Skip to main content

Thank you for visiting nature.com. 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.

Artificial intelligence in cancer research, diagnosis and therapy

Standfirst

Artificial intelligence and machine learning techniques are breaking into biomedical research and health care, which importantly includes cancer research and oncology, where the potential applications are vast. These include detection and diagnosis of cancer, subtype classification, optimization of cancer treatment and identification of new therapeutic targets in drug discovery. While big data used to train machine learning models may already exist, leveraging this opportunity to realize the full promise of artificial intelligence in both the cancer research space and the clinical space will first require significant obstacles to be surmounted. In this Viewpoint article, we asked four experts for their opinions on how we can begin to implement artificial intelligence while ensuring standards are maintained so as transform cancer diagnosis and the prognosis and treatment of patients with cancer and to drive biological discovery.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

References

  1. 1.

    Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017).

    CAS  Article  Google Scholar 

  2. 2.

    Kooi, T. et al. Large scale deep learning for computer aided detection of mammographic lesions. Med. Image Anal. 35, 303–312 (2017).

    Article  Google Scholar 

  3. 3.

    Pantanowitz, L. et al. An artificial intelligence algorithm for prostate cancer diagnosis in whole slide images of core needle biopsies: a blinded clinical validation and deployment study. Lancet Digit. Health 2, e407–e416 (2020).

    Article  Google Scholar 

  4. 4.

    Wang, P. et al. Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nat. Biomed. Eng. 2, 741–748 (2018).

    Article  Google Scholar 

  5. 5.

    Banchereau, R. et al. Molecular determinants of response to PD-L1 blockade across tumor types. Nat. Commun. 12, 3969 (2021).

    CAS  Article  Google Scholar 

  6. 6.

    Gomez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4, 268–276 (2018).

    CAS  Article  Google Scholar 

  7. 7.

    Madhukar, N. S. et al. A Bayesian machine learning approach for drug target identification using diverse data types. Nat. Commun. 10, 5221 (2019).

    Article  Google Scholar 

  8. 8.

    Gayvert, K. M. et al. A computational approach for identifying synergistic drug combinations. PLoS Comput. Biol. 13, e1005308 (2017).

    Article  Google Scholar 

  9. 9.

    Senior, A. W. et al. Improved protein structure prediction using potentials from deep learning. Nature. 577, 706–710 (2020).

    CAS  Article  Google Scholar 

  10. 10.

    Schreiber, J., Durham, T., Bilmes, J. & Noble, W. S. Avocado: a multi-scale deep tensor factorization method learns a latent representation of the human epigenome. Genome Biol. 21, 81 (2020).

    Article  Google Scholar 

  11. 11.

    Gonzalez, A. J., Setty, M. & Leslie, C. S. Early enhancer establishment and regulatory locus complexity shape transcriptional programs in hematopoietic differentiation. Nat. Genet. 47, 1249–1259 (2015).

    CAS  Article  Google Scholar 

  12. 12.

    Pritykin, Y. et al. A unified atlas of CD8 T cell dysfunctional states in cancer and infection. Mol. Cell 81, 2477–93 e10 (2021).

    CAS  Article  Google Scholar 

  13. 13.

    Avsec, Z. et al. Base-resolution models of transcription-factor binding reveal soft motif syntax. Nat. Genet. 53, 354–366 (2021).

    CAS  Article  Google Scholar 

  14. 14.

    Fudenberg, G., Kelley, D. R. & Pollard, K. S. Predicting 3D genome folding from DNA sequence with Akita. Nat. Methods 17, 1111–1117 (2020).

    Article  Google Scholar 

  15. 15.

    Karbalayghareh, A., Sahin, M. & Leslie, C. S. Chromatin interaction aware gene regulatory modeling with graph attention networks. Preprint at bioRxiv https://doi.org/10.1101/2021.03.31.437978 (2021).

    Article  Google Scholar 

  16. 16.

    Lopez, R., Regier, J., Cole, M. B., Jordan, M. I. & Yosef, N. Deep generative modeling for single-cell transcriptomics. Nat. Methods 15, 1053–1058 (2018).

    CAS  Article  Google Scholar 

  17. 17.

    Kimmel, J. C. & Kelley, D. R. Semi-supervised adversarial neural networks for single-cell classification. Genome Res. 31, 677–688 (2021).

    Article  Google Scholar 

  18. 18.

    Holmström, O. et al. Point-of-care digital cytology with artificial intelligence for cervical cancer screening in a resource-limited setting. JAMA Netw. Open 4, e211740 (2021).

    Article  Google Scholar 

  19. 19.

    Steiner, D. F. et al. Impact of deep learning assistance on the histopathologic review of lymph nodes for metastatic breast cancer. Am. J. Surg. Pathol. 42, 1636–1646 (2018).

    Article  Google Scholar 

  20. 20.

    Mobadersany, P. et al. Predicting cancer outcomes from histology and genomics using convolutional networks. Proc. Natl Acad. Sci. USA 115, E2970–E2979 (2018).

    CAS  Article  Google Scholar 

  21. 21.

    Bychkov, D. et al. Deep learning based tissue analysis predicts outcome in colorectal cancer. Sci. Rep. 8, 3395 (2018).

    Article  Google Scholar 

  22. 22.

    Silver, D. et al. Mastering the game of Go without human knowledge. Nature 550, 354 (2017).

    CAS  Article  Google Scholar 

  23. 23.

    Bychkov, D. et al. Deep learning identifies morphological features in breast cancer predictive of cancer ERBB2 status and trastuzumab treatment efficacy. Sci. Rep. 11, 4037 (2021).

    CAS  Article  Google Scholar 

  24. 24.

    Sharpless, N. E. & Kerlavage, A. R. The potential of AI in cancer care and research. Biochim. Biophys. Acta Rev. Cancer 1876, 188573 (2021).

    CAS  Article  Google Scholar 

  25. 25.

    Hendrycks, D., et al. (eds) Natural adversarial examples. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 15262–15271 (IEEE, 2021).

  26. 26.

    Lundberg, S. M. and Lee, S. I. A unified approach to interpreting model predictions.in Proceedings of the 31st International Conference on Neural Information Processing Systems; Long Beach 4768–4777 (Curran Associates Inc., 2017)

  27. 27.

    Holmström, O. et al. Detection of breast cancer lymph node metastases in frozen sections with a point-of-care low-cost microscope scanner. PLoS ONE 14, e0208366 (2019).

    Article  Google Scholar 

  28. 28.

    Begoli, E., Bhattacharya, T. & Kusnezov, D. The need for uncertainty quantification in machine-assisted medical decision making. Nat. Mach. Intell. 1, 20–23 (2019).

    Article  Google Scholar 

  29. 29.

    Adadi, A. and Berrada M. Explainable AI for healthcare: from black box to interpretable models. in Embedded Systems and Artificial Intelligence. 327–337 (Springer, 2020).

  30. 30.

    Silver, D. et al. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science. 362, 1140 (2018).

    CAS  Article  Google Scholar 

  31. 31.

    Burke H. B. and Grizzle W. E. Clinical validation of molecular biomarkers in translational medicine.in Biomarkers in Cancer Screening and Early Detection. 256–266 (Wiley, 2017).

  32. 32.

    Liu, X. et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit. Health 1, e271–e297 (2019).

    Article  Google Scholar 

  33. 33.

    McDermott, M. B. A. et al. Reproducibility in machine learning for health research: Still a ways to go. Sci. Transl. Med. 13, 586 (2021).

    Article  Google Scholar 

  34. 34.

    Goodman, S. N., Fanelli, D. & Ioannidis, J. P. A. What does research reproducibility mean? Sci. Transl. Med. 8, 341ps12–341ps12 (2016).

    Article  Google Scholar 

  35. 35.

    Parisi, G. I. et al. Continual lifelong learning with neural networks: a review. Neural Netw. 113, 54–71 (2019).

    Article  Google Scholar 

  36. 36.

    Xie, Z. et al. Artificial neural variability for deep learning: on overfitting, noise memorization, and catastrophic forgetting. Neural Comput. 33, 2163–2192 (2021).

    Article  Google Scholar 

  37. 37.

    Yala, A., Lehman, C., Schuster, T., Portnoi, T. & Barzilay, R. A deep learning mammography-based model for improved breast cancer risk prediction. Radiology 292, 60–66 (2019).

    Article  Google Scholar 

  38. 38.

    Rieke, N. et al. The future of digital health with federated learning. NPJ Digit. Med. 3, 119 (2020).

    Article  Google Scholar 

  39. 39.

    Rozman, D. Overview: data generation techniques: from omics to personalized approaches and clinical care. Syst. Med. https://doi.org/10.1016/B978-0-12-801238-3.11708-8 (2021).

    Article  Google Scholar 

  40. 40.

    Bhattacharya, T. et al. AI meets exascale computing: advancing cancer research with large-scale high performance computing. Front. Oncol. 9, 984 (2019).

    Article  Google Scholar 

Download references

Acknowledgements

C.L. acknowledges A. Kundaje, W. S. Noble, Q. Morris and T. Norman for helpful comments on the text. J.L. warmly thanks H. B. Burke and N. Linder for constructive comments on and valuable input to the text. J.L. also thanks research collaborators and group members at the Institute for Molecular Medicine Finland (FIMM), University of Helsinki, Finland, the Department of Global Public Health, Karolinska Institutet, Sweden, the Kinondo Kwetu Health Center, Kenya, the Muhimbili University of Health and Allied Sciences, Tanzania, and Aiforia Technologies Oy, Helsinki, who all contributed to the cited studies on applied artificial intelligence. J.L. acknowledges funding from the Erling-Persson Family Foundation, the Swedish Research Council, the Sigrid Jusélius Foundation, Finska Läkaresällskapet, Medicinska Understödsföreningen Liv och Hälsa and the iCAN Digital Precision Cancer Medicine Flagship project. This article was authored in part by UT-Battelle LLC under contract no. DE-AC05-00OR22725 with the US Department of Energy. The US Government retains and the publisher, by accepting the article for publication, acknowledges that the US Government retains a non-exclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this article, or allow others to do so, for US Government purposes.

Author information

Affiliations

Authors

Contributions

Olivier Elemento

Olivier Elemento is a professor of physiology and biophysics at Weill Cornell Medicine (WCM) and Cornell University. Since 2017, he has been Director of the Caryl and Israel Englander Institute for Precision Medicine, a multidisciplinary institute that draws on more than 100 faculty members from nearly all basic and clinical departments at Cornell University. Its mission is to use genomics, artificial intelligence (AI) and other technologies to develop and bring highly personalized medicine to patients at WCM’s affiliated hospital, NewYork-Presbyterian Hospital (NYPH), and elsewhere. The institute also fosters patient-centred basic and clinical research in the areas of genomics, systems biology, AI and data science. Olivier Elemento is funded by numerous NIH grants, foundation grants, NIH contracts and industry alliances. He has published more than 320 articles in the areas of precision medicine, genomics, computational biology, AI, systems biology and drug discovery. He has led the development of novel clinical genomics assays, including whole-exome sequencing offered to patients at WCM and NYPH, and is currently leading a large multidisease effort to bring whole-genome sequencing into clinical practice at WCM and NYPH. He co-founded two venture capital-funded companies: Volastra Therapeutics (with Lew Cantley and Sam Bakhoum) and OneThree Biotech (with Neel Madhukar). He serves on the scientific advisory boards of Volastra, OneThree Biotech, Owkin, Freenome and several other companies.

Christina Leslie

Christina Leslie is a member of the Computational and Systems Biology Program of the Sloan Kettering Institute at Memorial Sloan Kettering Cancer Center and a Professor of Physiology, Biophysics and Systems Biology in the Graduate School of Medical Sciences at WCM. She has pioneered machine learning methods for understanding the genomics of gene regulation, with applications to basic and cancer immunology, cancer biology and development.

Johan Lundin

Johan Lundin is a professor of medical technology at Karolinska Institutet, Stockholm, Sweden, and a research director and group leader at the Institute for Molecular Medicine Finland (FIMM), University of Helsinki, Finland. His overall research aims are to study the use of digital technologies and AI for improvement of diagnostics and care of the individual patient. In addition to research, he has together with his co-workers developed technologies for diagnostic decision support; for example, cloud-based and mobile solutions that allow the diagnostic process to be performed using AI-supported analysis in both high-resource and low-resource settings. He is also co-founder of Aiforia Technologies, a spin-off company of FIMM developing medical image-based AI.

Georgia Tourassi

Georgia Tourassi is Director of the National Center for Computational Sciences and the Oak Ridge Leadership Computing Facility at Oak Ridge National Laboratory. Concurrently, she holds appointments as an adjunct professor of radiology at Duke University and the University of Tennessee at Knoxville. Her research interests include high-performance computing and AI in biomedicine.

Corresponding authors

Correspondence to Olivier Elemento, Christina Leslie, Johan Lundin or Georgia Tourassi.

Ethics declarations

Competing interests

O.E. is supported by Janssen, Johnson & Johnson, AstraZeneca, Volastra and Eli Lilly research grants. He is a scientific advisor to and equity holder in Freenome, Owkin, Volastra Therapeutics and OneThree Biotech and is a paid scientific advisor to Champions Oncology. J.L. is a co-founder, shareholder and member of the Board of Directors of and receives consultation fees from Aiforia Technologies Oy. J.L. is also a founding member and an unpaid member of the Board of Advisors of the European Society of Digital and Integrative Pathology. C.L. and G.T. declare no competing interests.

Additional information

Publisher’s note

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

Related links

Kipoi: https://kipoi.org

Englander Institute for Precision Medicine: https://eipm.weill.cornell.edu/

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Elemento, O., Leslie, C., Lundin, J. et al. Artificial intelligence in cancer research, diagnosis and therapy. Nat Rev Cancer (2021). https://doi.org/10.1038/s41568-021-00399-1

Download citation

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing