Detection of key points on images for creatung digital twins of medical and biological objects


  • Vladyslav Peschanskii
  • Yevgeniya Sulema



3D visualization, digital twins, medical software.


The paper presents an analysis of optimal tools for creating a digital twin of human or-gans (on the example of otolaryngology) based on streaming video data received in real time from the camera of a medical device. Two main methods were studied: algorithmic recon-struction and the use of a neural network. The comparison of methods was performed accord-ing to the following criteria: efficiency, accuracy, speed of reaction and practicality of appli-cation in the medical environment. Special attention is paid to approaches based on neural networks due to their high adaptability, accuracy and ability to efficiently process noisy and incomplete data. The main advantages and features of this method in the context of medical application are determined. The results of the study confirm the high potential of neural net-works in creating accurate digital models of internal organs, which opens up new perspec-tives for the development of software for the creation of digital twins of medical and biologi-cal objects.


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

Zhen, W. and Luan, L., 2021, February. Physical World to Virtual Reality–Motion Capture Technology in Dance Creation. In Journal of Physics: Conference Series (Vol. 1828, No. 1, p. 012097). IOP Publishing.

Peng, K., Chen, X., Zhou, D. and Liu, Y., 2009, December. 3D reconstruction based on SIFT and Harris feature points. In 2009 IEEE international conference on robotics and biomimetics (ROBIO) (pp. 960-964). IEEE.

Kamel Boulos, M.N. and Zhang, P., 2021. Digital twins: from personalised medicine to precision public health. Journal of personalized medicine, 11(8), p.745.

Sipiran, I. and Bustos, B., 2011. Harris 3D: a robust extension of the Harris operator for interest point detection on 3D meshes. The Visual Computer, 27, pp.963-976.

Bradski, G. and Kaehler, A., 2000. OpenCV. Dr. Dobb’s journal of software tools, 3(2).

Pang, B., Nijkamp, E. and Wu, Y.N., 2020. Deep learning with tensorflow: A review. Journal of Educational and Behavioral Statistics, 45(2), pp.227-248.