MITNet: GAN Enhanced Magnetic Induction Tomography Based on Complex CNN
This work addresses the problem of non-intrusive brain disease monitoring for medical applications, representing a strong specific gain in image reconstruction quality.
The paper tackles the challenge of high-quality brain image reconstruction in magnetic induction tomography (MIT) by proposing MITNet, a GAN-enhanced technique based on a complex CNN, which outperforms the state-of-the-art method by 25.27% on a real-world dataset.
Magnetic induction tomography (MIT) is an efficient solution for long-term brain disease monitoring, which focuses on reconstructing bio-impedance distribution inside the human brain using non-intrusive electromagnetic fields. However, high-quality brain image reconstruction remains challenging since reconstructing images from the measured weak signals is a highly non-linear and ill-conditioned problem. In this work, we propose a generative adversarial network (GAN) enhanced MIT technique, named MITNet, based on a complex convolutional neural network (CNN). The experimental results on the real-world dataset validate the performance of our technique, which outperforms the state-of-art method by 25.27%.