CoChat
Sign Up
Cited by 42AI in cancer detectionArtificial Intelligence in Healthcare and EducationRadiomics and Machine Learning in Medical Imaging

Translation of tissue-based artificial intelligence into clinical practice: from discovery to adoption

Open access
Geaney, Alice, O’Reilly, Paul, Maxwell, Perry, James, Jacqueline A., McArt, Darragh, Salto-Tellez, Manuel·2023·Oncogene
DOI 10.1038/s41388-023-02857-6PMC PMC10673711
Open this paper in CoChat — free accountOpen PDF

Abstract

Digital pathology (DP), or the digitization of pathology images, has transformed oncology research and cancer diagnostics. The application of artificial intelligence (AI) and other forms of machine learning (ML) to these images allows for better interpretation of morphology, improved quantitation of biomarkers, introduction of novel concepts to discovery and diagnostics (such as spatial distribution of cellular elements), and the promise of a new paradigm of cancer biomarkers. The application of AI to tissue analysis can take several conceptual approaches, within the domains of language modelling and image analysis, such as Deep Learning Convolutional Neural Networks, Multiple Instance Learning approaches, or the modelling of risk scores and their application to ML. The use of different approaches solves different problems within pathology workflows, including assistive applications for the detection and grading of tumours, quantification of biomarkers, and the delivery of established and new image-based biomarkers for treatment prediction and prognostic purposes. All these AI formats, applied to digital tissue images, are also beginning to transform our approach to clinical trials. In parallel, the novelty of DP/AI devices and the related computational science pipeline introduces new requirements for manufacturers to build into their design, development, regulatory and post-market processes, which may need to be taken into account when using AI applied to tissues in cancer discovery. Finally, DP/AI represents challenge to the way we accredit new diagnostic tools with clinical applicability, the understanding of which will allow cancer patients to have access to a new generation of complex biomarkers.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41388-023-02857-6

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Models that may perform well during development can degrade in real-world settings due to dataset drift across diverse sites, devices, and populations.

    “Models that may perform well during development can degrade in real-world settings due to dataset drift across diverse sites, devices, and populations15–18.”

    From What the AI era doctor should know: a scoping review of proposed artificial intelligence competencies for medical education (2026) · cites this paper as [18]

    The Design and development section says real-world monitoring can identify drift and model degradation after clinical deployment. It also calls for attention to scanner type and patient-population variation when developing a model. The cited passages do not specifically establish that dataset drift across different sites, devices, and populations causes the degradation described in the claim; no page numbers were provided in our copy. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 34 · Cited by 42

Research works printed but not linked: 29

  1. [1]Salto-Tellez M, Maxwell P, Hamilton P. Artificial intelligence—the third revolution in pathology. Histopathology. 2019;74:372–6. 30270453
  2. [2]Arends MJ, Salto-Tellez M. Low-contact and high-interconnectivity pathology (LC&HI Path): post-COVID19-pandemic practice of pathology. Histopathology. 2020;77:518–24. https://onlinelibrary.wiley.com/doi/full/10.1111/his.14174. PMC7300838 32516836 · DOI
  3. [3]Chan JY, Salto-Tellez M. Opinion: molecular gestalt and modern pathology. Adv Anat Pathol. 2012;19:425–6. https://journals.lww.com/anatomicpathology/Fulltext/2012/11000/Opinion__Molecular_Gestalt_and_Modern_Pathology.8.aspx. 23060068
  4. [4]Beck AH, Sangoi AR, Leung S, Marinelli RJ, Nielsen TO, Van De Vijver MJ, et al. Imaging: systematic analysis of breast cancer morphology uncovers stromal features associated with survival. Sci Transl Med. 2011. https://www.science.org/doi/10.1126/scitranslmed.3002564. 22072638 · DOI
  5. [7]Coudray N, Ocampo PS, Sakellaropoulos T, Narula N, Snuderl M, Fenyö D, et al. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nat Med. 2018;24:1559–67. PMC9847512 30224757
  6. [8]Humphries MP McQuaid S Craig SG Bingham V Maxwell P Maurya M Critical appraisal of programmed death ligand 1 reflex diagnostic testing: current standards and future opportunities J Thorac Oncol 2019 14 45 53 10.1016/j.jtho.2018.09.025 30296485 PMC6328626 · DOI
  7. [9]Viratham Pulsawatdi A, Craig SG, Bingham V, McCombe K, Humphries MP, Senevirathne S, et al. A robust multiplex immunofluorescence and digital pathology workflow for the characterisation of the tumour immune microenvironment. Mol Oncol. 2020;14:2384–402. PMC7530793 32671911
  8. [10]Yuan Y. Spatial heterogeneity in the tumor microenvironment. Cold Spring Harb Perspect Med. 2016;6:a026583 http://perspectivesinmedicine.cshlp.org/content/6/8/a026583.full. PMC4968167 27481837
  9. [13]López-Úbeda P, Martín-Noguerol T, Aneiros-Fernández J, Luna A. Natural language processing in pathology: current trends and future insights. Am J Pathol. 2022;192:1486–95. 35985480
  10. [14]Brancati N Anniciello AM Pati P Riccio D Scognamiglio G Jaume G BRACS: a dataset for BReAst carcinoma subtyping in H&E histology images Database 2022 2022 baac093 10.1093/database/baac093 36251776 PMC9575967 · DOI
  11. [15]Campanella G, Hanna MG, Geneslaw L, Miraflor A, Werneck Krauss Silva V, Busam KJ, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med. 2019;25:1301–9. PMC7418463 31308507
  12. [16]Pantanowitz L Quiroga-Garza GM Bien L Heled R Laifenfeld D Linhart C 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 2020 2 e407 16 10.1016/S2589-7500(20)30159-X 33328045 · DOI
  13. [17]Sandbank J, Bataillon G, Nudelman A, Krasnitsky I, Mikulinsky R, Bien L, et al. Validation and real-world clinical application of an artificial intelligence algorithm for breast cancer detection in biopsies. npj Breast Cancer. 2022 8:1. https://www.nature.com/articles/s41523-022-00496-w. PMC9723672 36473870
  14. [19]Fremond S Andani S Barkey Wolf J Dijkstra J Melsbach S Jobsen JJ Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts Lancet Digit Health 2023 5 e71 82 10.1016/S2589-7500(22)00210-2 36496303 · DOI
  15. [20]Echle A Ghaffari Laleh N Quirke P Grabsch HI Muti HS Saldanha OL Artificial intelligence for detection of microsatellite instability in colorectal cancer—a multicentric analysis of a pre-screening tool for clinical application ESMO Open 2022 7 100400 10.1016/j.esmoop.2022.100400 35247870 PMC9058894 · DOI · Paper page
  16. [21]Sarker MMK, Makhlouf Y, Craig SG, Humphries MP, Loughrey M, James JA, et al. A means of assessing deep learning‐based detection of ICOS protein expression in colon cancer. Cancers. 202113:3825. https://www.mdpi.com/2072-6694/13/15/3825/htm. PMC8345140 34359723
  17. [22]Foersch S Glasner C Woerl AC Eckstein M Wagner DC Schulz S Multistain deep learning for prediction of prognosis and therapy response in colorectal cancer Nat Med 2023 29 430 9 10.1038/s41591-022-02134-1 36624314 · DOI · Paper page
  18. [23]Courtiol P, Maussion C, Moarii M, Pronier E, Pilcer S, Sefta M, et al. Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat Med. 2019;25:1519–25. 31591589
  19. [24]Garberis IJ, Saillard C, Drubay D, Schmauch B, Aubert V, Jaeger A, et al. 1124O Prediction of distant relapse in patients with invasive breast cancer from deep learning models applied to digital pathology slides. Ann Oncol. 2021;32:S921 http://www.annalsofoncology.org/article/S0923753421029951/fulltext.
  20. [25]Zheng Q, Yang R, Ni X, Yang S, Xiong L, Yan D, et al. Accurate diagnosis and survival prediction of bladder cancer using deep learning on histological slides. Cancers (Basel). 2022;14:5807. PMC9737237 36497289
  21. [26]Barrios W Abdollahi B Goyal M Song Q Suriawinata M Richards R Bladder cancer prognosis using deep neural networks and histopathology images J Pathol Inf 2022 13 100135 10.1016/j.jpi.2022.100135 PMC9577122 36268091 · DOI
  22. [27]Chunduru P Phillips JJ Molinaro AM Prognostic risk stratification of gliomas using deep learning in digital pathology images Neurooncol Adv. 2022 4 vdac111 10.1093/noajnl/vdac111 35990705 PMC9389424 · DOI
  23. [29]Elliott K, McQuaid S, Salto-Tellez M, Maxwell P. Immunohistochemistry should undergo robust validation equivalent to that of molecular diagnostics. J Clin Pathol. 2015;68:766–70. https://jcp.bmj.com/content/68/10/766. 26280782
  24. [30]Hamilton PW Bankhead P Wang Y Hutchinson R Kieran D McArt DG Digital pathology and image analysis in tissue biomarker research Methods 2014 70 59 73 10.1016/j.ymeth.2014.06.015 25034370 · DOI
  25. [31]Pell R, Oien K, Robinson M, Pitman H, Rajpoot N, Rittscher J, et al. The use of digital pathology and image analysis in clinical trials. J Pathol Clin Res. 2019;5:81–90. https://onlinelibrary.wiley.com/doi/full/10.1002/cjp2.127. PMC6463857 30767396 · DOI
  26. [32]Salto-Tellez M, Reis-Filho JS. Clinical trials and digital pathology—toward quantitative therapeutic immunohistochemistry and tissue hybridization. JAMA Oncol. 2023;9:168–9. https://jamanetwork.com/journals/jamaoncology/fullarticle/2799491. 36520447
  27. [39]Colling R Pitman H Oien K Rajpoot N Macklin P Bachtiar V Artificial intelligence in digital pathology: a roadmap to routine use in clinical practice J Pathol. 2019 249 143 50 10.1002/path.5310 31144302 · DOI
  28. [41]He X Liu X Zuo F Shi H Jing J Artificial intelligence-based multi-omics analysis fuels cancer precision medicine Semin Cancer Biol. 2023 88 187 200 10.1016/j.semcancer.2022.12.009 36596352 · DOI
  29. [44]Raciti P, Sue J, Retamero JA, Ceballos R, Godrich R, Kunz JD, et al. Clinical validation of artificial intelligence–augmented pathology diagnosis demonstrates significant gains in diagnostic accuracy in prostate cancer detection. Arch Pathol Lab Med. 2023;147:1178–85. 36538386

Authors
Geaney, A., O’Reilly, P., Maxwell, P., James, J. A., McArt, D., & Salto-Tellez, M.
Affiliations
Queen's University Belfast (GB)
ORCID
Venue
Oncogene
Publisher
Springer Science and Business Media LLC
Published
2023-10-24
Volume
42
Issue
48
Pages
3545-3555
ISSN
  • 0950-9232 (ISSN-L)
  • 1476-5594
DOI
10.1038/s41388-023-02857-6
PMC
PMC10673711
OpenAlex
W4387905971
Cited by
42
References
34
Citations by year
2026: 15 · 2025: 17 · 2024: 10
FWCI
0.88
Type
journal article
Language
en
Open access
Licence
Locations
  • Oncogene (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Research Portal (Queen's University Belfast) (acceptedVersion, cc-by)
Funders
National Institute for Health and Care Research (AI_AWARD02222)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
Keywords
digital pathology, artificial intelligence in pathology, cancer diagnosis, imaging biomarkers, biomarker quantification, spatial biomarkers, multiple instance learning, convolutional neural networks, risk score prediction, clinical translation of AI, clinical trials
MeSH terms
Machine Learning, Artificial Intelligence, Humans, Medical Oncology, Neoplasms, Biomarkers, Tumor

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review