Methods for morphological analysis in images of biological samples using artificial intelligence techniques

Authors

Keywords:

sickle cell disease, angiogenesis, morphology, classification, artificial intelligence

Abstract

Introduction: The morphological study of objects is applied in various contexts. Certain diseases or related processes can cause changes in cells, identifying these deformations is fundamental to making diagnoses and proposing treatments. This research focuses on two examples: sickle cell anemia, in which red blood cells take on a crescent shape, and angiogenesis, which is studied by in vitro cultures of endothelial cells from human umbilical cord veins. The morphology of these cells can be associated with the processes of cell migration and proliferation.

Objective: To propose and to evaluate new methods using artificial intelligence techniques to automatically perform cell morphological analysis in both types of biological samples.

Methods: Processing and analysis methods will be developed using own databases of both single cells and full field of view. Methods for segmentation, feature extraction and classification stages are proposed and evaluated, as well as two tools that define the practical contribution.

Results: Classification results are obtained that show equal or superior performance to the most relevant previous ones.

Conclusions: The methods and tools developed contribute to improve the diagnosis and the quality of life of patients.

Downloads

Download data is not yet available.

References

1. Paz Y, Herold S. Perspectivas recientes del análisis morfológico automatizado en eritrocitos. Rev. Cuba. Investig. Bioméd., 2021;suppl.1:40. Disponible en: http://scielo.sld.cu/scielo.php?pid=S0864-3002021000200014&script=sci_arttext&tlng=en

2. Escobedo M, Herold S, Ferreira L, Machado F, Monteiro E, Delgado W. Análisis morfológico de muestras de HUVEC utilizando funciones basadas en geometría integral. Rev. Cienc. Mat. 2016;30(2):79-86. Disponible en: https://revistas.uh.cu/rcm/article/view/8821

3. González M, Guerrero F, Herold S, Jaume A, Marrero P. Red Blood Cell Cluster Separation from Digital Images for use in Sickle Cell Disease. IEEE J Biomed Health. 2014;19(4):1514-25. Disponible en: https://doi.org/10.1109/JBHI.2014.2356402

4. Escobedo M, Herold S, Ferreira L, Delgado W, Machado F, Monteiro E. Clasificación morfológica de células endoteliales de venas del cordón umbilical humano en imágenes digitales de cultivos in vitro. Revista Medisan. 2017;22(2):123-31. Disponible en: http://scielo.sld.cu/scielo.php?pid=S1029-30192018000200002&script=sci_arttext&tlng=pt

5. Escobedo M, Herold S, Ferreira L, Machado F, Monteiro E, Delgado W. Clasificación morfológica usando descriptores elementales en imágenes digitales de muestras de HUVEC. Rev. Cienc. Mat. 2017;31(2):117-23. Disponible en: https://revistas.uh.cu/rcm/article/view/8845

6. Escobedo M, Herold S, Ferreira L, Machado F, Monteiro E, Delgado W. Clasificación morfológica de células endoteliales de venas de cordón umbilical humano (HUVEC) en imágenes digitales. Rev. Cuba. Cienc. Informat. 2018;12(1):1-13. Disponible en: http://scielo.sld.cu/scielo.php?pid=S2227-18992018000100001&script=sci_arttext

7. Escobedo M, Delgado W, Monteiro E, Ferreira L. Automatic Morphological Evaluation of Endothelial Cells Using Different Classification Methods. Proceedings IX Latin American Congress on Biomedical Engineering and XXVIII Brazilian Congress on Biomedical Engineering. CLAIB CBEB 2022; 2022 Oct 24-8; Brasil: IFMBE; 2024. 582-91 p. https://doi.org/10.1007/978-3-031-49404-8_56

8. Escobedo M, Delgado W, Jiménez J, Ferreira L. Deep Learning Models for Automatic Morphological Evaluation of Endothelial Cells. Proceedings XXIX Congreso Brasileño de Ingeniería Biomédica (CBEB); 2024 Sep 2-6; Ribeirão Preto-Brasil; 2024.

9. Grandales H, Soto Y, García S. Análisis de desempeño de segmentación sobre imágenes de muestras de sangre periférica. Orange Journal. 2021;3(6):21-33. Disponible en: https://doi.org/10.46502/issn.2710-995X/2021.6.03

10. Fernández K, Herold S, Fernández A, Escobedo M, Coello G, Marrero P. Estudio morfológico en muestras de sangre periférica. Proceedings V Latin American Congress on Biomedical Engineering CLAIB 2011; 2011 may. 16-21; La Habana, Cuba: Springer Berlin; 2013. 543-6 p. https://doi.org/10.1007/978-3-642-21198-0_139

11. Delgado W, Escobedo M, González M, Herold S, Jaume A, Mir A. Diagnosis support of sickle cell anemia by classifying red blood cell shape in peripheral blood images. Med Biol Eng Comput. 2020;58(6):1265-84. Disponible en: https://doi.org/10.1007/s11517-019-02085-9

12. Gual X, Herold S, Simó A. Shape description from generalized support functions. Pattern Recognit. Lett. 2013;34(6);619-26. Disponible en: https://doi.org/10.1016/j.patrec.2012.12.016

13. Gual X, Herold S, Simó A. Erythrocyte shape classification using integral-geometry-based methods. Med Biol Eng Comput. 2015;53:623-33. Disponible en: https://doi.org/10.1007/s11517-015-1267-x

14. Herold S, Fernandes L. New Methods for Morphological Erythrocytes Classification. Proceedings 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2019 Jul. 23-27; Berlin, Alemania; 2019. 4068-71 p. Disponible en: https://doi.org/10.1109/EMBC.2019.8857013

15. Paz Y, Herold S, Fernandes L, Díaz S. Automatic classification of erythrocytes using artificial neural networks and integral geometry-based functions. Proceedings 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI); 2020 nov. 7-10; Recife-Brasil: IEEE; 2020. 156-63 p. Disponible en: https://doi.org/10.1109/SIBGRAPI51738.2020.00029

16. Delgado W, González M, Herold S, Jaume A, Mir A. Erythrocytes morphological classification through HMM for sickle cell detection. Proceedings Articulated Motion and Deformable Objects: 9th International Conference AMDO; 2016 Jul. 13-15; Palma de Mallorca, España: Springer International Publishing; 2016.88-97 p. Disponible en: https://doi.org/10.1007/978-3-319-41778-3_9

17. Delgado W, Herold S, Escobedo M, Gonzalez M, Jaume A, Mir A, Ferreira L. Classification of Red Blood Cell Shapes Using a Sequential Learning Algorithm. Proceedings XXVII Brazilian Congress on Biomedical Engineering. CBEB 2020; 2020 Oct. 26-30; Brasil: IFMBE Proceedings; 2022. p. 2059-65. Disponible en: https://doi.org/10.1007/978-3-030-70601-2_301

18. Delgado W, Escobedo M, Pascual R. Uso del aprendizaje profundo para identificar formas en eritrocitos. Proceedings XVIII Congreso Internacional COMPUMATG; 2021 Dic. 15; Bayamo-Cuba; 2021.

19. Gual X, Herold S, Simó A. Geometric analysis of planar shapes with applications to cell deformations. Image Anal. Stereol. 2015:34:171-82. Disponible en: https://doi.org/10.5566/ias.1151

20. Epifanio I, Gual X, Herold S. Morphological analysis of cells by means of an elastic metric in the shape space. Image Anal. Stereol. 2020;39:281-91. Disponible en: https://doi.org/10.5566/ias.2183

21. Machado C, Escobedo M, Nigro C, Vaz S, Prado C, Augusto D, Palacios F, Ferreira L. Digital Image Processing Assessment of the Differential in vitro Antiangiogenic Effects of Dimeric and Monomeric Beta2-Glycoprotein I. J Cytol Histol. 2013;4(4):1-8. Disponible en: https://doi.org/10.4172/2157-7099.1000187

Downloads

Published

2025-09-21

How to Cite

Escobedo Nicot, M. M., Herold García, S., Delgado Font, W. E., Ferreira Gomes, L., Jaume i Capó, A., González Hidalgo, M., … Paz Soto, Y. (2025). Methods for morphological analysis in images of biological samples using artificial intelligence techniques. Anales De La Academia De Ciencias De Cuba, 15(3), e3184. Retrieved from https://revistaccuba.sld.cu/index.php/revacc/article/view/3184

Issue

Vol. 15 No. 3: Julio-Septiembre 2025. Número en Progreso

Section

Technical Sciences

License

Copyright (c) 2025 Miriela Milagros Escobedo Nicot, Silena Herold García, Wilkie Ernesto Delgado Font, Ligia Ferreira Gomes, Antoni Jaume i Capó, Manuel González Hidalgo, Ximo Gual-Arnau, Amelia Simó Vidal, Yaima Paz Soto

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The journal Anales de la Academia de Ciencias de Cuba protects copyright, and operates with a Creative Commons License 4.0 (Creative Commons Attribution-NonCommercial License 4.0). By publishing in it, authors allow themselves to copy, reproduce, distribute, publicly communicate their work and generate derivative works, as long as the original author is cited and acknowledged. They do not allow, however, the use of the original work for commercial or lucrative purposes.

The authors authorize the publication of their writings, retaining the authorship rights, and assigning and transferring to the magazine all the rights protected by the intellectual property laws that govern in Cuba, which imply editing to disseminate the work.

Authors may establish additional agreements for the non-exclusive distribution of the version of the work published in the journal (for example, placing it in an institutional repository or publishing it in a book), with recognition of having been first published in this journal.

To learn more, see https://creativecommons.org