Authors
Gorbunova A. V.
Student, Faculty of Biotechnology1
Shmakova Y. V.
Student, Faculty of Pharmacy2
Kalugina O. F.
Student, Faculty of Medicine3
Prokhorov M. V.
Student, Faculty of Pharmacy4
Bobrov A. I.
Student, Institute for Clinical Medicine5
Koshechkin K. A.
Doctor of Pharmacy, Professor, Chair for Information and Internet Technologies5
1 - Lomonosov Moscow State University, Moscow, Russian Federation
2 - Saint Petersburg State Chemical and Pharmaceutical University, St. Petersburg, Russian Federation
3 - Yaroslavl State Medical University, Yaroslavl, Russian Federation
4 - Voronezh State University, Voronezh, Russian Federation
5 - I. M. Sechenov First Moscow State Medical University (Sechenov University), Moscow, Russian Federation
Corresponding author
Aleksandra V. Gorbunova; e-mail: gorbunova.av2002@yandex.ru
Conflict of interest
None declared.
Funding
The study had no sponsorship.
Abstract
Introduction. The article discusses the problem of using laboratory animals in preclinical research and, as a solution to this problem, the use of modern technologies like artificial intelligence. The aim of the work is to study the application of computer vision methods and large language models for preclinical research. Discussion. Nowadays scientists all over the world are actively trying to replace animal models in preclinical research with more modern solutions. Artificial intelligence plays an important role in this process. It allows us to make research faster and also to improve the quality of experiments, and therefore, it can lead to the decrease in the number of tests, that may turn out to be unjustified and, in most cases, fatal to animals. The use of AI in preclinical research makes it possible to conduct more accurate experiments, reduce the likelihood of unsuccessful research and increase the reliability of the results. It also allows us to reduce the number of animals which are used in experiments, which is one of the main aspects of bioethics. It is possible to reduce the suffering of animals and improve their protection from the negative effects of experiments by replacing them with computer models and AI-based virtual systems. Conclusions. The use of artificial intelligence in preclinical studies is one of the best ways to develop more ethical, accurate and effective scientific methods.
Key words
artificial intelligence, preclinical research, machine learning
DOI
References
1. Animals Used in Research. Animal Legal Defence Fund. Available at: https://aldf.org/focus_area/animals-used-in-research/ Accessed: 09.04.2024.
2. Lab to algorithm: AI's role in minimising animal testing. Deeper insights. Available at: https://deeperinsights.com/ai-blog/lab-to-algorithm-ai-role-in-minimising-animal-testing#:~:text=Replacing%20animal%20testing%20with%20AI,and%20prioritise%20substances%20more%20efficiently Accessed: 09.04.2024.
3. Goryachkin B.S., Kitov M.A. Komp'yuternoe zrenie. [Computer Vision.] E-Scio 2020; (9): 317-345. (In Russ.)
4. Poschkamp B., Bekeschus S. Convolutional neuronal network for identifying single-cell-platelet–platelet-aggregates in human whole blood using imaging flow cytometry. Cytometry A. 2024; 105(5): 356-367, doi: 10.1002/cyto.a.24829
5. Markovic S., Li B., Pera V., Sznaier M., Camps O., Niedre M. A computer vision approach to rare cell in vivo fluorescence flow cytometry. Cytometry A. 2013; 83(12): 1113-1123, doi: 10.1002/cyto.a.22397
6. Pennati F., Belenkov S., Buccardi M., Ferrini E., Sverzellati N., Villetti G., Aliverti A., Stellari F.F. Multiphase micro-computed tomography reconstructions provide dynamic respiratory function in a mouse lung fibrosis model. iScience 2024; 27(3): 109262, doi: 10.1016/j.isci.2024.109262
7. Vincenzi E., Fantazzini A., Basso C., et al. A fully automated deep learning pipeline for micro-CT-imaging-based densitometry of lung fibrosis murine models. Respir Res 2022; 23(1): 308, doi: 10.1186/s12931-022-02236-x
8. Ji Y., Hwang G., Lee S.J., Lee K., Yoon H. A deep learning model for automated kidney calculi detection on non-contrast computed tomography scans in dogs. Frontiers in veterinary science 2023; 10: 1236579, doi: 10.3389/fvets.2023.1236579
9. Liu L., Cai B., Liu L., Zhuang X., Zhao Z., Huang X., Zhang J. Research on the morphological structure of partial fracture healing process in diabetic mice based on synchrotron radiation phase-contrast imaging computed tomography and deep learning. Bone Reports 2024; 20: 101743, doi: 10.1016/j.bonr.2024.101743
10. Mahmoodian N., Rezapourian M., Inamdar A.A., Kumar K., 1, Fachet M., Hoeschen C. Enabling Low-Dose In Vivo Benchtop X-ray Fluorescence Computed Tomography through Deep Learning-Based Denoising. J Imaging 2024; 10(6): 127, doi: 10.3390/jimaging10060127
11. Iizuka O., Kanavati F., Kato K., Rambeau M., Arihiro K., Tsuneki M. Deep Learning Models for Histopathological Classification of Gastric and Colonic Epithelial Tumours. Scientific Reports 2020: 10(1): 1504, doi: 10.1038/s41598-020-58467-9
12. Kather J.N., Pearson A.T., Halama N., et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nature Medicine 2019; 25(7): 1054-1056, doi: 10.1038/s41591-019-0462-y
13. Pereira T.D., Aldarondo D.E., Willmore L., Kislin M., Wang S.S.H., Murthy M., Shaevitz J.W. Fast animal pose estimation using deep neural networks. Nat. Methods 2019; 16(1): 117-125, doi: 10.1101/331181
14. Carreira M.J., Vila-Blanco N., Cabezas-Sainz P., Sánchez L. ZFTool: A Software for Automatic Quantification of Cancer Cell Mass Evolution in Zebrafish. Applied Sciences 2021; 11(16): 7721, doi: 10.3390/app11167721
15. Stefano A., Vernuccio F., Comelli A. Image Processing and Analysis for Preclinical and Clinical Applications. Applied Sciences 2022; 12(15): 7513, doi: 10.3390/app12157513
16. Khare S., Ho C., Kannan M., et al. 62 Applying machine vision to empower preclinical development of cell engager and adoptive cell therapeutics in patient-derived organoid models of solid tumors. Journal for ImmunoTherapy of Cancer 2021; 9, doi: 10.1136/jitc-2021-SITC2021.062
17. Guzman M., Geuther B., Sabnis G. Kumar V. Highly Accurate and Precise Determination of Mouse Mass Using Computer Vision. bioRxiv [Preprint] 2023:2023.12.30.573718, doi: 10.1101/2023.12.30.573718
18. Chien A., Tang H., Jagessar B., Chang K.-W., Peng N., Nael K., Salamon N. AI-Assisted Summarization of Radiologic Reports: Evaluating GPT3davinci, BARTcnn, LongT5booksum, LEDbooksum, LEDlegal, and LEDclinical American Journal of Neuroradiology 2024; 45(2): 244-248, doi: 10.3174/ajnr.A8102
19. Van Veen D., Van Uden C., Blankemeier L., et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat Med 2024; 30(4): 1134-1142, doi: 10.1038/s41591-024-02855-5
20. Tie X., Shin M., Pirasteh A., et al. Personalized Impression Generation for PET Reports Using Large Language Models. J Imaging Inform. Med. 2024; 37(2): 471-488, doi: 10.1007/s10278-024-00985-3
21. Wu H.Y., Zhang J., Ive J., Li T., Gupta V., Chen B., Guo Y. Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint. arXiv preprint 2022; arXiv:2205.12368, doi: 10.48550/arXiv.2205.12368
