Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Translational Therapeutics

Radiogenomics for predicting p53 status, PD-L1 expression, and prognosis with machine learning in pancreatic cancer



Radiogenomics is an emerging field that integrates “Radiomics” and “Genomics”. In the current study, we aimed to predict the genetic information of pancreatic tumours in a simple, inexpensive, and non-invasive manner, using cancer imaging analysis and radiogenomics. We focused on p53 mutations, which are highly implicated in pancreatic ductal adenocarcinoma (PDAC), and PD-L1, a biomarker for immune checkpoint inhibitor-based therapies.


Overall, 107 patients diagnosed with PDAC were retrospectively examined. The relationship between p53 mutations as well as PD-L1 abnormal expression and clinicopathological factors was investigated using immunohistochemistry. Imaging features (IFs) were extracted from CT scans and were used to create prediction models of p53 and PD-L1 status.


We found that p53 and PD-L1 are significant independent prognostic factors (P = 0.008, 0.013, respectively). The area under the curve for p53 and PD-L1 predictive models was 0.795 and 0.683, respectively. Radiogenomics-predicted p53 mutations were significantly associated with poor prognosis (P = 0.015), whereas the predicted abnormal expression of PD-L1 was not significant (P = 0.096).


Radiogenomics could predict p53 mutations and in turn the prognosis of PDAC patients. Hence, prediction of genetic information using radiogenomic analysis may aid in the development of precision medicine.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Immunohistochemistry of p53 and PD-L1 in PDAC.
Fig. 2: Machine learning processing was summarised.
Fig. 3: Kaplan-Meier plots of p53 and PD-L1 status by IHC compared with status by machine-learning, and ROC curve.


  1. 1.

    Spath, C., Nitsche, U., Muller, T., Michalski, C., Erkan, M., Kong, B. et al. Strategies to improve the outcome in locally advanced pancreatic cancer. Minerva Chir. 70, 97–106 (2015).

    CAS  PubMed  Google Scholar 

  2. 2.

    Waddell, N., Pajic, M., Patch, A. M., Chang, D. K., Kassahn, K. S., Bailey, P. et al. Whole genomes redefine the mutational landscape of pancreatic cancer. Nature 518, 495–501 (2015).

    CAS  PubMed  PubMed Central  Google Scholar 

  3. 3.

    Kamisawa, T., Wood, L. D., Itoi, T. & Takaori, K. Pancreatic cancer. Lancet (Lond., Engl.) 388, 73–85 (2016).

    CAS  Google Scholar 

  4. 4.

    Oshima, M., Okano, K., Muraki, S., Haba, R., Maeba, T., Suzuki, Y. et al. Immunohistochemically detected expression of 3 major genes (CDKN2A/p16, TP53, and SMAD4/DPC4) strongly predicts survival in patients with resectable pancreatic cancer. Ann. Surg. 258, 336–346 (2013).

    PubMed  Google Scholar 

  5. 5.

    Reck, M., Rodriguez-Abreu, D., Robinson, A. G., Hui, R., Csoszi, T., Fulop, A. et al. Pembrolizumab versus chemotherapy for PD-L1-positive non-small-cell lung cancer. N. Engl. J. Med. 375, 1823–1833 (2016).

    CAS  Google Scholar 

  6. 6.

    Gao, H. L., Liu, L., Qi, Z. H., Xu, H. X., Wang, W. Q., Wu, C. T. et al. The clinicopathological and prognostic significance of PD-L1 expression in pancreatic cancer: a meta-analysis. Hepatobiliary Pancreat. Dis. Int. 17, 95–100 (2018).

    PubMed  Google Scholar 

  7. 7.

    Brahmer, J., Reckamp, K. L., Baas, P., Crino, L., Eberhardt, W. E., Poddubskaya, E. et al. Nivolumab versus docetaxel in advanced squamous-cell non-small-cell lung cancer. N. Engl. J. Med. 373, 123–135 (2015).

    CAS  PubMed  PubMed Central  Google Scholar 

  8. 8.

    Borghaei, H., Paz-Ares, L., Horn, L., Spigel, D. R., Steins, M., Ready, N. E. et al. Nivolumab versus docetaxel in advanced nonsquamous non-small-cell lung cancer. N. Engl. J. Med. 373, 1627–1639 (2015).

    CAS  PubMed  PubMed Central  Google Scholar 

  9. 9.

    Herskind, C., Talbot, C. J., Kerns, S. L., Veldwijk, M. R., Rosenstein, B. S. & West, C. M. Radiogenomics: a systems biology approach to understanding genetic risk factors for radiotherapy toxicity? Cancer Lett. 382, 95–109 (2016).

    CAS  PubMed  PubMed Central  Google Scholar 

  10. 10.

    Woodard, G. A., Ray, K. M., Joe, B. N. & Price, E. R. Qualitative radiogenomics: association between oncotype DX Test recurrence score and BI-RADS mammographic and breast MR imaging features. Radiology 286, 60–70 (2018).

    PubMed  Google Scholar 

  11. 11.

    Zhou, M., Leung, A., Echegaray, S., Gentles, A., Shrager, J. B., Jensen, K. C. et al. Non-small cell lung cancer radiogenomics map identifies relationships between molecular and imaging phenotypes with prognostic implications. Radiology 286, 307–315 (2018).

    PubMed  Google Scholar 

  12. 12.

    Kickingereder, P., Bonekamp, D., Nowosielski, M., Kratz, A., Sill, M., Burth, S. et al. Radiogenomics of glioblastoma: machine learning-based classification of molecular characteristics by using multiparametric and multiregional MR imaging features. Radiology 281, 907–918 (2016).

    PubMed  Google Scholar 

  13. 13.

    Eilaghi, A., Baig, S., Zhang, Y., Zhang, J., Karanicolas, P., Gallinger, S. et al. CT texture features are associated with overall survival in pancreatic ductal adenocarcinoma—a quantitative analysis. BMC Med. Imaging 17, 38 (2017).

    PubMed  PubMed Central  Google Scholar 

  14. 14.

    Sun, R., Limkin, E. J., Vakalopoulou, M., Dercle, L., Champiat, S., Han, S. R. et al. A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study. Lancet Oncol. 19, 1180–1191 (2018).

    CAS  PubMed  Google Scholar 

  15. 15.

    Attiyeh, M. A., Chakraborty, J., McIntyre, C. A., Kappagantula, R., Chou, Y., Askan, G. et al. CT radiomics associations with genotype and stromal content in pancreatic ductal adenocarcinoma. Abdom. Radiol. 44, 3148–3157 (2019).

    Google Scholar 

  16. 16.

    Attiyeh, M. A., Chakraborty, J., Doussot, A., Langdon-Embry, L., Mainarich, S., Gonen, M. et al. Survival prediction in pancreatic ductal adenocarcinoma by quantitative computed tomography image analysis. Ann. surgical Oncol. 25, 1034–1042 (2018).

    Google Scholar 

  17. 17.

    Kobel, M., Ronnett, B. M., Singh, N., Soslow, R. A., Gilks, C. B. & McCluggage, W. G. Interpretation of P53 immunohistochemistry in endometrial carcinomas: toward increased reproducibility. Int. J. Gynecol. Pathol. 38, S123–S131 (2019).

    PubMed  Google Scholar 

  18. 18.

    van Griethuysen, J. J. M., Fedorov, A., Parmar, C., Hosny, A., Aucoin, N., Narayan, V. et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77, e104–e107 (2017).

    PubMed  PubMed Central  Google Scholar 

  19. 19.

    Feldser, D. M., Kostova, K. K., Winslow, M. M., Taylor, S. E., Cashman, C., Whittaker, C. A. et al. Stage-specific sensitivity to p53 restoration during lung cancer progression. Nature 468, 572–575 (2010).

    CAS  PubMed  PubMed Central  Google Scholar 

  20. 20.

    Furukawa, H., Makino, T., Yamasaki, M., Tanaka, K., Miyazaki, Y., Takahashi, T. et al. PRIMA-1 induces p53-mediated apoptosis by upregulating Noxa in esophageal squamous cell carcinoma with TP53 missense mutation. Cancer Sci. 109, 412–421 (2018).

    CAS  PubMed  Google Scholar 

  21. 21.

    Saha, M. N., Jiang, H., Yang, Y., Reece, D. & Chang, H. PRIMA-1Met/APR-246 displays high antitumor activity in multiple myeloma by induction of p73 and Noxa. Mol. Cancer Ther. 12, 2331–2341 (2013).

    CAS  PubMed  Google Scholar 

  22. 22.

    Zandi, R., Selivanova, G., Christensen, C. L., Gerds, T. A., Willumsen, B. M. & Poulsen, H. S. PRIMA-1Met/APR-246 induces apoptosis and tumor growth delay in small cell lung cancer expressing mutant p53. Clin. Cancer Res. 17, 2830–2841 (2011).

    CAS  PubMed  Google Scholar 

  23. 23.

    Liang, Y., Besch-Williford, C. & Hyder, S. M. PRIMA-1 inhibits growth of breast cancer cells by re-activating mutant p53 protein. Int. J. Oncol. 35, 1015–1023 (2009).

    CAS  PubMed  Google Scholar 

  24. 24.

    Li, X. L., Zhou, J., Chan, Z. L., Chooi, J. Y., Chen, Z. R. & Chng, W. J. PRIMA-1met (APR-246) inhibits growth of colorectal cancer cells with different p53 status through distinct mechanisms. Oncotarget 6, 36689–36699 (2015).

    PubMed  PubMed Central  Google Scholar 

  25. 25.

    Thiem, A., Hesbacher, S., Kneitz, H., di Primio, T., Heppt, M. V., Hermanns, H. M. et al. IFN-gamma-induced PD-L1 expression in melanoma depends on p53 expression. J. Exp. Clin. Cancer Res. 38, 397 (2019).

    PubMed  PubMed Central  Google Scholar 

  26. 26.

    Schlitter, A. M., Segler, A., Steiger, K., Michalski, C. W., Jager, C., Konukiewitz, B. et al. Molecular, morphological and survival analysis of 177 resected pancreatic ductal adenocarcinomas (PDACs): identification of prognostic subtypes. Sci. Rep. 7, 41064 (2017).

    CAS  PubMed  PubMed Central  Google Scholar 

  27. 27.

    Vennin, C., Melenec, P., Rouet, R., Nobis, M., Cazet, A. S., Murphy, K. J. et al. CAF hierarchy driven by pancreatic cancer cell p53-status creates a pro-metastatic and chemoresistant environment via perlecan. Nat. Commun. 10, 3637 (2019).

    PubMed  PubMed Central  Google Scholar 

  28. 28.

    Muller, P. A. & Vousden, K. H. Mutant p53 in cancer: new functions and therapeutic opportunities. Cancer Cell 25, 304–317 (2014).

    CAS  PubMed  PubMed Central  Google Scholar 

  29. 29.

    Murnyak, B. & Hortobagyi, T. Immunohistochemical correlates of TP53 somatic mutations in cancer. Oncotarget 7, 64910–64920 (2016).

    PubMed  PubMed Central  Google Scholar 

  30. 30.

    Kaserer, K., Schmaus, J., Bethge, U., Migschitz, B., Fasching, S., Walch, A. et al. Staining patterns of p53 immunohistochemistry and their biological significance in colorectal cancer. J. Pathol. 190, 450–456 (2000).

    CAS  PubMed  Google Scholar 

  31. 31.

    Yemelyanova, A., Vang, R., Kshirsagar, M., Lu, D., Marks, M. A., Shih, Ie. M. et al. Immunohistochemical staining patterns of p53 can serve as a surrogate marker for TP53 mutations in ovarian carcinoma: an immunohistochemical and nucleotide sequencing analysis. Mod. Pathol. 24, 1248–1253 (2011).

    CAS  PubMed  Google Scholar 

  32. 32.

    Hodgson, A., Xu, B. & Downes, M. R. p53 immunohistochemistry in high-grade urothelial carcinoma of the bladder is prognostically significant. Histopathology 71, 296–304 (2017).

    PubMed  Google Scholar 

  33. 33.

    Alsner, J., Jensen, V., Kyndi, M., Offersen, B. V., Vu, P., Borresen-Dale, A. L. et al. A comparison between p53 accumulation determined by immunohistochemistry and TP53 mutations as prognostic variables in tumours from breast cancer patients. Acta Oncol. 47, 600–607 (2008).

    CAS  PubMed  Google Scholar 

  34. 34.

    Herbst, R. S., Soria, J. C., Kowanetz, M., Fine, G. D., Hamid, O., Gordon, M. S. et al. Predictive correlates of response to the anti-PD-L1 antibody MPDL3280A in cancer patients. Nature 515, 563–567 (2014).

    CAS  PubMed  PubMed Central  Google Scholar 

  35. 35.

    Teng, M. W., Ngiow, S. F., Ribas, A. & Smyth, M. J. Classifying Cancers Based on T-cell Infiltration and PD-L1. Cancer Res. 75, 2139–2145 (2015).

    CAS  PubMed  PubMed Central  Google Scholar 

  36. 36.

    Le, D. T., Durham, J. N., Smith, K. N., Wang, H., Bartlett, B. R., Aulakh, L. K. et al. Mismatch repair deficiency predicts response of solid tumors to PD-1 blockade. Science 357, 409–413 (2017).

    CAS  PubMed  PubMed Central  Google Scholar 

  37. 37.

    Hectors, S. J., Wagner, M., Bane, O., Besa, C., Lewis, S., Remark, R. et al. Quantification of hepatocellular carcinoma heterogeneity with multiparametric magnetic resonance imaging. Sci. Rep. 7, 2452 (2017).

    PubMed  PubMed Central  Google Scholar 

  38. 38.

    Taguchi, N., Oda, S., Yokota, Y., Yamamura, S., Imuta, M., Tsuchigame, T. et al. CT texture analysis for the prediction of KRAS mutation status in colorectal cancer via a machine learning approach. Eur. J. Radiol. 118, 38–43 (2019).

    PubMed  Google Scholar 

  39. 39.

    Hoshino, I., Yokota, H., Ishige, F., Iwatate, Y., Takeshita, N., Nagase, H. et al. Radiogenomics predicts the expression of microRNA-1246 in the serum of esophageal cancer patients. Sci. Rep. 10, 2532 (2020).

    CAS  PubMed  PubMed Central  Google Scholar 

  40. 40.

    Hutchings, D., Waters, K. M., Weiss, M. J., Wolfgang, C. L., Makary, M. A., He, J. et al. Cancerization of the pancreatic ducts: demonstration of a common and under-recognized process using immunolabeling of paired duct lesions and invasive pancreatic ductal adenocarcinoma for p53 and Smad4 expression. Am. J. surgical Pathol. 42, 1556–1561 (2018).

    Google Scholar 

  41. 41.

    Snyder, A., Makarov, V., Merghoub, T., Yuan, J., Zaretsky, J. M., Desrichard, A. et al. Genetic basis for clinical response to CTLA-4 blockade in melanoma. N. Engl. J. Med. 371, 2189–2199 (2014).

    PubMed  PubMed Central  Google Scholar 

  42. 42.

    Chen, D. S. & Mellman, I. Oncology meets immunology: the cancer-immunity cycle. Immunity 39, 1–10 (2013).

    PubMed  PubMed Central  Google Scholar 

  43. 43.

    Lane, D. P. Cancer. p53, guardian of the genome. Nature 358, 15–16 (1992).

    CAS  Google Scholar 

Download references

Author information




Y.I. and I.H. analysed and interpreted patient data. Y.I. was a major contributor to the writing of the paper. F.I., S.C., H.A., H.Yanagibashi., H.N., and W.T. performed the CT scans in PDAC patients and registered the images. H.Yokota and Y.M. extracted the imaging features from CT scans and analysed the relationship between imaging features and clinicopathological features. M.I. performed the pathological examination of pancreatic cancer samples and interpreted IHC results. All authors read and approved the final paper.

Corresponding author

Correspondence to Isamu Hoshino.

Ethics declarations

Ethics approval and consent to participate

This study was approved by the Chiba Cancer Center Review Board (H29-006). All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation and with the Helsinki Declaration of 1964 and its later amendments. Informed consent was obtained from all patients in this study.

Consent to publish

Written informed consent was obtained from the patients for publication of this study and accompanying clinicopathological data.

Data availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Competing interests

The authors declare no competing interests.

Funding information

Funding information is not applicable.

Additional information

Note This work is published under the standard license to publish agreement. After 12 months the work will become freely available and the license terms will switch to a Creative Commons Attribution 4.0 International (CC BY 4.0).

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Iwatate, Y., Hoshino, I., Yokota, H. et al. Radiogenomics for predicting p53 status, PD-L1 expression, and prognosis with machine learning in pancreatic cancer. Br J Cancer 123, 1253–1261 (2020).

Download citation

Further reading


Quick links