Accurate blood glucose level monitoring using microwave imaging

Abstract

Painless, and non-invasive detection techniques are needed to replace finger-pick blood for diabetic. In this paper, a first-of-its-kind, noninvasive, and continuous blood glucose level (BGL) detection method based on microwave imaging is introduced. This method avoids the complex task of frequency choice for the design of electromagnetic sensor. A radar-based microwave imaging technology combined with improved very-deep super resolution (VDSR-BL) method is introduced to obtain high-resolution (HR) microwave images. After image super-resolution reconstruction by VDSR-BL, the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) of HR images reach 35.4461 dB and 0.9761, respectively. Then an ensemble learning strategy based on support vector regression (SVR) and random forest algorithms is proposed to identify HR microwave images for BGL estimation. The developed detection system has been verified on the medium under tests (MUT) with different glucose solution. The final detection results obtain the root mean squared error (RMSE) of 0.1394 mg/mL and the mean absolute relative difference (MARD) of 8.02%, which show well accuracy with clinical acceptance. Meanwhile, we also conducted human trials. The high correlation coefficient (R) of 0.9254 was achieved between the results of microwave imaging and invasive BGL. Together, these results show that microwave imaging offers a promising new approach for noninvasive BGL monitoring.