#PAGE_PARAMS# #ADS_HEAD_SCRIPTS# #MICRODATA#
preLekára.sk / Journals / Czecho-Slovak Pathology / 2025 - 1

Introduction to Machine Learning for Pathologists

Czech version

Authors: Tomáš Brázdil 1;  Adam Kukučka 1;  Vít Musil 1;  Rudolf Nenutil 2;  Petr Holub 3
Authors‘ workplace: Fakulta informatiky, Masarykova univerzita, Brno, Česká republika 1;  Masarykův onkologický ústav, Brno, Česká republika 2;  Ústav výpočetní techniky, Masarykova univerzita, Brno, Česká republika 3
Published in: Čes.-slov. Patol., 61, 2025, No. 1, p. 11-21
Category: Reviews Article

Overview

Digitalization has gradually made its way into many areas of medicine, including pathology. Along with digital data processing comes the application of artificial intelligence methods to simplify routine processes, enhance safety, etc. Although general awareness of artificial intelligence methods is increasing, it is still not common for professionals from non-technical fields to have a detailed understanding of how such systems work and learn. This text aims to explain the basics of machine learning in an accessible way using examples and illustrations from digital pathology. This is not intended to be a comprehensive overview or an introduction to cutting-edge methods. Instead, we use the simplest models to focus on fundamental concepts behind most learning systems. The text concentrates on decision trees, whose functionality is easy to explain, and basic neural networks, the primary models used in today’s artificial intelligence. We also attempt to describe the collaborative process between medical specialists, who provide the data, and computer scientists, who use this data to develop learning systems. This text will help bridge the knowledge gap between medical professionals and computer scientists, contributing to more effective interdisciplinary collaboration.

Keywords:

machine learning – Neural networks – Decision trees – Digital Pathology – Diagnostic Systems

Sources

  1. Song AH, Jaume G, Williamson DFK, et al. Artificial intelligence for digital and computational pathology. Nat Rev Bioeng 2023; 1(12): 930–949.
  2. Chen P, Li H, Zhu C, Zheng S, Shui Z, Yang L. WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Images. In: Linguraru MG, Dou Q, Feragen A, et al., editors. Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 [Internet]. Cham: Springer Nature Switzerland; 2024 [cited 2024 Nov 14]. p. 546–556. (Lecture Notes in Computer Science; vol. 15004). Available from: https://link.springer. com/10.1007/978-3-031-72083-3_51
  3. ChatGPT [Internet]. OpenAI; (Large language model). Available from: https://chat.openai. com/
  4. Russell SJ, Norvig P, Davis E. Artificial intelligence: a modern approach. 3rd ed. Upper Saddle River: Prentice Hall; 2010. 1132 p. (Prentice Hall series in artificial intelligence).
  5. Géron A. Hands-on machine learning with Scikit-Learn, Keras and TensorFlow: concepts, tools, and techniques to build intelligent systems. Third edition. Beijing: O’Reilly Media, Inc; 2023. 834 p.
  6. Street WN, Wolberg WH, Mangasarian OL. Nuclear feature extraction for breast tumor diagnosis. In: Acharya RS, Goldgof DB, editors. San Jose, CA; 1993 [cited 2024 Nov 14]. p. 861–70. Available from: http://proceedings. spiedigitallibrary.org/proceeding.aspx?articleid=1008972
  7. Hendriks MP, Verbeek XAAM, van Manen JG, et al. Clinical decision trees support systematic evaluation of multidisciplinary team recommendations. Breast Cancer Res Treat 2020; 183(2): 355–363.
  8. Hruška J. Visualization of hidden layers in convolutional neural networks [Internet]. Masarykova univerzita, Fakulta informatiky; 2022. Available from: https://is.muni.cz/auth/ th/huq0h/#paneltext
  9. Khened M, Kori A, Rajkumar H, Krishnamurthi G, Srinivasan B. A generalized deep learning framework for whole-slide image segmentation and analysis. Sci Rep 2021;11(1): 11579.
  10. Amerikanos P, Maglogiannis I. Image Analysis in Digital Pathology Utilizing Machine Learning and Deep Neural Networks. JPM 2022; 12(9): 1444.
  11. Xu J, Wang A, Wang Y, et al. AICellCounter: A Machine Learning-Based Automated Cell Counting Tool Requiring Only One Image for Training. Neurosci Bull 2023; 39(1): 83–88.
  12. Pocevičiūtė M, Eilertsen G, Lundström C. Unsupervised anomaly detection in digital pathology using GANs [Internet]. arXiv; 2021 [cited 2024 Nov 15]. Available from: https:// arxiv.org/abs/2103.08945
  13. Pozzi M, Noei S, Robbi E, et al. Generating synthetic data in digital pathology through diffusion models: a multifaceted approach to evaluation [Internet]. Pathology; 2023 [cited 2024 Nov 15]. Available from: http://medrxiv. org/lookup/doi/10.1101/2023.11.21.23298808
  14. Serafin R, Xie W, Glaser AK, Liu JTC. FalseColor-Python: A rapid intensity-leveling and digital-staining package for fluorescence-based slide-free digital pathology. Lin JCW editor. PLoS ONE 2020; 15(10): e0233198.
  15. Dubey A, Jauhri A, Pandey A, et al. The Llama 3 Herd of Models [Internet]. arXiv; 2024 [cited 2024 Nov 14]. Available from: http:// arxiv.org/abs/2407.21783
  16. Nguyen AT, Vuong TTL, Kwak JT. Towards a Text-Based Quantitative and Explainable Histopathology Image Analysis. In: Linguraru MG, Dou Q, Feragen A, et al., editors. Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 [Internet]. Cham: Springer Nature Switzerland; 2024 [cited 2024 Nov 14]. p. 514–524. (Lecture Notes in Computer Science; vol. 15004). Available from: https://link.springer.com/10.1007/9783-031-72083-3_48
  17. Omar M, Ullanat V, Loda M, Marchionni L, Umeton R. ChatGPT for digital pathology research. Lancet Digit Health 2024; 6(8): e595– 600.
  18. Waqas A, Naveed J, Shahnawaz W, Asghar S, Bui MM, Rasool G. Digital pathology and multimodal learning on oncology data. BJR|Artificial Intelligence 2024; 1(1): ubae014.
  19. Shafi S, Parwani AV. Artificial intelligence in diagnostic pathology. Diagn Pathol 2023; 18(1): 109.
  20. Moxley-Wyles B, Colling R. Artificial intelligence and digital pathology: where are we now and what are the implementation barriers? Diagnostic Histopathology 2024; 30(11): 597–603.
  21. Wulczyn E, Steiner DF, Moran M, et al. Interpretable survival prediction for colorectal cancer using deep learning. npj Digit Med 2021; 4(1): 71.
  22. Bankhead P, Loughrey MB, Fernández JA, et al. QuPath: Open source software for digital pathology image analysis. Sci Rep 2017; 7(1): 16878.
  23. Marée R, Rollus L, Stévens B, et al. Collaborative analysis of multi-gigapixel imaging data using Cytomine. Bioinformatics 2016; 32(9): 1395–1401.
  24. Horák J, Furmanová K, Kozlíková B, et al. xOpat: eXplainable Open Pathology Analysis Tool. Computer Graphics Forum 2023; 42(3): 63–73.
  25. Holub P, Müller H, Bíl T, et al. Privacy risks of whole-slide image sharing in digital pathology. Nat Commun 2023; 14(1): 2577.
  26. Pantanowitz L, Quiroga-Garza GM, Bien 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. The Lancet Digital Health 2020; 2(8): e407–416.
  27. Rong Y, Leemann T, Nguyen TT, et al. Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations. IEEE Trans Pattern Anal Mach Intell 2024; 46(4): 2104–2122.
  28. Mersha M, Lam K, Wood J, AlShami AK, Kalita J. Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction. Neurocomputing 2024; 599: 128111.
  29. Gallo M, Krajňanský V, Nenutil R, Holub P, Brázdil T. Shedding light on the black box of a neural network used to detect prostate cancer in whole slide images by occlusion-based explainability. New Biotechnology 2023; 78: 52–67.
  1. Xu H, Usuyama N, Bagga J, et al. A wholeslide foundation model for digital pathology from real-world data. Nature 2024; 630(8015): 181–188.
  2. Juyal D, Padigela H, Shah C, et al. PLUTO: Pathology-Universal Transformer [Internet]. arXiv; 2024 [cited 2024 Dec 6]. Available from: http://arxiv.org/abs/2405.07905
  3. Chen RJ, Ding T, Lu MY, et al. Towards a general-purpose foundation model for computational pathology. Nat Med 2024; 30(3): 850–862.
  4. Filiot A, Jacob P, Kain AM, Saillard C. Phikon-v2, A large and public feature extractor for biomarker prediction [Internet]. arXiv; 2024 [cited 2024 Dec 6]. Available from: http://arxiv.org/abs/2409.09173
  5. Zimmermann E, Vorontsov E, Viret J, et al. Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology [Internet]. arXiv; 2024 [cited 2024 Nov 19]. Available from: http://arxiv.org/abs/2408.00738
  6. Lu MY, Chen B, Williamson DFK, et al. A multimodal generative AI copilot for human pathology. Nature 2024; 634(8033): 466–473.
Labels
Anatomical pathology Forensic medical examiner Toxicology
EDITORIAL
INTERVIEW
MONITOR aneb nemělo by vám uniknout, že...
Integration of digital pathology workflow in the anatomic pathology laboratory
Diagnostic Benefits and Potential Applications of Micro-Computed Tomography in the Histopathological Analysis of Biopsy Samples
The way to the diagnosis of alveolar proteinosis: what is decisive?
POKYNY AUTORŮM
Article was published in

Czecho-Slovak Pathology

Issue 1
2025 Issue 1
Most read in this issue
Login
Forgotten password

Enter the email address that you registered with. We will send you instructions on how to set a new password.

Login

Don‘t have an account?  Create new account

#ADS_BOTTOM_SCRIPTS#