A User-friendly Machine Learning Approach for Cardiac Structures Assessment

Overview

Journal Front Cardiovasc Med

Specialty Cardiology & Vascular Diseases

Date 2024 Jul 22

PMID 39036503

Authors

Atilla Orhan

Hakan Akbayrak

Omer Faruk Cicek

Ismail Harmankaya

Husamettin Vatansev

Affiliations

Soon will be listed here.

Abstract

Background: Machine learning is increasingly being used to diagnose and treat various diseases, including cardiovascular diseases. Automatic image analysis can expedite tissue analysis and save time. However, using machine learning is limited among researchers due to the requirement of technical expertise. By offering extensible features through plugins and scripts, machine-learning platforms make these techniques more accessible to researchers with limited programming knowledge. The misuse of anabolic-androgenic steroids is prevalent, particularly among athletes and bodybuilders, and there is strong evidence of their detrimental effects on ventricular myocardial capillaries and muscle cells. However, most studies rely on qualitative data, which can lead to bias and limited reliability. We present a user-friendly approach using machine learning algorithms to measure the effects of exercise and anabolic-androgenic steroids on cardiac ventricular capillaries and myocytes in an experimental animal model.

Method: Male Wistar rats were divided into four groups ( = 28): control, exercise-only, anabolic-androgenic steroid-alone, and exercise with anabolic-androgenic steroid. Histopathological analysis of heart tissue was conducted, with images processed and analyzed using the Trainable Weka Segmentation plugin in Fiji software. Machine learning classifiers were trained to segment capillary and myocyte nuclei structures, enabling quantitative morphological measurements.

Results: Exercise significantly increased capillary density compared to other groups. However, in the exercise + anabolic-androgenic steroid group, steroid use counteracted this effect. Anabolic-androgenic steroid alone did not significantly impact capillary density compared to the control group. Additionally, the exercise group had a significantly shorter intercapillary distance than all other groups. Again, using steroids in the exercise + anabolic-androgenic steroid group diminished this positive effect.

Conclusion: Despite limited programming skills, researchers can use artificial intelligence techniques to investigate the adverse effects of anabolic steroids on the heart's vascular network and muscle cells. By employing accessible tools like machine learning algorithms and image processing software, histopathological images of capillary and myocyte structures in heart tissues can be analyzed.

References

Mbiki S, McClendon J, Alexander-Bryant A, Gilmore J . Classifying changes in LN-18 glial cell morphology: a supervised machine learning approach to analyzing cell microscopy data via FIJI and WEKA. Med Biol Eng Comput. 2020; 58(7):1419-1430. DOI: 10.1007/s11517-020-02177-x. View

Opstad I, Godtliebsen G, Ahluwalia B, Myrmel T, Agarwal K, Birgisdottir A . Mitochondrial dynamics and quantification of mitochondria-derived vesicles in cardiomyoblasts using structured illumination microscopy. J Biophotonics. 2021; 15(2):e202100305. DOI: 10.1002/jbio.202100305. View

Basaria S, Wahlstrom J, Dobs A . Clinical review 138: Anabolic-androgenic steroid therapy in the treatment of chronic diseases. J Clin Endocrinol Metab. 2001; 86(11):5108-17. DOI: 10.1210/jcem.86.11.7983. View

Ikeda T, Okano S, Hashimoto N, Kimura K, Kudo K, Tsutsumi R . Histomorphological investigation of intrahepatic connective tissue for surgical anatomy based on modern computer imaging analysis. J Hepatobiliary Pancreat Sci. 2020; 28(1):76-85. PMC: 7891672. DOI: 10.1002/jhbp.753. View

Deter H, Dies M, Cameron C, Butzin N, Buceta J . A Cell Segmentation/Tracking Tool Based on Machine Learning. Methods Mol Biol. 2019; 2040:399-422. DOI: 10.1007/978-1-4939-9686-5_19. View

Subudhi A, Rajendra Acharya U, Dash M, Jena S, Sabut S . Automated approach for detection of ischemic stroke using Delaunay Triangulation in brain MRI images. Comput Biol Med. 2018; 103:116-129. DOI: 10.1016/j.compbiomed.2018.10.016. View

Schindelin J, Arganda-Carreras I, Frise E, Kaynig V, Longair M, Pietzsch T . Fiji: an open-source platform for biological-image analysis. Nat Methods. 2012; 9(7):676-82. PMC: 3855844. DOI: 10.1038/nmeth.2019. View

Lusetti M, Licata M, Silingardi E, Reggiani Bonetti L, Palmiere C . Pathological changes in anabolic androgenic steroid users. J Forensic Leg Med. 2015; 33:101-4. DOI: 10.1016/j.jflm.2015.04.014. View

Goncalves L, de Souza R, Maifrino L, Caperuto E, Carbone P, Rodrigues B . Resistance exercise and testosterone treatment alters the proportion of numerical density of capillaries of the left ventricle of aging Wistar rats. Aging Male. 2014; 17(4):243-7. DOI: 10.3109/13685538.2014.919252. View

10.

Schneider C, Rasband W, Eliceiri K . NIH Image to ImageJ: 25 years of image analysis. Nat Methods. 2012; 9(7):671-5. PMC: 5554542. DOI: 10.1038/nmeth.2089. View

11.

Zhang K, Tuffy C, Mertz J, Quillen S, Wechsler L, Quigley H . Role of the Internal Limiting Membrane in Structural Engraftment and Topographic Spacing of Transplanted Human Stem Cell-Derived Retinal Ganglion Cells. Stem Cell Reports. 2020; 16(1):149-167. PMC: 7897583. DOI: 10.1016/j.stemcr.2020.12.001. View

12.

Tagarakis C, Bloch W, Hartmann G, Hollmann W, Addicks K . Testosterone-propionate impairs the response of the cardiac capillary bed to exercise. Med Sci Sports Exerc. 2000; 32(5):946-53. DOI: 10.1097/00005768-200005000-00011. View

13.

Moran-Sanchez J, Santisteban-Espejo A, Martin-Piedra M, Perez-Requena J, Garcia-Rojo M . Translational Applications of Artificial Intelligence and Machine Learning for Diagnostic Pathology in Lymphoid Neoplasms: A Comprehensive and Evolutive Analysis. Biomolecules. 2021; 11(6). PMC: 8227233. DOI: 10.3390/biom11060793. View

14.

Hydock D, Lien C, Schneider C, Hayward R . Effects of voluntary wheel running on cardiac function and myosin heavy chain in chemically gonadectomized rats. Am J Physiol Heart Circ Physiol. 2007; 293(6):H3254-64. DOI: 10.1152/ajpheart.00801.2007. View

15.

Tagarakis C, Bloch W, Hartmann G, Hollmann W, Addicks K . Anabolic steroids impair the exercise-induced growth of the cardiac capillary bed. Int J Sports Med. 2000; 21(6):412-8. DOI: 10.1055/s-2000-3835. View

16.

Pereira F, Moraes R, Tibirica E, Nobrega A . Interval and continuous exercise training produce similar increases in skeletal muscle and left ventricle microvascular density in rats. Biomed Res Int. 2013; 2013:752817. PMC: 3858873. DOI: 10.1155/2013/752817. View

17.

Caetano Dos Santos F, Michalek I, Laurila K, Kaukinen K, Hyttinen J, Lindfors K . Automatic classification of IgA endomysial antibody test for celiac disease: a new method deploying machine learning. Sci Rep. 2019; 9(1):9217. PMC: 6592927. DOI: 10.1038/s41598-019-45679-x. View

18.

Cui M, Zhang D . Artificial intelligence and computational pathology. Lab Invest. 2021; 101(4):412-422. PMC: 7811340. DOI: 10.1038/s41374-020-00514-0. View

19.

Henquell L, Odoroff C, HONIG C . Intercapillary distance and capillary reserve in hypertrophied rat hearts beating in situ. Circ Res. 1977; 41(3):400-8. DOI: 10.1161/01.res.41.3.400. View

20.

Arganda-Carreras I, Kaynig V, Rueden C, Eliceiri K, Schindelin J, Cardona A . Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification. Bioinformatics. 2017; 33(15):2424-2426. DOI: 10.1093/bioinformatics/btx180. View