Review of Russian regulatory documents on the organization and functioning of offices and departments of magnetic resonance imaging.

Diagnostic studies carried out using any medical equipment require comprehensive control, which is provided by a number of regulatory documents. Particular attention is paid to X-ray imaging methods, but in the field of magnetic resonance imaging (MRI), one can notice both the lack of this attention and the multidirectional efforts to normalize. This is understandable - this diagnostic method is not based on the use of ionizing radiation, and although magnetic fields have some effect on human health, especially on personnel who work in MRI rooms all the time, they are safe for patients who come to the diagnostic procedure from time to time. time and do not have in their body foreign metal (steel implants) or electronic (pacemakers, neurostimulators) objects. However, ignorance and non-compliance with both advisory and mandatory requirements can significantly increase the risk of harm to patients or staff, as well as lead to a decrease in the quality of imaging and diagnostics. A separate feature of the field of MRI regulation is that over the past decades, more than a dozen different standards, sanitary norms, rules, letters and recommendations have been published or revised, a significant part of which complement or duplicate each other, or completely contradict each other. As a result, the need to ensure compliance of the MRI room / department with the requirements of regulatory documents is greatly complicated. This paper provides an overview of the regulatory documentation in force in Russia related to the organization and functioning of an MRI room / department, highlights the aspects that are most important from the point of view of safe and high-quality operation, and formulates the steps necessary to modernize the system, both from the point of view of the quality of diagnostics. and the safety of MRI studies.

Deep learning based solder joint defect detection on industrial printed circuit board X-ray images

With the improvement of electronic circuit production methods, such as reduction of component size and the increase of component density, the risk of defects is increasing in the production line. Many techniques have been incorporated to check for failed solder joints, such as X-ray imaging, optical imaging and thermal imaging, among which X-ray imaging can inspect external and internal defects. However, some advanced algorithms are not accurate enough to meet the requirements of quality control. A lot of manual inspection is required that increases the specialist workload. In addition, automatic X-ray inspection could produce incorrect region of interests that deteriorates the defect detection. The high-dimensionality of X-ray images and changes in image size also pose challenges to detection algorithms. Recently, the latest advances in deep learning provide inspiration for image-based tasks and are competitive with human level. In this work, deep learning is introduced in the inspection for quality control. Four joint defect detection models based on artificial intelligence are proposed and compared. The noisy ROI and the change of image dimension problems are addressed. The effectiveness of the proposed models is verified by experiments on real-world 3D X-ray dataset, which saves the specialist inspection workload greatly.

Multi-threshold window discriminator based on SAR logic

The new X-ray imaging detectors allow capturing an X-ray image in various photon energy ranges in one shot. This technique is called X-ray color imaging, and it is becoming a promising method in fields such as medical imaging, computed tomography, and non-destructive material testing. To measure the energy spectrum in one shot, discriminant circuits need to be integrated into the pixel front-end electronics. Several solutions of in-pixel discriminators exist. However, current designs suffer from a low number of discrimination bins and need to adjust each threshold separately, leading to relatively complicated calibration procedures. This work introduces a novel design of a multi-threshold window discriminator based on successive approximation register logic. This circuit realizes in-pixel binning to ten equidistant windows. Two variables are used for tuning the multi-threshold window discriminator: offset of the first window and width of the windows. Setting these parameters allows the user to fulfill the need of the target application.

X-ray in-line holography and holotomography at the NanoMAX beamline

Coherent X-ray imaging techniques, such as in-line holography, exploit the high brilliance provided by diffraction-limited storage rings to perform imaging sensitive to the electron density through contrast due to the phase shift, rather than conventional attenuation contrast. Thus, coherent X-ray imaging techniques enable high-sensitivity and low-dose imaging, especially for low-atomic-number (Z) chemical elements and materials with similar attenuation contrast. Here, the first implementation of in-line holography at the NanoMAX beamline is presented, which benefits from the exceptional focusing capabilities and the high brilliance provided by MAX IV, the first operational diffraction-limited storage ring up to approximately 300 eV. It is demonstrated that in-line holography at NanoMAX can provide 2D diffraction-limited images, where the achievable resolution is only limited by the 70 nm focal spot at 13 keV X-ray energy. Also, the 3D capabilities of this instrument are demonstrated by performing holotomography on a chalk sample at a mesoscale resolution of around 155 nm. It is foreseen that in-line holography will broaden the spectra of capabilities of MAX IV by providing fast 2D and 3D electron density images from mesoscale down to nanoscale resolution.