Gamma Radiation Imaging System via Variable and Time-Multiplexed Pinhole Arrays

Deep learning method for pinhole array color image reconstruction

The following paper proposes a combination of a supervised encoder-decoder neural network with coded apertures. Coded apertures provide improved sensitivity and signal-to-noise ratio (SNR) in planar images. The unique array design of this method overcomes the spatial frequency cutoff found in standard multi-pinhole arrays. In this design, the pinholes were positioned to minimize loss in spatial frequencies. The large number of pinholes results in significant overlapping on the detector. To overcome the overlapping issue, reconstruction of the object from the obtained image is done using inverse filtering methods. However, traces of duplications remain leading to a decline in SNR, contrast, and resolution. The proposed technique addresses the challenge of image distortion caused by the lack of accuracy in the inverse filter methods, by using a deep neural network. In this work, the coded aperture is combined with a deep convolutional neural network (CNN) to remove noise caused by pinhole imaging and inverse filter limitations. Compared to only using Wiener filtering, the proposed method delivers higher SNR, contrast, and resolution. The imaging system is presented in detail with experimental results that illustrate its efficiency.

Signal-to-Noise Ratio Improvement for Multiple-Pinhole Imaging Using Supervised Encoder–Decoder Convolutional Neural Network Architecture

Digital image devices have been widely applied in many fields, such as individual recognition and remote sensing. The captured image is a degraded image from the latent observation, where the degradation processing is affected by some factors, such as lighting and noise corruption. Specifically, noise is generated in the processing of transmission and compression from the unknown latent observation. Thus, it is essential to use image denoising techniques to remove noise and recover the latent observation from the given degraded image. In this research, a supervised encoder–decoder convolution neural network was used to fix image distortion stemming from the limited accuracy of inverse filter methods (Wiener filter, Lucy–Richardson deconvolution, etc.). Particularly, we will correct image degradation that mainly stems from duplications arising from multiple-pinhole array imaging.

A Novel Portable Gamma Radiation Sensor Based on a Monolithic Lutetium-Yttrium Oxyorthosilicate Ring

Portable radiation detectors are widely used in environmental radiation detection and medical imaging due to their portability feature, high detection efficiency, and large field of view. Lutetium-yttrium oxyorthosilicate (LYSO) is a widely used scintillator in gamma radiation detection. However, the structure and the arrangement of scintillators limit the sensitivity and detection accuracy of these radiation detectors. In this study, a novel portable sensor based on a monolithic LYSO ring was developed for the detection of environmental radiation through simulation, followed by construction and assessments. Monte Carlo simulations were utilized to prove the detection of gamma rays at 511 keV by the developed sensor. The simulations data, including energy resolutions, decoding errors, and sensitivity, showed good potential for the detection of gamma rays by the as-obtained sensor. The experimental results using the VA method revealed decoding errors in the energy window width of 50 keV less than 2°. The average error was estimated at 0.67°, a sufficient value for the detection of gamma radiation. In sum, the proposed radiation sensor appears promising for the construction of high-performance radiation detectors and systems.

Reduction in Irradiation Dose in Aperture Coded Enhanced Computed Tomography Imager Using Super-Resolution Techniques

One of the main concerns regarding medical imaging is the danger tissue’s ionizing due to the applied radiation. Many medical procedures are based on this ionizing radiation (such as X-rays and Gamma radiation). This radiation allows the physician to perform diagnosis inside the human body. Still, the main concern is stochastic effects to the DNA, particularly the cause of cancer. The radiation dose endangers not only the patient but also the medical staff, who might be close to the patient and be exposed to this dangerous radiation in a daily manner. This paper presents a novel concept of radiation reduced Computed Tomography (CT) scans. The proposed concept includes two main methods: minification to enhance the energy concertation per pixel and subpixel resolution enhancement, using shifted images, to preserve resolution. The proposed process uses several pinhole masks as the base of the imaging modality. The proposed concept was validated numerically and experimentally and has demonstrated the capability of reducing the radiation efficiency by factor 4, being highly significant to the world of radiology and CT scans. This dose reduction allows a safer imaging process for the patient and the medical staff. This method simplifies the system and improves the obtained image quality. The proposed method can contribute additively to standard existing dose reduction or super-resolution techniques to achieve even better performance.