The study on the inverse problem of applied current thermoacoustic imaging based on generative adversarial network

Mechanism of acoustic pressure spectrum shifting toward lower frequencies in applied current thermoacoustic imaging

Objective. Thermoacoustic tomography (TAT) is a promising imaging technique used for early cancer diagnosis, tumor therapy, animal study and brain imaging. Although it is widely known that the TAT frequency response depends on the pulse width of the source and the size of the object, a thorough comprehension of the quantitative frequency modulation in TAT and the mechanism governing the shift in the thermoacoustic pressure spectrum towards lower frequencies with respect to the excitation source is still lacking. This study aims to understand why the acoustic pressure spectrum and the final voltage signals shift towards lower frequencies in TAT.Approach. We employed a linear time-invariant model. In the proposed model, the applied current thermoacoustic imaging (ACTAI) process is divided into the thermoacoustic stage and the acoustoelectric stage. These two stages are characterized by the thermoacoustic transfer function(TATF) and the transducer transfer function (TDTF), respectively. We confirmed the effectiveness of our model through a rigorous examination involving both simulations and experiments.Main results. Simulation results indicate that the TATF behaves as a low-pass filter. The inherent low-pass nature induces a shift towards low frequencies in the acoustic pressure spectrum. Experiments further confirm this behavior, demonstrating that the final electrical voltage also shifts towards low frequencies. Notably, employing the proposed model, there is a remarkable consistency between the main frequency bands of the synthesized and measured final voltage spectrum.Significance. The proposed model thoroughly explains how the TATF causes shifts to low frequencies in both the acoustic pressure spectrum and the final voltage spectrum in TAT. These insights deepen our understanding of optimizing TAT systems in the frequency domain, including aspects like filter design and transducer selection. Furthermore, we underscore the potential significance of this discovery for medical applications, particularly in the context of cancer diagnosis.

Metal Particle Detection by Integration of a Generative Adversarial Network and Electrical Impedance Tomography (GAN-EIT) for a Wet-Type Gravity Vibration Separator

The minor copper (Cu) particles among major aluminum (Al) particles have been detected by means of an integration of a generative adversarial network and electrical impedance tomography (GAN-EIT) for a wet-type gravity vibration separator (WGS). This study solves the problem of blurred EIT reconstructed images by proposing a GAN-EIT integration system for Cu detection in WGS. GAN-EIT produces two types of images of various Cu positions among major Al particles, which are (1) the photo-based GAN-EIT images, where blurred EIT reconstructed images are enhanced by GAN based on a full set of photo images, and (2) the simulation-based GAN-EIT images. The proposed metal particle detection by GAN-EIT is applied in experiments under static conditions to investigate the performance of the metal detection method under single-layer conditions with the variation of the position of Cu particles. As a quantitative result, the images of detected Cu by GAN-EIT ψ̿GAN in different positions have higher accuracy as compared to σ*EIT. In the region of interest (ROI) covered by the developed linear sensor, GAN-EIT successfully reduces the Cu detection error of conventional EIT by 40% while maintaining a minimum signal-to-noise ratio (SNR) of 60 [dB]. In conclusion, GAN-EIT is capable of improving the detailed features of the reconstructed images to visualize the detected Cu effectively.