Prediction of Tumor-Infiltrating CD20+ B-Cells in Patients with Pancreatic Ductal Adenocarcinoma Using a Multilayer Perceptron Network Classifier Based on Non-contrast MRI

Published:December 16, 2021DOI:

      Rationale and Objectives

      Conventional chemotherapy has limited benefit in pancreatic ductal adenocarcinoma (PDAC), necessitating identification of novel therapeutic targets. Radiomics may enable non-invasive prediction of CD20 expression, a hypothesized therapeutic target in PDAC. To develop a machine learning classifier based on noncontrast magnetic resonance imaging for predicting CD20 expression in PDAC.

      Materials and Methods

      Retrospective study was conducted on preoperative noncontrast magnetic resonance imaging of 156 patients with pathologically confirmed PDAC from January 2017 to April 2018. For each patient, 1409 radiomics features were selected using minimum absolute contraction and selective operator logistic regression algorithms. CD20 expression was quantified using immunohistochemistry. A multilayer perceptron network classifier was developed using the training and validation set.


      A log-rank test showed that the CD20-high group (22.37 months, 95% CI: 19.10–25.65) had significantly longer survival than the CD20-low group (14.9 months, 95% CI: 10.96–18.84). The predictive model showed good differentiation in training (area under the curve [AUC], 0.79) and validation (AUC, 0.79) sets. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 73.21%, 75.47%, 0.74, 0.76, and 0.73, respectively, for the training set and 69.23%, 80.95%, 0.74, 0.82, and 0.68, respectively, for the validation set.


      Multilayer perceptron classifier based on noncontrast magnetic resonance imaging scanning can predict the level of CD20 expression in PDAC patients.

      Key Words


      PDAC (pancreatic ductal adenocarcinoma), TIL (tumor-infiltrating lymphocyte), OS (overall survival), US-FNA (ultrasound-guided fine-needle aspiration), CT (computed tomography), MRI (magnetic resonance imaging), TR (repetition time), TE (echo time), FOV (field of view), ROI (region of interest), ICC (intraclass correlation coefficient), MLP (multilayer perceptron), AUC (area under the curve), DCA (decision curve analysis), CI (confidence interval), T1WI (T1-weighted imaging), T2WI (T2-weighted imaging)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Mutgan AC
        • Besikcioglu HE
        • Wang S
        • et al.
        Insulin/IGF-driven cancer cell-stroma crosstalk as a novel therapeutic target in pancreatic cancer.
        Mol Cancer. 2018; 17: 66
        • Rahib L
        • Smith BD
        • Aizenberg R
        • et al.
        Projecting cancer incidence and deaths to 2030: the unexpected burden of thyroid, liver, and pancreas cancers in the United States.
        Cancer Res. 2014; 74: 2913-2921
        • Dhir M
        • Malhotra GK
        • Sohal DPS
        • et al.
        Neoadjuvant treatment of pancreatic adenocarcinoma: a systematic review and meta-analysis of 5520 patients.
        World J Surg Oncol. 2017; 15: 183
        • Melzer MK
        • Arnold F
        • Stifter K
        • et al.
        An immunological glance on pancreatic ductal adenocarcinoma.
        Int J Mol Sci. 2020; 21: 3345
        • Wei ZW
        • Wu J
        • Huang WB
        • et al.
        Immune-infiltration based signature as a novel prognostic biomarker in gastrointestinal stromal tumour.
        EBioMedicine. 2020; 57102850
        • Miksch RC
        • Schoenberg MB
        • Weniger M
        • et al.
        Prognostic impact of tumor-infiltrating lymphocytes and neutrophils on survival of patients with upfront resection of pancreatic cancer.
        Cancers (Basel). 2019; 11: 39
        • Anitei MG
        • Zeitoun G
        • Mlecnik B
        • et al.
        Prognostic and predictive values of the immunoscore in patients with rectal cancer.
        Clin Cancer Res. 2014; 20: 1891-1899
        • Donnem T
        • Kilvaer TK
        • Andersen S
        • et al.
        Strategies for clinical implementation of TNM-Immunoscore in resected nonsmall-cell lung cancer.
        Ann Oncol. 2016; 27: 225-232
        • Romagnoli G
        • Wiedermann M
        • Hübner F
        • et al.
        Morphological evaluation of Tumor-Infiltrating Lymphocytes (TILs) to investigate invasive breast cancer immunogenicity, reveal lymphocytic networks and help relapse prediction: a retrospective study.
        Int J Mol Sci. 2017; 18: 1936
        • Curigliano G
        • Perez EA.
        Immunoscoring breast cancer: TILs remember what they target.
        Ann Oncol. 2014; 25: 1455-1456
        • Germain C
        • Gnjatic S
        • Dieu-Nosjean MC.
        Tertiary lymphoid structure-associated B cells are key players in anti-tumor immunity.
        Front Immunol. 2015; 6: 67
        • Guo FF
        • Cui JW.
        The role of tumor-infiltrating B cells in tumor immunity.
        J Oncol. 2019; 20192592419
        • Cabrita R
        • Lauss M
        • Sanna A
        • et al.
        Tertiary lymphoid structures improve immunotherapy and survival in melanoma.
        Nature. 2020; 577: 561-565
        • Mahmoud SM
        • Lee AH
        • Paish EC
        • et al.
        The prognostic significance of B lymphocytes in invasive carcinoma of the breast.
        Breast Cancer Res Treat. 2012; 132: 545-553
        • Al-Shibli KI
        • Donnem T
        • Al-Saad S
        • et al.
        Prognostic effect of epithelial and stromal lymphocyte infiltration in non-small cell lung cancer.
        Clin Cancer Res. 2008; 14: 5220-5227
        • Milne K
        • Köbel M
        • Kalloger SE
        • et al.
        Systematic analysis of immune infiltrates in high-grade serous ovarian cancer reveals CD20, FoxP3 and TIA-1 as positive prognostic factors.
        PLoS One. 2009; 4: e6412
        • 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: 628-640
        • 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: 2286-2293
        • Aerts HJ
        • Velazquez ER
        • Leijenaar RT
        • et al.
        Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.
        Nat Commun. 2014; 5: 4006
        • Liao H
        • Zhang Z
        • Chen J
        • et al.
        Preoperative radiomic approach to evaluate tumor-infiltrating CD8(+) T Cells in hepatocellular carcinoma patients using contrast-enhanced computed tomography.
        Ann Surg Oncol. 2019; 26: 4537-4547
        • Li J
        • Shi Z
        • Liu F
        • et al.
        XGBoost classifier based on computed tomography radiomics for prediction of tumor-infiltrating CD8(+) T-Cells in patients with pancreatic ductal adenocarcinoma.
        Front Oncol. 2021; 11671333
        • 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: W1-73
        • Watanabe H
        • Okada M
        • Kaji Y
        • et al.
        New response evaluation criteria in solid tumours-revised RECIST guideline (version 1.1).
        Gan To Kagaku Ryoho. 2009; 36: 2495-2501
        • van Griethuysen JJM
        • Fedorov A
        • Parmar C
        • et al.
        Computational radiomics system to decode the radiographic phenotype.
        Cancer Res. 2017; 77: e104-e1e7
        • Shrout PE
        • Fleiss JL.
        Intraclass correlations: uses in assessing rater reliability.
        Psychol Bull. 1979; 86: 420-428
        • Camp RL
        • Dolled-Filhart M
        • Rimm DL.
        X-tile: a new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization.
        Clin Cancer Res. 2004; 10: 7252-7259
        • Brunner M
        • Maier K
        • Rümmele P
        • et al.
        Upregulation of CD20 Positive B-Cells and B-Cell aggregates in the tumor infiltration zone is associated with better survival of patients with pancreatic ductal adenocarcinoma.
        Int J Mol Sci. 2020; 21: 1779
        • Tewari N
        • Zaitoun AM
        • Arora A
        • et al.
        The presence of tumour-associated lymphocytes confers a good prognosis in pancreatic ductal adenocarcinoma: an immunohistochemical study of tissue microarrays.
        BMC Cancer. 2013; 13: 436
        • Zettlitz KA
        • Tavaré R
        • Knowles SM
        • et al.
        ImmunoPET of malignant and normal B Cells with (89)Zr- and (124)I-Labeled obinutuzumab antibody fragments reveals differential CD20 internalization in vivo.
        Clin Cancer Res. 2017; 23: 7242-7252
        • Yoon JT
        • Longtine MS
        • Marquez-Nostra BV
        • et al.
        Evaluation of next-generation Anti-CD20 antibodies labeled with (89)Zr in human lymphoma xenografts.
        J Nucl Med. 2018; 59: 1219-1224
        • Jiang Y
        • Wang H
        • Wu J
        • et al.
        Noninvasive imaging evaluation of tumor immune microenvironment to predict outcomes in gastric cancer.
        Ann Oncol. 2020; 31: 760-768
        • Jiang Y
        • Chen C
        • Xie J
        • et al.
        Radiomics signature of computed tomography imaging for prediction of survival and chemotherapeutic benefits in gastric cancer.
        EBioMedicine. 2018; 36: 171-182
        • Eresen A
        • Yang J
        • Shangguan J
        • et al.
        Detection of immunotherapeutic response in a transgenic mouse model of pancreatic ductal adenocarcinoma using multiparametric MRI radiomics: a preliminary investigation.
        Acad Radiol. 2021; 28: e147-ee54
        • Horii M
        • Matsushita T.
        Regulatory B cells and T cell regulation in cancer.
        J Mol Biol. 2021; 433166685