Search

Magnetic resonance (MR) imaging is an important computer-aided diagnosis technique with rich pathological information. The factor of physical and physiological constraint seriously affects the applicability of that technique. Thus, computed tomography (CT)-based radiotherapy is more popular on account of its imaging rapidity and environmental simplicity. Therefore, it is of great theoretical and practical significance to design a method that can construct an MR image from the corresponding CT image. In this paper, we treat MR imaging as a machine vision problem and propose a multi-conditional constraint generative adversarial network (GAN) for MR imaging from CT scan data. Considering reversibility of GAN, both generator and reverse generator are designed for MR and CT imaging, respectively, which can constrain each other and improve consistency between features of CT and MR images. In addition, we innovatively treat the real and generated MR image discrimination as object re-identification; cosine error fusing with original GAN loss is designed to enhance verisimilitude and textural features of the MR image. The experimental results with the challenging public CT-MR image dataset show distinct performance improvement over other GANs utilized in medical imaging and demonstrate the effect of our method for medical image modal transformation. [ABSTRACT FROM AUTHOR]

Although cable-based seismic sensing systems have provided reliable data in the past several decades, they become a bottleneck for large-area monitoring and critical environmental (volcanic eruptions) sensing because of their cost, difficulty in deploying and expanding, and lack of accurate three-dimensional geographic information. In this paper, a new wireless sensing system is designed consisting of a portable satellite device, a self-sustaining power source, a low-cost computational core, and a high-precision sensor. The emphasis of this paper is to implement in low-cost hardware without requirements of highly specialized and expensive data acquisition instruments. Meanwhile, a computational-core-embedded algorithm based on compressive sensing (CS) is also developed to compress data size for transmission and encrypt the measured data preventing information loss. Seismic data captured by the accelerometer sensor are coded into compressive data packages and then transferred via satellite communication to a cloud-based server for storage. Acceleration and GPS information is decrypted by the ℓ1-norm minimization optimization algorithm for further processing. In this research, the feasibility of the proposed sensing system for the acquisition of seismic testing is investigated in an outdoor field surface wave testing. Results indicate the proposed low-cost wireless sensing system has the capability of collecting ground motions, transferring data, and sharing GPS information via satellite communication for large area monitoring. In addition, it has a great potential of recovering measurements even with significant data package loss. [ABSTRACT FROM AUTHOR]