+
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.

  • Perspective
  • Published:

Artificial intelligence in digital pathology — time for a reality check

Nature Reviews Clinical Oncology volume 22, pages 283–291 (2025)Cite this article

Subjects

Abstract

The past decade has seen the introduction of artificial intelligence (AI)-based approaches aimed at optimizing several workflows across many medical specialties. In clinical oncology, the most promising applications include those involving image analysis, such as digital pathology. In this Perspective, we provide a comprehensive examination of the developments in AI in digital pathology between 2019 and 2024. We evaluate the current landscape from the lens of technological innovations, regulatory trends, deployment and implementation, reimbursement and commercial implications. We assess the technological advances that have driven improvements in AI, enabling more robust and scalable solutions for digital pathology. We also examine regulatory developments, in particular those affecting in-house devices and laboratory-developed tests, which are shaping the landscape of AI-based tools in digital pathology. Finally, we discuss the role of reimbursement frameworks and commercial investment in the clinical adoption of AI-based technologies. In this Perspective, we highlight both the progress and challenges in AI-driven digital pathology over the past 5 years, outlining the path forward for its adoption into routine practice in clinical oncology.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: FDA approvals of artificial intelligence-based or machine learning-based devices across medical specialties.
Fig. 2: Proposed strategy for achieving higher levels of evidence in the validation of artificial intelligence-based or machine learning-based models for digital pathology applications.

Similar content being viewed by others

References

  1. Rajpurkar, P., Chen, E., Banerjee, O. & Topol, E. J. AI in health and medicine. Nat. Med. 28, 31–38 (2022).

    CAS  PubMed  Google Scholar 

  2. Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44–56 (2019).

    CAS  PubMed  Google Scholar 

  3. Aeffner, F. et al. Introduction to digital image analysis in whole-slide imaging: a white paper from the Digital Pathology Association. J. Pathol. Inform. 10, 9 (2019).

    PubMed  PubMed Central  Google Scholar 

  4. van der Laak, J., Litjens, G. & Ciompi, F. Deep learning in histopathology: the path to the clinic. Nat. Med. 27, 775–784 (2021).

    PubMed  Google Scholar 

  5. Shafi, S. & Parwani, A. V. Artificial intelligence in diagnostic pathology. Diagn. Pathol. 18, 109 (2023).

    PubMed  PubMed Central  Google Scholar 

  6. Baxi, V., Edwards, R., Montalto, M. & Saha, S. Digital pathology and artificial intelligence in translational medicine and clinical practice. Mod. Pathol. 35, 23–32 (2022).

    CAS  PubMed  Google Scholar 

  7. Bera, K., Schalper, K. A., Rimm, D. L., Velcheti, V. & Madabhushi, A. Artificial intelligence in digital pathology – new tools for diagnosis and precision oncology. Nat. Rev. Clin. Oncol. 16, 703–715 (2019).

    PubMed  PubMed Central  Google Scholar 

  8. O’Shea, K. & Nash, R. An introduction to convolutional neural networks. Preprint at arXiv https://doi.org/10.48550/arXiv.1511.08458 (2015).

  9. Coudray, N. et al. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nat. Med. 24, 1559–1567 (2018).

    CAS  PubMed  PubMed Central  Google Scholar 

  10. Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. Preprint at arXiv https://doi.org/10.48550/arXiv.2010.11929 (2020).

  11. Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850–862 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  12. Xu, H. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 630, 181–188 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  13. Vorontsov, E. A foundation model for clinical-grade computational pathology and rare cancers detection. Nat. Med. 30, 2924–2935 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  14. Dippel, J. et al. RudolfV: a foundation model by pathologists for pathologists. Preprint at arXiv https://doi.org/10.48550/arXiv.2401.04079 (2024).

  15. Wang, X. et al. A pathology foundation model for cancer diagnosis and prognosis prediction. Nature 634, 970–978 (2024).

    CAS  PubMed  Google Scholar 

  16. Ma, J. et al. Towards a generalizable pathology foundation model via unified knowledge distillation. Preprint at arXiv https://doi.org/10.48550/arXiv.2407.18449 (2024).

  17. Yang, Z. et al. A foundation model for generalizable cancer diagnosis and survival prediction from histopathological images. Preprint at bioRxiv https://doi.org/10.1101/2024.05.16.594499 (2024).

  18. Hua, S., Yan, F., Shen, T., Ma, L. & Zhang, X. PathoDuet: foundation models for pathological slide analysis of H&E and IHC stains. Med. Image Anal. 97, 103289 (2024).

    PubMed  Google Scholar 

  19. Nechaev, D., Pchelnikov, A. & Ivanova, E. Hibou: a family of foundational vision transformers for pathology. Preprint at arXiv https://doi.org/10.48550/arXiv.2406.05074 (2024).

  20. Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. 30, 863–874 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  21. Zimmermann, E. et al. Virchow2: scaling self-supervised mixed magnification models in pathology. Preprint at arXiv https://doi.org/10.48550/arXiv.2408.00738 (2024).

  22. Juyal, D. et al. PLUTO: pathology-universal transformer. Preprint at arXiv https://doi.org/10.48550/arXiv.2405.07905 (2024).

  23. Li, H. et al. A prognostic and predictive computational pathology immune signature for ductal carcinoma in situ: retrospective results from a cohort within the UK/ANZ DCIS trial. Lancet Digital Health 6, e562–e569 (2024).

    CAS  PubMed  Google Scholar 

  24. Lu, M. Y. et al. AI-based pathology predicts origins for cancers of unknown primary. Nature 594, 106–110 (2021).

    CAS  PubMed  Google Scholar 

  25. Bulten, W. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat. Med. 28, 154–163 (2022).

    CAS  PubMed  PubMed Central  Google Scholar 

  26. Bulten, W. et al. Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study. Lancet Oncol. 21, 233–241 (2020).

    PubMed  Google Scholar 

  27. Aggarwal, A. et al. Computational pathology identifies immune-mediated collagen disruption to predict clinical outcomes in gynecologic malignancies. Commun. Med. 4, 2 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  28. Li, H. et al. Collagen fiber orientation disorder from H&E images is prognostic for early stage breast cancer: clinical trial validation. NPJ Breast Cancer 7, 104 (2021).

    CAS  PubMed  PubMed Central  Google Scholar 

  29. Bilal, M. et al. Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study. Lancet Digital Health 3, e763–e772 (2021).

    CAS  PubMed  Google Scholar 

  30. Lugli, A., Zlobec, I., Berger, M. D., Kirsch, R. & Nagtegaal, I. D. Tumour budding in solid cancers. Nat. Rev. Clin. Oncol. 18, 101–115 (2021).

    PubMed  Google Scholar 

  31. Neppl, C., Zlobec, I., Schmid, R. A. & Berezowska, S. Validation of the International Tumor Budding Consensus Conference (ITBCC) 2016 recommendation in squamous cell carcinoma of the lung – a single-center analysis of 354 cases. Mod. Pathol. 33, 802–811 (2020).

    CAS  PubMed  Google Scholar 

  32. Dawson, H. et al. Tumour budding/T cell infiltrates in colorectal cancer: proposal of a novel combined score. Histopathology 76, 572–580 (2020).

    PubMed  Google Scholar 

  33. Xie, W. et al. Prostate cancer risk stratification via nondestructive 3D pathology with deep learning-assisted gland analysis. Cancer Res. 82, 334–345 (2022).

    CAS  PubMed  Google Scholar 

  34. Lu, C. et al. A prognostic model for overall survival of patients with early-stage non-small cell lung cancer: a multicentre, retrospective study. Lancet Digital Health 2, e594–e606 (2020).

    PubMed  Google Scholar 

  35. Lu, C. et al. Feature-driven local cell graph (FLocK): new computational pathology-based descriptors for prognosis of lung cancer and HPV status of oropharyngeal cancers. Med. Image Anal. 68, 101903 (2021).

    PubMed  Google Scholar 

  36. Fashi, P. A., Hemati, S., Babaie, M., Gonzalez, R. & Tizhoosh, H. R. A self-supervised contrastive learning approach for whole slide image representation in digital pathology. J. Pathol. Inf. 13, 100133 (2022).

    Google Scholar 

  37. Tsai, P.-C. et al. Histopathology images predict multi-omics aberrations and prognoses in colorectal cancer patients. Nat. Commun. 14, 2102 (2023).

    CAS  PubMed  PubMed Central  Google Scholar 

  38. Marostica, E. et al. Development of a histopathology informatics pipeline for classification and prediction of clinical outcomes in subtypes of renal cell carcinoma. Clin. Cancer Res. 27, 2868–2878 (2021).

    CAS  PubMed  Google Scholar 

  39. Campanella, G., Vanderbilt, C. & Fuchs, T. Computational pathology at health system scale – self-supervised foundation models from three billion images. Preprint at arXiv https://doi.org/10.48550/arXiv.2310.07033 (2024).

  40. Da Silva, L. M. et al. Independent real‐world application of a clinical‐grade automated prostate cancer detection system. J. Pathol. 254, 147–158 (2021).

    PubMed  PubMed Central  Google Scholar 

  41. Corredor, G. et al. Spatial architecture and arrangement of tumor-infiltrating lymphocytes for predicting likelihood of recurrence in early-stage non-small cell lung cancer. Clin. Cancer Res. 25, 1526–1534 (2019).

    CAS  PubMed  Google Scholar 

  42. Koyuncu, C. F. et al. Computerized tumor multinucleation index (MuNI) is prognostic in p16+ oropharyngeal carcinoma. J. Clin. Invest. 131, e145488 (2021).

    PubMed  PubMed Central  Google Scholar 

  43. Balkenhol, M. C. A. et al. Optimized tumour infiltrating lymphocyte assessment for triple negative breast cancer prognostics. Breast 56, 78–87 (2021).

    PubMed  PubMed Central  Google Scholar 

  44. Pinckaers, H. et al. Predicting biochemical recurrence of prostate cancer with artificial intelligence. Commun. Med. 2, 64 (2022).

    PubMed  PubMed Central  Google Scholar 

  45. Vendittelli, P. et al. Automatic quantification of tumor–stroma ratio as a prognostic marker for pancreatic cancer. PLoS ONE 19, e0301969 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  46. Aggarwal, A. et al. Image analysis uncovers associations between immune landscape, collagen structure, and neoadjuvant chemotherapy in high-grade serous ovarian carcinomas. Heliyon 10, e33618 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  47. Li, H. et al. Quantitative nuclear histomorphometric features are predictive of Oncotype DX risk categories in ductal carcinoma in situ: preliminary findings. Breast Cancer Res. 21, 114 (2019).

    PubMed  PubMed Central  Google Scholar 

  48. Geaney, A. et al. Translation of tissue-based artificial intelligence into clinical practice: from discovery to adoption. Oncogene 42, 3545–3555 (2023).

    CAS  PubMed  PubMed Central  Google Scholar 

  49. Balestriero, R. et al. A cookbook of self-supervised learning. Preprint at arXiv https://doi.org/10.48550/arXiv.2304.12210 (2023).

  50. Unger, M. & Kather, J. N. A systematic analysis of deep learning in genomics and histopathology for precision oncology. BMC Med. Genomics 17, 48 (2024).

    PubMed  PubMed Central  Google Scholar 

  51. Monabbati, S. et al. Machine vision-detected peritumoral lymphocytic aggregates are associated with disease-free survival in papillary thyroid carcinoma patients. Lab. Invest. 104, 102168 (2024).

    PubMed  Google Scholar 

  52. Monabbati, S. et al. A novel computational pathology approach for identifying gene signatures prognostic of disease-free survival for papillary thyroid carcinomas. Eur. J. Cancer 212, 114326 (2024).

    CAS  PubMed  Google Scholar 

  53. Wang, X. et al. Spatial interplay patterns of cancer nuclei and tumor-infiltrating lymphocytes (TILs) predict clinical benefit for immune checkpoint inhibitors. Sci. Adv. 8, eabn3966 (2022).

    CAS  PubMed  PubMed Central  Google Scholar 

  54. Arabyarmohammadi, S. et al. in Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 Part VI (eds Greenspan, H. et al.) 797–807 (Springer, 2023).

  55. Monabbati, S., Khalighi, S., Fu, P., Asa, S. & Madabhushi, A. in Medical Imaging 2023: Digital and Computational Pathology Vol. 12471 (eds Tomaszewski, J. E. & Ward, A. D.) 284–293 (SPIE, 2023).

  56. Nag, R. et al. Association of artificial intelligence-derived collagen disorder architecture (CoDA) features with survival outcome and objective response to immune checkpoint inhibitors in patients with head and neck squamous cell carcinoma [abstract]. J. Clin. Oncol. 42 (Suppl. 16), 6061 (2024).

    Google Scholar 

  57. Monabbati, S. et al. Automated analysis of computerized morphological features of cell clusters associated with malignancy on bile duct brushing whole slide images. Cancer Med. 12, 6365–6378 (2023).

    PubMed  Google Scholar 

  58. Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555–570 (2021).

    PubMed  PubMed Central  Google Scholar 

  59. Oquab, M. et al. DINOv2: learning robust visual features without supervision. Preprint at arXiv https://doi.org/10.48550/arXiv.2304.07193 (2024).

  60. Alfasly, S. et al. Foundation models for histopathology – fanfare or flair. Mayo Clin. Proceedings: Digital Health 2, 165–174 (2024).

    Google Scholar 

  61. Spratt, D. E. et al. Artificial intelligence predictive model for hormone therapy use in prostate cancer. NEJM Evid. 2, EVIDoa2300023 (2023).

    PubMed  PubMed Central  Google Scholar 

  62. Boehm, K. M. et al. Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer. Nat. Cancer 3, 723–733 (2022).

    CAS  PubMed  PubMed Central  Google Scholar 

  63. Lu, C., Shiradkar, R. & Liu, Z. Integrating pathomics with radiomics and genomics for cancer prognosis: a brief review. Chin. J. Cancer Res. 33, 563–573 (2021).

    PubMed  PubMed Central  Google Scholar 

  64. Guo, J. et al. Cross-modal deep learning model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer. NPJ Precis. Onc. 8, 189 (2024).

    Google Scholar 

  65. Goyal, M. et al. A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk. NPJ Breast Cancer 10, 93 (2024).

    CAS  PubMed  PubMed Central  Google Scholar 

  66. Joshi, G. et al. FDA-approved artificial intelligence and machine learning (AI/ML)-enabled medical devices: an updated landscape. Electronics 13, 498 (2024).

    Google Scholar 

  67. FDA. Artificial intelligence and machine learning (AI/ML)-enabled medical devices. FDA https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices (2024).

  68. Cheng, J. Y., Abel, J. T., Balis, U. G. J., McClintock, D. S. & Pantanowitz, L. Challenges in the development, deployment, and regulation of artificial intelligence in anatomic pathology. Am. J. Pathol. 191, 1684–1692 (2021).

    PubMed  Google Scholar 

  69. European Commission. Proposal for a Regulation of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act) and Amending Certain Union Legislative Acts (Publications Office of the European Union, 2021).

  70. Proscia. Proscia receives FDA 510(k) clearance for Concentriq AP-Dx. Proscia proscia.com/press-releases/proscia-receives-fda-510k-clearance-for-concentriq-ap-dx-2/ (2024).

  71. IBEX. AI-First Approach to Cancer Diagnostics Earns Ibex Medical Analytics Notable Milestones. IBEX ibex-ai.com/milestones/ (2024).

  72. Directorate-General for Health and Food Safety. Manufacturer IVD. ec.europa.eu https://health.ec.europa.eu/medical-devices-new-regulations/getting-ready-new-regulations/manufacturer-ivd_en (accessed 7 February 2025).

  73. Food and Drug Administration. FDA Authorizes Software that Can Help Identify Prostate Cancer. FDA www.fda.gov/news-events/press-announcements/fda-authorizes-software-can-help-identify-prostate-cancer (2021).

  74. Roche Diagnostics. Roche Receives FDA Clearance on its Digital Pathology Solution for Diagnostic Use. Roche Diagnostics diagnostics.roche.com/us/en/news-listing/2024/roche-receives-fda-clearance-on-its-digital-pathology-solution-for-diagnostic-use.html (2024).

  75. American Medical Association. CPT® Overview and Code Approval. AMA www.ama-assn.org/practice-management/cpt/cpt-overview-and-code-approval (2024).

  76. Centers for Medicare & Medicaid Services. Medicare Claims Processing Manual. CMS.gov www.cms.gov/Regulations-and-Guidance/Guidance/Manuals/Internet-Only-Manuals-IOMs-Items/CMS018912 (2024).

  77. College of American Pathologists. 13 Digital Pathology Codes you Should Use in 2023 and Beyond. College of American Pathologists www.cap.org/member-resources/articles/13-digital-pathology-codes-you-should-use-in-2023-and-beyond (2023).

  78. College of American Pathologists. Digital Pathology Codes. College of American Pathologists www.cap.org/advocacy/payments-for-pathology-services/digital-pathology-codes (2023).

  79. College of American Pathologists. How to Use the New Digital Pathology CPT Codes: CAP Answers Questions. College of American Pathologists www.cap.org/member-resources/articles/how-to-use-the-new-digital-pathology-cpt-codes (2023).

  80. Mantovani, A., Leopaldi, C., Nighswander, C. M. & Bidino, R. D. Access and reimbursement pathways for digital health solutions and in vitro diagnostic devices: current scenario and challenges. Front. Med. Technol. 5, 1101476 (2023).

    PubMed  PubMed Central  Google Scholar 

  81. Pharmaceuticals and Medical Devices Agency. The 1st Subcommittee on Software as a Medical Device Utilizing AI and Machine Learning. PMDA www.pmda.go.jp/english/rs-sb-std/sb/subcommittees/0024.html (2021).

  82. Ministry of Food and Drug Safety. Guidance on the Review and Approval of Artificial Intelligence (AI)-based Medical Devices. Ministry of Food and Drug Safety www.mfds.go.kr/eng/brd/m_40/view.do?seq=72627&utm_source=chatgpt.com (2023).

  83. National Medical Products Administration. NMPA Announcement on Guidance for the Classification Defining of AI-Based Medical Software Products. NMPA english.nmpa.gov.cn/2021-07/08/c_660267.htm?utm_source=chatgpt.com (2021).

  84. Indian Council of Medical Research. Ethical Guidelines for Application of Artificial Intelligence in Biomedical Research and Healthcare. ICMR www.icmr.gov.in/ethical-guidelines-for-application-of-artificial-intelligence-in-biomedical-research-and-healthcare (2023).

  85. Larsen, M. P. & Tsang, P. Laboratory Developed Tests. PathologyOutlines.com www.pathologyoutlines.com/topic/managementlabdevelopedtests.html (2024).

  86. Food and Drug Administration. Laboratory Developed Tests. FDA www.fda.gov/medical-devices/in-vitro-diagnostics/laboratory-developed-tests (2025).

  87. Artera. For Patients. Artera https://artera.ai/for-patients (2025).

  88. Codify. CPT® Code 0376U, Under Proprietary Laboratory Analyses. AAPC www.aapc.com/codes/cpt-codes/0376U (2024).

  89. Schaeffer, E. M. et al. NCCN guidelines® insights: prostate cancer, version 3.2024. J. Natl Compr. Cancer Netw. 22, 140–150 (2024).

    Google Scholar 

  90. Backman, I. The FDA’s Proposed Ruling on Lab Tests Could Have Unintended Consequences. Yale School of Medicine medicine.yale.edu/news-article/the-fdas-proposed-ruling-on-lab-tests-could-have-unintended-consequences/ (2024).

  91. Dombrink, I. et al. Critical implications of IVDR for innovation in diagnostics: input from the Biomed Alliance Diagnostics Task Force. HemaSphere 6, e724 (2022).

    PubMed  PubMed Central  Google Scholar 

  92. Yousif, M., Hassell, L. & Pantanowitz, L. in Digital Innovation for Healthcare in COVID-19 Pandemic (eds de Pablos, P. O. et al.) Ch. 7, 95–107 (Academic Press, 2022).

  93. Luchini, C., Pea, A. & Scarpa, A. Artificial intelligence in oncology: current applications and future perspectives. Br. J. Cancer 126, 4–9 (2022).

    PubMed  Google Scholar 

  94. Wu, S. et al. An artificial intelligence model for detecting pathological lymph node metastasis in prostate cancer using whole slide images: a retrospective, multicentre, diagnostic study. eClinicalMedicine 71, 102580 (2024).

    PubMed  PubMed Central  Google Scholar 

  95. Reddy, S., Shaheed, A., Seo, Y. & Patel, R. Development of an artificial intelligence model for the classification of gastric carcinoma stages using pathology slides. Cureus 16, e56740 (2024).

    PubMed  PubMed Central  Google Scholar 

  96. van Dooijeweert, C. et al. Clinical implementation of artificial-intelligence-assisted detection of breast cancer metastases in sentinel lymph nodes: the CONFIDENT-B single-center, non-randomized clinical trial. Nat. Cancer 5, 1195–1205 (2024).

    PubMed  PubMed Central  Google Scholar 

  97. Eloy, C. et al. Artificial intelligence-assisted cancer diagnosis improves the efficiency of pathologists in prostatic biopsies. Virchows Arch. 482, 595–604 (2023).

    CAS  PubMed  PubMed Central  Google Scholar 

  98. Dawson, H. Digital pathology – rising to the challenge. Front. Med. 9, 888896 (2022).

    Google Scholar 

  99. Williams, B. J., Lee, J., Oien, K. A. & Treanor, D. Digital pathology access and usage in the UK: results from a national survey on behalf of the National Cancer Research Institute’s CM-Path initiative. J. Clin. Pathol. 71, 463–466 (2018).

    PubMed  Google Scholar 

  100. Aggarwal, A., Badve, S. S., Cuzick, J., Madabhushi, A. & Thorat, M. A. A computational pathology collagen signature predictive of tamoxifen benefit in ductal carcinoma in situ: results from a cohort within the UK/ANZ DCIS randomized trial [abstract 171P]. Ann. Oncol. 35 (Suppl. 2), S284 (2024).

    Google Scholar 

  101. Spratt, D. E. et al. Patient-level data meta-analysis of a multi-modal artificial intelligence (MMAI) prognostic biomarker in high-risk prostate cancer: results from six NRG/RTOG phase III randomized trials [abstract]. J. Clin. Oncol. 41 (Suppl. 6), 299 (2023).

    Google Scholar 

  102. Vora, L. K. et al. Artificial intelligence in pharmaceutical technology and drug delivery design. Pharmaceutics 15, 1916 (2023).

    CAS  PubMed  PubMed Central  Google Scholar 

  103. Lam, T. Y. T. et al. Randomized controlled trials of artificial intelligence in clinical practice: systematic review. J. Med. Internet Res. 24, e37188 (2022).

    PubMed  PubMed Central  Google Scholar 

  104. Kiran, N. et al. Digital pathology: transforming diagnosis in the digital age. Cureus 15, e44620 (2023).

    PubMed  PubMed Central  Google Scholar 

  105. Zarella, M. D. et al. A practical guide to whole slide imaging: a white paper from the digital pathology association. Arch. Pathol. Laboratory Med. 143, 222–234 (2019).

    Google Scholar 

  106. Pantanowitz, L. Digital images and the future of digital pathology. J. Pathol. Inform. 1, 15 (2010).

    PubMed  PubMed Central  Google Scholar 

  107. Morales, S., Engan, K. & Naranjo, V. Artificial intelligence in computational pathology – challenges and future directions. Digital Signal. Process. 119, 103196 (2021).

    Google Scholar 

  108. Fitt, I. Digital Pathology – World – 2023. Signify Research www.signifyresearch.net/market-intelligence/digital-pathology-world-2023/ (2023).

  109. Law, R. Roche gains 510(k) clearance for digital pathology solution for diagnostic use. Medical Device Network https://www.medicaldevice-network.com/news/roche-gains-501-clearance-for-digital-pathology-solution-for-diagnostic-use/?cf-view (2024).

  110. Abbvie. Precision Medicine. Abbvie www.abbvie.com/science/areas-of-innovation/precision-medicine.html (2024).

  111. Berbís, M. Á. Digital and computational pathology: what a time to be alive! Mayo Clin. Proc. Digital Health 2, 18–20 (2024).

    Google Scholar 

  112. García-Rivello, H. et al. Digital pathology in Latin America. Surg. Exp. Pathol. 6, 10 (2023).

    Google Scholar 

  113. Baidoshvili, A. et al. Evaluating the benefits of digital pathology implementation: time savings in laboratory logistics. Histopathology 73, 784–794 (2018).

    PubMed  Google Scholar 

  114. Hanna, M. G. et al. Implementation of digital pathology offers clinical and operational increase in efficiency and cost savings. Arch. Pathol. Lab. Med. 143, 1545–1555 (2019).

    PubMed  PubMed Central  Google Scholar 

  115. Vergani, A., Regis, B., Jocollé, G., Patetta, R. & Rossi, G. Noninferiority diagnostic value, but also economic and turnaround time advantages from digital pathology. Am. J. Surg. Pathol. 42, 841 (2018).

    PubMed  Google Scholar 

  116. Zarella, M. D. et al. Artificial intelligence and digital pathology: clinical promise and deployment considerations. J. Med. Imaging 10, 051802 (2023).

    Google Scholar 

  117. Pinto, D. G., Bychkov, A., Tsuyama, N., Fukuoka, J. & Eloy, C. Real-world implementation of digital pathology: results from an intercontinental survey. Lab. Invest. 103, 100261 (2023).

    PubMed  Google Scholar 

  118. Scalco, R. et al. The status of digital pathology and associated infrastructure within Alzheimer’s disease centers. J. Neuropathol. Exp. Neurol. 82, 202–211 (2023).

    PubMed  PubMed Central  Google Scholar 

  119. Indu, M., Rathy, R. & Binu, M. P. “Slide less pathology”: fairy tale or reality? J. Oral. Maxillofac. Pathol. 20, 284 (2016).

    CAS  PubMed  PubMed Central  Google Scholar 

  120. Bhargava, R. & Madabhushi, A. Emerging themes in image informatics and molecular analysis for digital pathology. Annu. Rev. Biomed. Eng. 18, 387–412 (2016).

    CAS  PubMed  PubMed Central  Google Scholar 

  121. Liu, Y., Levenson, R. M. & Jenkins, M. W. Slide over: advances in slide-free optical microscopy as drivers of diagnostic pathology. Am. J. Pathol. 192, 180–194 (2022).

    PubMed  PubMed Central  Google Scholar 

  122. Indica Labs. Indica Labs Receives First FDA Clearance for HALO AP Dx Digital Pathology Platform. Indica Labs indicalab.com/news/indica-labs-receives-first-fda-clearance-for-halo-ap-dx-digital-pathology-platform/ (2024).

  123. Hosseini, M. S. et al. Computational pathology: a survey review and the way forward. J. Pathol. Inf. 15, 100357 (2024).

    Google Scholar 

  124. Ghassemi, M., Oakden-Rayner, L. & Beam, A. L. The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digital Health 3, e745–e750 (2021).

    CAS  PubMed  Google Scholar 

  125. Chauhan, C. & Gullapalli, R. R. Ethics of AI in pathology: current paradigms and emerging issues. Am. J. Pathol. 191, 1673–1683 (2021).

    PubMed  PubMed Central  Google Scholar 

  126. Roberts, H. et al. in Ethics, Governance, and Policies in Artificial Intelligence (ed. Floridi, L.) 47–79 (Springer, 2021).

  127. Habuka, H. Japan’s Approach to AI Regulation and its Impact on the 2023 G7 Presidency (Center for Strategic & International Studies, 2023).

  128. Chouffani El Fassi, S. et al. Not all AI health tools with regulatory authorization are clinically validated. Nat. Med. 30, 2718–2720 (2024).

    CAS  PubMed  Google Scholar 

  129. Businesswire. ArteraAI Announced as the First-and-Only Predictive Test for Therapy Personalization in the 2024 NCCN Guidelines® for Prostate Cancer. Businesswire www.businesswire.com/news/home/20240304893588/en/ArteraAI-Announced-as-the-First-and-Only-Predictive-Test-for-Therapy-Personalization-in-the-2024-NCCN-Guidelines%C2%AE-for-Prostate-Cancer (2024).

  130. Businesswire. Three UK-Based Hospital Systems Exploring the Power of Paige’s AI for Diagnosing Prostate Cancer in Live Clinical Settings. Businesswire www.businesswire.com/news/home/20240722858117/en/Three-UK-Based-Hospital-Systems-Exploring-the-Power-of-Paige%E2%80%99s-AI-for-Diagnosing-Prostate-Cancer-in-Live-Clinical-Settings (2024).

  131. Kim, I., Kang, K., Song, Y. & Kim, T.-J. Application of artificial intelligence in pathology: trends and challenges. Diagnostics 12, 2794 (2022).

    PubMed  PubMed Central  Google Scholar 

  132. Kanan, C. et al. Independent validation of Paige Prostate: assessing clinical benefit of an artificial intelligence tool within a digital diagnostic pathology laboratory workflow [abstract]. J. Clin. Oncol. 38 (Suppl. 15), e14076 (2020).

    Google Scholar 

  133. Zehra, T., Parwani, A., Abdul-Ghafar, J. & Ahmad, Z. A suggested way forward for adoption of AI-enabled digital pathology in low resource organizations in the developing world. Diagn. Pathol. 18, 68 (2023).

    PubMed  PubMed Central  Google Scholar 

  134. Schwen, L. O., Kiehl, T.-R., Carvalho, R., Zerbe, N. & Homeyer, A. Digitization of pathology labs: a review of lessons learned. Lab. Invest. 103, 100244 (2023).

    PubMed  Google Scholar 

  135. Zhang, D. Y. et al. Implementation of digital pathology and artificial intelligence in routine pathology practice. Lab. Invest. 104, 102111 (2024).

    PubMed  Google Scholar 

  136. Sparano, J. A. et al. Adjuvant chemotherapy guided by a 21-gene expression assay in breast cancer. N. Engl. J. Med. 379, 111–121 (2018).

    CAS  PubMed  PubMed Central  Google Scholar 

  137. Food and Drug Administration. 510(k) Premarket Notification. FDA www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm?ID=K212361 (2024).

  138. Food and Drug Administration. Premarket Approval (PMA). FDA www.fda.gov/medical-devices/premarket-submissions-selecting-and-preparing-correct-submission/premarket-approval-pma (2023).

  139. Food and Drug Administration. De Novo Classification Request. FDA www.fda.gov/medical-devices/premarket-submissions-selecting-and-preparing-correct-submission/de-novo-classification-request (2022).

  140. Directorate-General for Health and Food Safety. In-House Medical Devices. European Commission health.ec.europa.eu/medical-devices-topics-interest/house-medical-devices_en (2024).

  141. Shurrab, S. & Duwairi, R. Self-supervised learning methods and applications in medical imaging analysis: a survey. PeerJ Comput. Sci. 8, e1045 (2022).

    PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

The research of A.M. is supported by the Lung Cancer Research Program (W81XWH-18-1-0440, W81XWH-20-1-0595), Mayo Clinic Breast Cancer SPORE grant P50 CA116201 from the National Institutes of Health, the Kidney Precision Medicine Project (KPMP) Glue Grant, National Cancer Institute (under award numbers R01CA249992-01A1, R01CA202752-01A1, R01CA208236-01A1, R01CA216579-01A1, R01CA220581-01A1, R01CA257612-01A1, 1U01CA239055-01, 1U01CA248226-01 and 1U54CA254566-01), National Center for Research Resources (under award number 1 C06 RR12463-01), National Heart, Lung and Blood Institute (1R01HL15127701A1 and R01HL15807101A1), National Institute of Biomedical Imaging and Bioengineering (1R43EB028736-01), Peer Reviewed Cancer Research Program (W81XWH-18-1-0404, W81XWH-21-1-0345 and W81XWH-21-1-0160), Prostate Cancer Research Program (W81XWH-15-1-0558 and W81XWH-20-1-0851). and the VA Merit Review Award IBX004121A from the United States Department of Veterans Affairs Biomedical Laboratory Research and Development Service the Office of the Assistant Secretary of Defense for Health Affairs, through the Breast Cancer Research Program (W81XWH-19-1-0668). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health, the US Department of Veterans Affairs, the Department of Defense, or the US Government.

Author information

Author notes

  1. These authors contributed equally: Arpit Aggarwal, Satvika Bharadwaj.

Authors and Affiliations

  1. Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA

    Arpit Aggarwal, Satvika Bharadwaj, Germán Corredor & Anant Madabhushi

  2. Atlanta Veterans Affairs Medical Center, Atlanta, GA, USA

    Germán Corredor & Anant Madabhushi

  3. Department of Biomedical Engineering, Emory University, Atlanta, GA, USA

    Tilak Pathak

  4. Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA, USA

    Sunil Badve

Authors
  1. Arpit Aggarwal
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Satvika Bharadwaj
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Germán Corredor
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Tilak Pathak
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Sunil Badve
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Anant Madabhushi
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

A.A. and S. Bharadwaj researched data for the article and wrote it. All authors contributed substantially to discussion of the contents, and reviewed and edited the manuscript before submission.

Corresponding author

Correspondence to Anant Madabhushi.

Ethics declarations

Competing interests

S. Badve is on the advisory board for Mindpeak; and is also an ad hoc adviser for Agilent, AstraZeneca, Daichii-Sanyo and Roche-Ventana. A.M. is an equity holder in Picture Health, Elucid Bioimaging and Inspirata Inc.; currently he serves on the advisory board of Picture Health; has sponsored research agreements with AstraZeneca, Boehringer-Ingelheim, Bristol Myers-Squibb and Eli-Lilly; has developed technology licensed to Picture Health and Elucid Bioimaging; is involved in two different R01 grants with Inspirata Inc.; and is a member for the Frederick National Laboratory Advisory Committee. A.A., S. Bharadwaj, G.C. and T.P. declare no competing interests.

Peer review

Peer review information

Nature Reviews Clinical Oncology thanks J. N. Kather and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

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

Glossary

510(k) clearance

Premarket approval submitted to the FDA to demonstrate that the device to be marketed is safe and effective137. Premarket approvals are conducted by the FDA to ensure the safety and effectiveness of Class III medical devices138.

Convolutional neural networks

(CNNs). A type of deep learning model designed to process data, such as images7. CNNs use convolutional layers to automatically extract spatial features, such as edges, shapes and textures, making them highly effective for image-based tasks, including tumour segmentation, classification and pattern recognition in computational pathology7.

De Novo Classification Request

FDA pathway for the classification and marketing of Class I and II medical devices, which precede future 510(k) submissions139.

Foundation models

Large-scale machine learning models trained on vast, unlabelled datasets that can be fine-tuned for various downstream tasks. In computational pathology, these models can be adapted for image classification, segmentation and prognostic prediction across different types of tissue, leveraging their broad generalization capabilities to enhance accuracy and adaptability in various clinical applications11.

In-house devices

In vitro diagnostic devices manufactured and used exclusively within health-care institutions in the European Union, exempt from Conformité Européene marking if they comply with the provisions of Article 5(5) of the In Vitro Diagnostic Medical Devices Regulation140.

Laboratory-developed tests

In vitro diagnostic products intended for clinical use in the USA and designed, manufactured and used within a single laboratory certified under the Clinical Laboratory Improvement Amendments of 1988 (ref. 86).

Machine learning

An approach that enables the identification of patterns from data and the making of decisions or predictions without explicit programming. In computational pathology, machine learning approaches are used to analyse large-scale medical datasets, such as digitized slides, aiding in patient diagnosis, prognosis and treatment planning7.

Self-supervised learning models

A machine learning approach in which models learn from data without the need for manually labelled examples. These models are particularly valuable in computational pathology, an area in which annotated datasets are limited but large-scale image repositories are available141.

Supervised learning models

A machine learning approach in which models learn from labelled data (that is, from datasets with known input–output pairs). This technique is often used in tasks for which labelled pathology images, such as tumour versus non-tumour regions, are available, enabling the model to classify new data on the basis of learned patterns7.

Transformers

Deep learning architectures designed for natural language processing tasks but increasingly applied to image analysis tasks138. Transformers rely on a self-attention mechanism that enables them to capture relationships across all parts of the input image138. In computational pathology, transformers are being used for tasks including whole-slide image classification138.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Aggarwal, A., Bharadwaj, S., Corredor, G. et al. Artificial intelligence in digital pathology — time for a reality check. Nat Rev Clin Oncol 22, 283–291 (2025). https://doi.org/10.1038/s41571-025-00991-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41571-025-00991-6

Search

Advanced search

Quick links

Nature Briefing: Cancer

Sign up for the Nature Briefing: Cancer newsletter — what matters in cancer research, free to your inbox weekly.

Get what matters in cancer research, free to your inbox weekly. Sign up for Nature Briefing: Cancer
点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载