BIOMEDICAL IMAGE TEXTURE ANALYSIS SYSTEM
- Authors: Polyakov E.V.1, Dmitrieva V.V.1
-
Affiliations:
- National Research Nuclear University MEPhI
- Issue: No 2 (2025)
- Pages: 85-94
- Section: MODELS, SYSTEMS, MECHANISMS IN THE TECHNIQUE
- URL: https://journal-vniispk.ru/2227-8486/article/view/307555
- DOI: https://doi.org/10.21685/2227-8486-2025-2-7
- ID: 307555
Cite item
Full Text
Abstract
Background. In today's healthcare environment, there is an increasing need for efficient methods to analyze biomedical images for disease diagnosis. The present study aims to develop a biomedical image texture analysis system that uses various approaches to detect structural differences between objects. Materials and methods. In this work, local pixel distributions, Fourier transform, and fractal analysis methods are applied. A random forest classifier and dimensionality reduction and clustering methods implemented in the Scikit-learn library are used to evaluate the informativeness of texture features. Experimental data include bone marrow cell images, CT scans, and skin neoplasms. Results. Experimental results show that features based on spatial adjacency matrix and Fourier transform are the most informative for classifying blood and bone marrow cell images. For CT images and skin neoplasms, effective texture features are also identified, achieving f1 metrics as high as 0.93. Conclusions. The developed system enables efficient texture analysis of biomedical images and provides tools for automated evaluation of tumor features, which can significantly improve diagnostic accuracy. Further research will focus on extending the functionality of the system and improving data visualization methods.
About the authors
Evgeny V. Polyakov
National Research Nuclear University MEPhI
Author for correspondence.
Email: EVPolyakov@mephi.ru
Candidate of technical sciences, associate professor of the subdepartment of medical physics
(Moscow Engineering Physics Institute) (31 Kashirskoe shosse, Moscow, Russia)Valentina V. Dmitrieva
National Research Nuclear University MEPhI
Email: VVdmitriyeva@mephi.ru
Candidate of technical sciences, associate professor of the sub-department of electrophysical systems
(Moscow Engineering Physics Institute) (31 Kashirskoe shosse, Moscow, Russia)References
- Jiang X., Hu Z., Wang S., Zhang Y. Deep learning for medical image-based cancer diagnosis. Cancers. 2023;15(14):3608.
- Fanous M.J., Pillar N., Ozcan A. Digital staining facilitates biomedical microscopy. Frontiers in Bioinformatics. 2023;3:1243663.
- Tavakoli S., Ghaffari A., Kouzehkanan Z.M., Hosseini R. New segmentation and feature extraction algorithm for classification of white blood cells in peripheral smear images. Scientific Reports. 2021;11(1):19428.
- Ryu D., Kim J., Lim D. J. et al. Label-free white blood cell classification using refractive index tomography and deep learning. BME frontiers. 2021.
- Mollazade K. et al. Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging. Computers and electronics in agriculture. 2013;98:34–45.
- Tang X., Stewart W.K. Optical and sonar image classification: wavelet packet transform vs Fourier transform. Computer vision and image understanding. 2000;79(1):25–46.
- Abdesselam A. Texture image retrieval using Fourier transform. Proc. Int. Conf. Commun., Comput. Power (ICCCP’09). 2009.
- Gibson D., Gaydecki P.A. Definition and application of a fourier domain texture measure: applications to histological image segmentation. Computers in biology and medicine. 1995;25(6):551–557.
- Dincic M., Popovic T.B., Kojadinovic M. et al. Morphological, fractal, and textural features for the blood cell classification: The case of acute myeloid leukemia. European Biophysics Journal. 2021;50:1111–1127. doi: 10.1007/ s00249-021-01574-w
- Zhuang X., Meng Q. Local fuzzy fractal dimension and its application in medical image processing. Artificial Intelligence in Medicine. 2004;32(1):29–36.
- Metze K., Adam R., Florindo J.B. The fractal dimension of chromatin-a potential molecular marker for carcinogenesis, tumor progression and prognosis. Expert review of molecular diagnostics. 2019;19(4):299–312.
- Costa A.F., Humpire-Mamani G., Traina A.J.M. An efficient algorithm for fractal analysis of textures. 25th SIBGRAPI conference on graphics, patterns and images. 2012:39–46.
- Costa A.F., Tekli J., Traina A.J.M. Fast fractal stack: fractal analysis of computed tomography scans of the lung. Proceedings of the 2011 international ACM work-shop on Medical multimedia analysis and retrieval. 2011:13–18.
- A multiresolution clinical decision support system based on fractal model design for classification of histological brain tumours. Computerized Medical Imaging and Graphics. 2015;41:67–79.
- Molnar C. Interpretable machine learning. Lulu. Com. 2020.
- Pedregosa et. al. Scikit-learn: Machine Learning in Python. JMLR 12. 2011:2825–2830.
- Rudin C. et al. Interpretable machine learning: Fundamental principles and 10 grand challenges. Statistic Surveys. 2022;16:1–85.
- Van der Maaten L., Hinton G. Visualising Data using t-SNE. J. of machine learning research. 2008;9(11).
- Mayerhoefer M.E. et al. Introduction to radiomics. J. of Nuclear Medicine. 2020;61(4):488–495.
- Ursprung S. et al. Radiomics of computed tomography and magnetic resonance imaging in renal cell carcinoma–a systematic review and meta-analysis. European radiology. 2020;30:3558–3566.
- Gorduladze D.N., Sirota E.S., Rapoport L.M. [et al.]. Possibilities of textural analysis of radiation imaging methods in the diagnosis of kidney parenchyma formations. Onkourologiya = Oncourology. 2021;(4):129–135. (In Russ.)
- Gorduladze D., Sirota E., Rapoport L. [et al.]. Prospects of texture analysis in radiological imaging for diagnosis of renal parenchyma tumor. Cancer Urology. 2021;(17):129– 135. doi: 10.17650/1726-9776-2021-17-4-129-135
- Manaev A.V., Trukhin A.A., Zakharova S.M. et al. Textural Statistical Features of Ultrasound Imaging of Thyroid Nodules in the Assessment of Malignancy Status. Physics of Atomic Nuclei. 2023;86(11):2500–2506.
- Dmitrieva V.V., Tupitsyn N.N., Polyakov E.V [et al.]. A web-based medical information system for the diagnosis of acute lymphoblastic leukemia and minimal residual disease. Bezopasnost' informatsionnykh tekhnologiy = Information technology security. 2021;28(3):44–45. (In Russ.). doi: 10.26583/bit.2021.3.03
- Selchuk V.Y., Rodionova O.V., Sukhova O.G. et al. Methods of formation of the knowledge base in the diagnosis of melanoma. Journal of Physics: Conference Series. 2017;798(1):012137.
- Fazeli S., Samiei A., Lee T.D., Sarrafzadeh M. Beyond Labels: Visual Representations for Bone Marrow Cell Morphology Recognition. Computer Vision and Pattern Recognition. 19.05.2022. doi: 10.48550/arXiv.2205.09880
Supplementary files
