Keywords
digital pathology
tumor grading
immunohistochemistry
histopathology
How to Cite
Abstract
Introduction: Artificial intelligence (AI) is at the forefront of modern technology, with emerging applications in the healthcare sector now gaining recognition. Pathology is anticipated to be a key area where the impact of AI will be substantial. As more laboratories transition to digital pathology, this will create the essential infrastructure needed to implement these tools, making their application a reality in diagnostic practice. The potential of AI in pathology lies in developing image analysis tools that can support diagnosis or generate new insights into disease biology, beyond what a human observer can achieve. Examples currently exist providing diagnostic support for a limited but growing number of applications, such as tumor detection, automated tumor grading, immunohistochemistry scoring, and predicting mutation status. Several challenges remain, including the validation and establishment of a regulatory framework for these tools, as well as the ethical implications of AI in pathology. These include concerns about patient privacy and consent, along with the potential for AI to worsen existing healthcare disparities. In this article, we offer an overview of AI in histopathology, discuss its possible workflow applications, and highlight significant examples of AI's potential impact in clinical practice. We also explore considerations for implementing AI in practice.
Conclusion: There has been a significant increase in the development and application of AI tools, including image-based algorithms, in pathology services, and they are expected to dominate the field in the coming years. The implementation of computational pathology and the use of pathology-related AI tools can be viewed as a paradigm shift that will transform the management of pathology services. While AI will undoubtedly enhance the efficiency of pathology services, it is crucial to recognize that it will not replace the role of pathologists. Instead, it will augment their capabilities, enabling them better to meet the demands of this era of precision medicine.
References
Moxley-Wyles, B., Colling, R., & Verrill, C. (2020). Artificial intelligence in pathology: an overview. Diagnostic Histopathology, 26(11), 513–520. https://doi.org/10.1016/j.mpdhp.2020.08.004
Bera, K., Schalper, K. A., Rimm, D. L., Velcheti, V., & Madabhushi, A. (2019). Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology. Nature Reviews. Clinical oncology, 16(11), 703–715. https://doi.org/10.1038/s41571-019-0252-y
Hunter, B., Hindocha, S., & Lee, R. W. (2022). The Role of Artificial Intelligence in Early Cancer Diagnosis. Cancers, 14(6), 1524. https://doi.org/10.3390/cancers14061524
Rakha EA, Toss M, Shiino S, et al. Current and future applications of artificial intelligence in pathology: a clinical perspective. Journal of Clinical Pathology 2021;74:409-414. https://doi.org/10.1136/jclinpath-2020-206908
Huo, Y., Deng, R., Liu, Q., Fogo, A. B., & Yang, H. (2021). AI applications in renal pathology. Kidney International, 99(6), 1309-1320. https://doi.org/10.1016/j.kint.2021.01.015
Jara-Lazaro, A. R., Thamboo, T. P., Teh, M., & Tan, P. H. (2010). Digital pathology: exploring its applications in diagnostic surgical pathology practice. Pathology, 42(6), 512-518. https://doi.org/10.3109/00313025.2010.508787
Webster J.D., Dunstan R.W. Whole-slide imaging and automated image analysis: considerations and opportunities in the practice of pathology Vet Pathol, 51 (2014), pp. 211-223 http://www.sagepub.com/journalsPermissions.nav
LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539
Krizhevsky, I. Sutskever, G.E. Hinton ImageNet classification with deep convolutional neural networks Commun ACM, 60 (2017), pp. 84-90 https://doi.org/10.1145/3065386
Goodfellow, Y., Bengio, A., Courville, Y., Bengio, Deep Learning, MIT Press, Cambridge, MA (2016). http://www.deeplearningbook.org/
Wang S, Yang DM, Rong R, Zhan X, Xiao G (2019). Pathology image analysis using segmentation deep learning algorithms. Am J Pathol 189(9):1686–1698 https://doi.org/10.1016/j.ajpath.2019.05.007
Hunter, B., Hindocha, S., & Lee, R. W. (2022). The Role of Artificial Intelligence in Early Cancer Diagnosis. Cancers, 14(6), 1524. https://doi.org/10.3390/cancers14061524
Reis-Filho, J. S., & Kather, J. N. (2023). Overcoming the challenges to the implementation of artificial intelligence in pathology. Journal of the National Cancer Institute, 115(6), 608–612. https://doi.org/10.1093/jnci/djad048
Bera, K., Schalper, K. A., Rimm, D. L., Velcheti, V., & Madabhushi, A. (2019). Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology. Nature Reviews. Clinical oncology, 16(11), 703–715. https://doi.org/10.1038/s41571-019-0252-y
Reis-Filho, J. S., & Kather, J. N. (2023). Overcoming the challenges to the implementation of artificial intelligence in pathology. Journal of the National Cancer Institute, 115(6), 608–612. https://doi.org/10.1093/jnci/djad048
Rakha EA, Toss M, Shiino S, et al. Current and future applications of artificial intelligence in pathology: a clinical perspective; Journal of Clinical Pathology 2021;74:409-414.