The search for non-invasive, fast, and low-cost diagnostic tools has gained significant traction among many researchers worldwide. Dielectric properties calculated from microwave signals offer unique insights into biological tissue. Material properties, such as relative permittivity (εr) and conductivity (σ), can vary significantly between healthy and unhealthy tissue types at a given frequency. Understanding this difference in properties is key for identifying the disease state. The frequency-dependent nature of the dielectric measurements results in large datasets, which can be postprocessed using artificial intelligence (AI) methods. In this work, the dielectric properties of liver tissues in three mouse models of liver disease are characterized using dielectric spectroscopy. The measurements are grouped into four categories based on the diets or disease state of the mice, i.e., healthy mice, mice with non-alcoholic steatohepatitis (NASH) induced by choline-deficient high-fat diet, mice with NASH induced by western diet, and mice with liver fibrosis. Multi-class classification machine learning (ML) models are then explored to differentiate the liver tissue groups based on dielectric measurements. The results show that the support vector machine (SVM) model was able to differentiate the tissue groups with an accuracy up to 90%. This technology pipeline, thus, shows great potential for developing the next generation non-invasive diagnostic tools.

Department of Biological and Medical Sciences Faculty of Pharmacy in Hradec Králové Charles University Heyrovskeho 1203 500 05 Hradec Kralove Czech Republic

Department of Computer Science University of Wisconsin La Crosse WI 54601 USA

Department of Electrical and Computer Engineering North Dakota State University Fargo ND 58105 USA

Department of Electrical Engineering and Computer Science South Dakota Mines Rapid City SD 57701 USA

Department of Medicine Mayo Clinic Rochester MN 55905 USA

Department of Radiology Mayo Clinic Rochester MN 55905 USA

Gastroenterology Research Division of Gastroenterology and Hepatology Mayo Clinic Rochester MN 55905 USA

GIH Artificial Intelligence Laboratory Division of Gastroenterology and Hepatology Department of Medicine Mayo Clinic Rochester MN 55905 USA

Microwave Engineering and Imaging Laboratory Division of Gastroenterology and Hepatology Department of Medicine Mayo Clinic Rochester MN 55905 USA

See more in PubMed

Gabriel C., Gabriel S., Corthout E. The dielectric properties of biological tissues: I. Literature survey. Phys. Med. Biol. 1996;41:2231–2249. doi: 10.1088/0031-9155/41/11/001. PubMed DOI

Gabriel S., Lau R.W., Gabriel C. The dielectric properties of biological tissues: II. Measurements in the frequency range 10 Hz to 20 GHz. Phys. Med. Biol. 1996;41:2251–2269. doi: 10.1088/0031-9155/41/11/002. PubMed DOI

Gabriel S., Lau R.W., Gabriel C. The dielectric properties of biological tissues: III. Parametric models for the dielectric spectrum of tissues. Phys. Med. Biol. 1996;41:2271–2293. doi: 10.1088/0031-9155/41/11/003. PubMed DOI

Amin B., Elahi M.A., Shahzad A., Porter E., McDermott B., O’Halloran M. Dielectric properties of bones for the monitoring of osteoporosis. Med Biol. Eng. Comput. 2018;57:1–13. doi: 10.1007/s11517-018-1887-z. PubMed DOI

Di Meo S., Espin-Lopez P., Martellosio A., Pasian M., Bozzi M., Perregrini L., Mazzanti A., Svelto F., Summers P., Renne G., et al. Dielectric properties of breast tissues: Experimental results up to 50 GHz; Proceedings of the 12th European Conference on Antennas and Propagation (EuCAP 2018); London, UK. 9–13 April 2018; pp. 1–5.

Liewei S., Ward E.R., Story B. A review of dielectric properties of normal and malignant breast tissue; Proceedings of the IEEE SoutheastCon 2002; Columbia, SC, USA. 5–7 April 2002; pp. 457–462.

Surowiec A.J., Stuchly S.S., Barr J.R., Swarup A. Dielectric properties of breast carcinoma and the surrounding tissues. IEEE Trans. Biomed. Eng. 1988;35:257–263. doi: 10.1109/10.1374. PubMed DOI

Lazebnik M., Okoniewski M., Booske J.H., Hagness S.C. Highly Accurate Debye Models for Normal and Malignant Breast Tissue Dielectric Properties at Microwave Frequencies. IEEE Microw. Wirel. Components Lett. 2007;17:822–882. doi: 10.1109/LMWC.2007.910465. DOI

O’Rourke A.P., Lazebnik M., Bertram J.M., Converse M.C., Hagness S.C., Webster J.G., Mahvi D.M. Dielectric properties of human normal, malignant and cirrhotic liver tissue: In vivo and ex vivo measurements from 0.5 to 20 GHz using a precision open-ended coaxial probe. Phys. Med. Biol. 2007;52:4707–4719. doi: 10.1088/0031-9155/52/15/022. PubMed DOI

Yilmaz T., Foster R., Hao Y. Towards Accurate Dielectric Property Retrieval of Biological Tissues for Blood Glucose Monitoring. IEEE Trans. Microw. Theory Tech. 2014;62:3193–3204. doi: 10.1109/TMTT.2014.2365019. DOI

Treo E., Cervantes D., Felice C., Tirado M., Valentinuzzi M. Hematocrit measurement by dielectric spectroscopy. IEEE Trans. Biomed. Eng. 2005;52:124–127. doi: 10.1109/TBME.2004.836514. PubMed DOI

Sacli B., Aydinalp C., Cansiz G., Joof S., Yilmaz T., Cayoren M., Onal B., Akduman I. Microwave dielectric property based classification of renal calculi: Application of a kNN algorithm. Comput. Biol. Med. 2019;112:103366. doi: 10.1016/j.compbiomed.2019.103366. PubMed DOI

Gaddam S., Samaddar P., Khan M., Damani D., Shivaram S., Roy S., Dey S., Mitra D., Arunachalam S.P. On the Non-invasive Sensing of Arterial Waveform and Hematocrit using Microwaves; Proceedings of the IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (AP-S/URSI); Denver, CO, USA. 10–15 July 2022; pp. 1082–1083.

Samaddar P., Steinfort L.M.N., Fetzer J., Arunachalam S.P., Wang K.K., Leggett C.L. Tu1660: The Dielectric Properties of Upper Gastrointestinal Tissue Types—An Ex-Vivo Feasibility Study. Gastroenterology. 2022;162:S-1206. doi: 10.1016/S0016-5085(22)62442-9. DOI

Gaddam S., Samaddar P., Khan M., Damani D., Shivaram S., Roy S., Mitra D., Dey S., Arunachalam S.P. Towards Non-Invasive Mapping of Blood Flow Velocity using Microwaves; Proceedings of the IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (AP-S/URSI); Denver, CO, USA. 10–15 July 2022.

Rahmani H., Archang M.M., Jamali B., Forghani M., Ambrus A.M., Ramalingam D., Sun Z., Scumpia P.O., Coller H.A., Babakhani A. Towards a Machine-Learning-Assisted Dielectric Sensing Platform for Point-of-Care Wound Monitoring. IEEE Sens. Lett. 2020;4:1–4. doi: 10.1109/LSENS.2020.2999031. PubMed DOI

Helwana A., Idokob J.B., Abiyev R.H. Machine learning techniques for classification of breast tissue; Proceedings of the 9th International Conference on Theory and Application of Soft Computing, Computing with Words and Perception, ICSCCW 2017 Procedia Computer Science; Budapest, Hungary. 24–25 August 2017; pp. 402–410.

Yilmaz T., Kılıç M.A., Erdoğan M., Çayören M., Tunaoğlu D., Kurtoğlu İ., Yaslan Y., Çayören H., Arıkan A.E., Teksöz S., et al. Machine learning aided diagnosis of hepatic malignancies through in vivo dielectric measurements with microwaves. Phys. Med. Biol. 2016;61:5089–5102. doi: 10.1088/0031-9155/61/13/5089. PubMed DOI

La Gioia A., Porter E., Merunka I., Shahzad A., Salahuddin S., Jones M., O’Halloran M. Open-Ended Coaxial Probe Technique for Dielectric Measurement of Biological Tissues: Challenges and Common Practices. Diagnostics. 2018;8:40. doi: 10.3390/diagnostics8020040. PubMed DOI PMC

Samaddar P., Gaddam S., K P.S., Khan M., Mitra D., Leggett C., Roy S., Arunachalam S.P. On the Effects of the Measured Dielectric Properties at Variable Thickness of Biological Tissue Samples using Open-Ended Coaxial Probe Method; Proceedings of the IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (AP-S/URSI); Denver, CO, USA. 10–15 July 2022.

Samaddar P., Gaddam S., Khan M., Roy S., Mitra D., Arunachalam S.P. On the Dielectric Characterization of Biological Samples for Microwave Imaging Reconstruction; Proceedings of the IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (AP-S/URSI); Denver, CO, USA. 10–15 July 2022; pp. 1082–1083.

Gao J., Wei B., de Assuncao T.M., Liu Z., Hu X., Ibrahim S., Cooper S.A., Cao S., Shah V.H., Kostallari E. Hepatic stellate cell autophagy inhibits extracellular vesicle release to attenuate liver fibrosis. J. Hepatol. 2020;73:1144–1154. doi: 10.1016/j.jhep.2020.04.044. PubMed DOI PMC

Kostallari E., Hirsova P., Prasnicka A., Verma V.K., Yaqoob U., Wongjarupong N., Roberts L.R., Shah V.H. Hepatic stellate cell-derived platelet-derived growth factor receptor-alpha-enriched extracellular vesicles promote liver fibrosis in mice through SHP2. Hepatology. 2018;68:333–348. doi: 10.1002/hep.29803. PubMed DOI PMC

Kostallari E., Wei B., Sicard D., Li J., Cooper S.A., Gao J., Dehankar M., Li Y., Cao S., Yin M., et al. Stiffness is associated with hepatic stellate cell heterogeneity during liver fibrosis. Am. J. Physiol. Liver Physiol. 2022;322:G234–G246. doi: 10.1152/ajpgi.00254.2021. PubMed DOI PMC

Farrugiaa L., W P.S., Mangiona L.Z., Sammut C.V. Accurate in vivo dielectric properties of liver from 500 MHz to 40 GHz and their correlation to ex vivo measurements. Electromagn. Biol. Med. 2016;35:365–373. doi: 10.3109/15368378.2015.1120221. PubMed DOI

Pollacco D.A., Farina L., Wismayer P.S., Farrugia L., Sammut C.V. Characterization of the dielectric properties of biological tissues and their correlation to tissue hydration. IEEE Trans. Dielectr. Electr. Insul. 2018;25:2191–2197. doi: 10.1109/TDEI.2018.007346. DOI

N1501A Dielectric Probe Kit, Keysight Technologies. [(accessed on 11 November 2022)]. Available online: https://www.keysight.com/us/en/support/N1501A/dielectric-probe-kit.html.

Cavagnaro M., Ruvio G. Numerical Sensitivity Analysis for Dielectric Characterization of Biological Samples by Open-Ended Probe Technique. Sensors. 2020;20:3756. doi: 10.3390/s20133756. PubMed DOI PMC

Porter E., la Gioia A., Santorelli A., O’Halloran M. Modeling of the Dielectric Properties of Biological Tissues within the Histology Region. IEEE Trans. Dielectr. Electr. Insul. 2017;24:3290–3301. doi: 10.1109/TDEI.2017.006690. DOI

Andreuccetti D., Fossi R., Petrucci C. An Internet Resource for the Calculation of the Dielectric Properties of Body Tissues in the Frequency Range 10 Hz–100 GHz. [(accessed on 1 December 2022)]. Available online: http://niremf.ifac.cnr.it/tissprop/

Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011;12:2825–2830.

King G., Zeng L. Logistic Regression in Rare Events Data. Political Anal. 2001;9:137–163. doi: 10.1093/oxfordjournals.pan.a004868. DOI

Betmouni S. Diagnostic digital pathology implementation: Learning from the digital health experience. Digit. Health. 2021;7:20552076211020240. doi: 10.1177/20552076211020240. PubMed DOI PMC

Cheng J.Y., Abel J.T., Balis U.G., McClintock D.S., Pantanowitz L. Challenges in the Development, Deployment, and Regulation of Artificial Intelligence in Anatomic Pathology. Am. J. Pathol. 2020;191:1684–1692. doi: 10.1016/j.ajpath.2020.10.018. PubMed DOI

Gabriel C., Peyman A. Conn’s Handbook of Models for Human Aging. 2nd ed. Elsevier; Amsterdam, The Netherlands: 2018. Dielectric Properties of Biological TissuesVariation with Age; pp. 939–952.

Hussein M., Awwad F., Jithin D., El Hasasna H., Athamneh K., Iratni R. Breast cancer cells exhibits specific dielectric signature in vitro using the open-ended coaxial probe technique from 200 MHz to 13.6 GHz. Sci. Rep. 2019;9:468. doi: 10.1038/s41598-019-41124-1. PubMed DOI PMC