The aim of this work was to test microwave brain stroke detection and classification using support vector machines (SVMs). We tested how the nature and variability of training data and system parameters impact the achieved classification accuracy. Using experimentally verified numerical models, a large database of synthetic training and test data was created. The models consist of an antenna array surrounding reconfigurable geometrically and dielectrically realistic human head phantoms with virtually inserted strokes of arbitrary size, and different dielectric parameters in different positions. The generated synthetic data sets were used to test four different hypotheses, regarding the appropriate parameters of the training dataset, the appropriate frequency range and the number of frequency points, as well as the level of subject variability to reach the highest SVM classification accuracy. The results indicate that the SVM algorithm is able to detect the presence of the stroke and classify it (i.e., ischemic or hemorrhagic) even when trained with single-frequency data. Moreover, it is shown that data of subjects with smaller strokes appear to be the most suitable for training accurate SVM predictors with high generalization capabilities. Finally, the datasets created for this study are made available to the community for testing and developing their own algorithms.

Department of Biomedical Technology Faculty of Biomedical Engineering Czech Technical University Prague 166 00 Prague Czech Republic

ELEDIA Research Center DICAM Department of Civil Environmental and Mechanical Engineering Via Mesiano 77 38123 Trento Italy

See more in PubMed

Meaney P.M. Microwave Imaging and Emerging Applications. Int. J. Biomed. Imaging. 2012;2012:252093. doi: 10.1155/2012/252093. PubMed DOI PMC

Semenov S., Huynh T., Williams T., Nicholson B., Vasilenko A. Dielectric properties of brain tissue at 1 GHz in acute ischemic stroke: Experimental study on swine. Bioelectromagnetics. 2017;38:158–163. doi: 10.1002/bem.22024. PubMed DOI

Salucci M., Arrebola M., Shan T., Li M. Artificial Intelligence: New Frontiers in Real-Time Inverse Scattering and Electromagnetic Imaging. IEEE Trans. Antennas Propag. 2022;70:6349–6364. doi: 10.1109/TAP.2022.3177556. DOI

Massa A., Oliveri G., Salucci M., Anselmi N., Rocca P. Learning-by-examples techniques as applied to electromagnetics. J. Electromagn. Waves Appl. 2018;32:516–541. doi: 10.1080/09205071.2017.1402713. DOI

Oliveri G., Rocca P., Massa A. SVM for Electromagnetics: State-of-art, potentialities, and trends; Proceedings of the 2012 IEEE International Symposium on Antennas and Propagation; Chicago, IL, USA. 8–14 July 2012; pp. 1–2.

Persson M., Fhager A., Trefná H.D., Yu Y., McKelvey T., Pegenius G., Karlsson J.E., Elam M. Microwave-Based Stroke Diagnosis Making Global Prehospital Thrombolytic Treatment Possible. IEEE Trans. Biomed. Eng. 2014;61:2806–2817. doi: 10.1109/TBME.2014.2330554. PubMed DOI

Zhu G., Bialkowski A., Guo L., Mohammed B., Abbosh A. Stroke Classification in Simulated Electromagnetic Imaging Using Graph Approaches. IEEE J. Electromagn. RF Microw. Med. Biol. 2021;5:46–53. doi: 10.1109/JERM.2020.2995329. DOI

Li J., Zhu G., Xi M. Automating Stroke Subtype Classification from Electromagnetic Signals Using Principal Component Methods; Proceedings of the The 7th International Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII2021); Beijing, China. 31 October–3 November 2021.

Fhager A., Candefjord S., Elam M., Persson M. 3D Simulations of Intracerebral Hemorrhage Detection Using Broadband Microwave Technology. Sensors. 2019;19:3482. doi: 10.3390/s19163482. PubMed DOI PMC

Candefjord S., Winges J., Malik A.A., Yu Y., Rylander T., McKelvey T., Fhager A., Elam M., Persson M. Microwave technology for detecting traumatic intracranial bleedings: Tests on phantom of subdural hematoma and numerical simulations. Med. Biol. Eng. Comput. 2017;55:1177–1188. doi: 10.1007/s11517-016-1578-6. PubMed DOI PMC

Merunka I., Massa A., Vrba D., Fiser O., Salucci M., Vrba J. Microwave Tomography System for Methodical Testing of Human Brain Stroke Detection Approaches. [(accessed on 8 April 2019)]. Available online: https://www.hindawi.com/journals/ijap/2019/4074862/abs/

Salucci M., Vrba J., Merunka I., Massa A. Real-time brain stroke detection through a learning-by-examples technique—An experimental assessment. Microw. Opt. Technol. Lett. 2017;59:2796–2799. doi: 10.1002/mop.30821. DOI

Salucci M., Gelmini A., Vrba J., Merunka I., Oliveri G., Rocca P. Instantaneous brain stroke classification and localization from real scattering data. Microw. Opt. Technol. Lett. 2019;61:808. doi: 10.1002/mop.31639. DOI

Pokorny T., Tesarik J. Microwave Stroke Detection and Classification Using Different Methods from MATLAB’s Classification Learner Toolbox; Proceedings of the 2019 European Microwave Conference in Central Europe (EuMCE); Prague, Czech Republic. 13–15 May 2019; pp. 500–503.

Salucci M., Polo A., Vrba J. Multi-Step Learning-by-Examples Strategy for Real-Time Brain Stroke Microwave Scattering Data Inversion. Electronics. 2021;10:95. doi: 10.3390/electronics10010095. DOI

COMSOL Multiphysics®. COMSOL AB; Stockholm, Sweden: 2022. [(accessed on 9 January 2023)]. Available online: www.comsol.com.

Tesarik J., Pokorny T., Vrba J. Dielectric sensitivity of different antennas types for microwave-based head imaging: Numerical study and experimental verification. Int. J. Microw. Wirel. Technol. 2020;12:982–995. doi: 10.1017/S1759078720000835. DOI

Erik G., Lee R.L.H. Population Head Model Repository V1.0. IT’IS Foundation; Zurich, Switzerland: 2016. DOI

Materialize 3-Matic; Leuven, Belgium. [(accessed on 9 January 2023)]. Available online: www.materialise.com.

Said T., Varadan V.V. Variation of Cole-Cole model parameters with the complex permittivity of biological tissues; Proceedings of the 2009 IEEE MTT-S International Microwave Symposium Digest; Boston, MA, USA. 7–12 June 2009; pp. 1445–1448.

Hasgall P.A., Di Gennnaro F., Baumgartner C., Neufeld E., Lloyd B., Gosselin M.C., Payne D., Klingenböck A., Kuster N. IT’IS Database for Thermal and Electromagnetic Parameters of Biological Tissues, version 4.0. IT’IS Foundation; Zurich, Switzerland: 2018. DOI

IEEE Recommended Practice for Determining the Peak Spatial-Average Specific Absorption Rate (SAR) in the Human Head from Wireless Communications Devices: Measurement Techniques. IEEE; New York, NY, USA: 2013. pp. 1–246. DOI

McGurgan I.J., Ziai W.C., Werring D.J., Salman R.A.-S., Parry-Jones A.R. Acute intracerebral haemorrhage: Diagnosis and management. Pract. Neurol. 2021;21:128–136. doi: 10.1136/practneurol-2020-002763. PubMed DOI PMC

Mariano V., Tobon Vasquez J.A., Casu M.R., Vipiana F. Brain Stroke Classification via Machine Learning Algorithms Trained with a Linearized Scattering Operator. Diagnostics. 2023;13:23. doi: 10.3390/diagnostics13010023. PubMed DOI PMC

Tesarik J., Diaz Rondon L.F., Fiser O. Prototype of Simplified Microwave Imaging System for Brain Stroke Follow Up. In: Lhotska L., Sukupova L., Lacković I., Ibbott G.S., editors. Proceedings of the World Congress on Medical Physics and Biomedical Engineering 2018; Prague, Czech Republic. 3–8 June 2018; Singapore: Springer; 2019. pp. 771–774.

Pokorny T., Vrba D., Tesarik J., Rodrigues D.B., Vrba J. Anatomically and Dielectrically Realistic 2.5D 5-Layer Reconfigurable Head Phantom for Testing Microwave Stroke Detection and Classification. [(accessed on 25 November 2019)]. Available online: https://www.hindawi.com/journals/ijap/2019/5459391/

An Experimental 10-Port Microwave System for Brain Stroke Diagnosis-Potentials and Limitations