Currently, the tuberculosis (TB) detection model based on chest X-ray images has the problem of excessive reliance on hardware computing resources, high equipment performance requirements, and being harder to deploy in low-cost personal computer and embedded devices. An efficient tuberculosis detection model is proposed to achieve accurate, efficient, and stable tuberculosis screening on devices with lower hardware levels. Due to the particularity of the chest X-ray images of TB patients, there are fewer labeled data, and the deep neural network model is difficult to fully train. We first analyzed the data distribution characteristics of two public TB datasets, and found that the two-stage tuberculosis identification (first divide, then classify) is insufficient. Secondly, according to the particularity of the detection image(s), the basic residual module was optimized and improved, and this is regarded as a crucial component of this article’s network. Finally, an efficient attention mechanism was introduced, which was used to fuse the channel features. The network architecture was optimally designed and adjusted according to the correct and sufficient experimental content. In order to evaluate the performance of the network, it was compared with other lightweight networks under personal computer and Jetson Xavier embedded devices. The experimental results show that the recall rate and accuracy of the E-TBNet proposed in this paper are better than those of classic lightweight networks such as SqueezeNet and ShuffleNet, and it also has a shorter reasoning time. E-TBNet will be more advantageous to deploy on equipment with low levels of hardware.

For bench-top X-ray fluorescence computed tomography (XFCT), the X-ray tube source will bring extreme Compton background noise, resulting in a low signal-to-noise ratio and low contrast detection limit. In this paper, a noise2noise denoising algorithm based on the UNet deep learning network is proposed. The network can use noise image learning to convert the noise image into a clean image. Two sets of phantoms (high concentration Gd phantom and low concentration Bi phantom) are used for scanning to simulate the imaging process under different noise levels and generate the required data set. Additionally, the data set is generated by Geant4 simulation. In the training process, the L1 loss function is used for its good convergence. The image quality is evaluated according to CNR and pixel profile, which shows that our algorithm is better than BM3D, both visually and quantitatively.

Polychromatic source X-ray fluorescence computed tomography (XFCT) is a novel imaging method, which is applied for the diagnosis and treatment studies of early stage cancer. In this paper, we propose a fast multi-pinhole L-shell XFCT imaging system to reduce the scan time and radiation dose, which has potential in detecting lower concentration of contrast agents (gold nanoparticles, GNPs). Two kinds of phantoms –the concentration-phantom 1 and the size-phantom 2 are designed to verify imaging performance for low-concentration and small-size ROI. The scanning processes are simulated by Geant4, and images are reconstructed by Optimized EM-TV algorithm. It is concluded that this imaging system is more sensitive in detecting low concentration GNPs than K-shell imaging system. Simulation experiments show the reconstructed images can achieve the highest CNR both for phantom 1 and phantom 2 with iterating 10 times. The detection limit can reach 0.16% when pinhole radius is 0.08mm.