroendocrine tumors: recent advances, current status, and controversies. Expert Rev Anticancer Ther. 2018; 18(9):837-60.
Cantisani V, Mortele KJ, Levy A, et al. MR imaging features of solid pseudopapillary tumor of the pancreas in adult and pediatric patients. AJR Am J Roentgenol. 2003; 181(2):395-401.
Hu F, Hu Y, Wang D, et al. Cystic Neoplasms of the Pancreas: Differential Diagnosis and Radiology Correlation. Front Oncol. 2022; 12:860740.
Funding
This work was supported in part by the National Science Foundation for Scientists of China (Grant Nos. 81871352, 82171915, 82171930, U1809205, 62171230, 92159301, 62101365 and 91959207), The Natural Science Foundation of Shanghai Science and Technology Innovation Action Plan (Grant Nos. 21ZR1478500, 21Y11910300), Clinical Research Plan of SHDC (SHDC2020CR4073), and 234 Platform Discipline Consolidation Foundation Project (Grant Nos. 2019YPT001, 2020YPT001).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, Q., Zhou, Z., Chen, Y. et al. Fully automated magnetic resonance imaging-based radiomics analysis for differentiating pancreatic adenosquamous carcinoma from pancreatic ductal adenocarcinoma. Abdom Radiol 48, 2074–2084 (2023). https://doi.org/10.1007/s00261-023-03801-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00261-023-03801-8