Methods of creating digital twins of medico-biological objects using otolaryngology as an example

Authors

  • Vladyslav Peschanskii
  • Yevgeniya Sulema

DOI:

https://doi.org/10.34185/1562-9945-5-154-2024-14

Keywords:

software engineering, software, digital twin, 3D modeling, data synchronization, videolaryngostroboscopy, acoustic analysis, vocal apparatus biomechanics, personalized medicine.

Abstract

The paper presents an in-depth analysis on the most suitable tools and techniques for the formulation of a digital twin, specifically focusing on internal organs. The larynx, a pivotal organ in the human respiratory and vocal systems, is highlighted as the primary case study. The basis of this digital twin generation is the video stream sourced directly from a medical device's onboard camera, which provides real-time visual data of the organ. Two methodologies are put under the microscope in this study: one that harnesses the power of neural networks and another grounded in algorithmic reconstruction using crucial points or markers within the video feed. Each method is evaluated against a set of well-defined criteria. These benchmarks include the efficiency of the tool, the accuracy of the digital representation it produces, the speed of its response, and its overall ap-plicability within the confines of a typical medical environment. After a rigorous comparative analysis, the research gravitates towards neural network-based approaches, spotlighting them due to several standout features. Neural networks, as elucidated in the paper, exhibit remarkable adaptability, ensuring that they can be tailored to diverse medical scenarios. Their accuracy, even when confronted with "noisy" or fragmented data, is another standout feature. This is paramount, especially in real-world scenarios where the data might not always be pristine. The ability of neural networks to sieve through such data and still produce ac-curate digital representations is a significant advancement in the field. In conclusion, by affirming the superior potential of neural networks in crafting precise digi-tal avatars of internal organs, the research not only provides a blueprint for enhanced diagnostic and therapeutic methodologies but also underscores a paradigm shift in how medical professionals can leverage technology for better patient outcomes. This synthesis of medical expertise and cut-ting-edge technology is poised to redefine the boundaries of medical science, heralding a new era of advanced diagnostics and treatment modalities.

References

Yanase, J. and Triantaphyllou, E., 2019. A systematic survey of computer-aided diagnosis in medicine: Past and present developments. Expert Systems with Applications, 138, p.112821.

Lynn, L.A., 2019. Artificial intelligence systems for complex decision-making in acute care medicine: a review. Patient safety in Surgery, 13(1), p.6.

Bailly, L., Cochereau, T., Orgéas, L., Henrich Bernardoni, N., Rolland du Roscoat, S., McLeer-Florin, A., Robert, Y., Laval, X., Laurencin, T., Chaffanjon, P. and Fayard, B., 2018. 3D multiscale imaging of human vocal folds using synchrotron X-ray microtomography in phase retrieval mode. Scientific reports, 8(1), p.14003.

Woo, P., 2021. Stroboscopy and high-speed imaging of the vocal function. Plural publishing.

Soltanisehat, L., Alizadeh, R., Hao, H. and Choo, K.K.R., 2020. Technical, temporal, and spatial research challenges and opportunities in blockchain-based healthcare: A systematic literature re-view. IEEE Transactions on Engineering Management, 70(1), pp.353-368.

Steneker, M., 2016. Towards an empirical validation of the TIOBE Quality Indicator (Doctoral dissertation, Eindhoven University of Technology).

White, A.C. and Carding, P., 2022. Pre-and postoperative voice therapy for benign vocal fold lesions: factors influencing a complex intervention. Journal of Voice, 36(1), pp.59-67.

Rast, C., Unteregger, F., Honegger, F., Zwicky, S. and Storck, C., 2023. An Old Myth: Predic-tion of the Correct Singing Voice Classification. True or not?. Journal of Voice, 37(6), pp.968-e13.

Wu, X., Qu, P., Wang, S., Xie, L. and Dong, J., 2021. Extend the FFmpeg framework to analyze media content. arXiv preprint arXiv:2103.03539.

Demidenko, O.M., Aksionova, N.A., Varuyeu, A.V. and Kucharav, A.I., 2021, November. 3D-modeling of Augmented Reality objects using Shi-Tomasi corner detection algorithms. In Journal of Physics: Conference Series (Vol. 2091, No. 1, p. 012058). IOP Publishing.

Sun, Z., Sarma, P., Sethares, W. and Liang, Y., 2020, April. Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis. In Proceed-ings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 05, pp. 8992-8999).

Downloads

Published

2024-10-03