Research on coal-gangue dual-energy X-ray image detection method based on SGMM-YOLO

Dual-energy X-ray imaging is of significant interest for medical diagnostics, security screening, and industrial inspection; however, existing approaches based on photon-counting or multilayer detectors often increase the system complexity. Here, we introduce a surface-treated perovskite thin-crystal device with an engineered electrode architecture, enabling high-sensitivity, dual-energy X-ray imaging. With surface treatment, the device achieves enhanced optoelectronic performance with a sensitivity of 4.5 × 104 μC·Gy1-·cm-2, a low detection limit of 13.8 nGy·s-1, and greatly improved device stability. By tailoring the internal electric field distribution through the electrode design, the device achieves controlled absorption of X-ray photons with different energies, thereby exhibiting an excellent energy discrimination capability. Subtraction imaging of overlapping low- and high-density objects was successfully reconstructed by the algorithmic processing of response currents. Furthermore, precise material differentiation was achieved through introducing the ratio of X-ray absorption coefficients (μL/μH), which cannot be realized by conventional X-ray detectors. Our study provides a simple and efficient route for dual-energy X-ray imaging and offers new perspectives for the development of multifunctional perovskite-based devices.

Background: Dual-energy X-ray images (DEI) can distinguish or improve materials of interest in a two-dimensional radiographic image, by combining two images obtained from separate low and high energies. The concepts of DEI performance describing the performance of double-exposure DEI systems in the Fourier domain been previously introduced, however, the performance of double-exposure DEI itself in terms of various parameters, has not been reported.Materials and Methods: To investigate the DEI performance, signal-difference-to-noise ratio, modulation transfer function, noise power spectrum, and noise equivalent quanta were used. Low- and high-energy were 60 and 130 kVp with 0.01–0.09 mGy, respectively. The energyseparation filter material and its thicknesses were tin (Sn) and 0.0–1.0 mm, respectively. Noise-reduction (NR) filtering used the Gaussian-filter NR, median-filter NR, and anti-correlated NR.Results and Discussion: DEI performance was affected by Sn-filter thickness, weighting factor, and dose allocation. All NR filtering successfully reduced noise, when compared with the dual-energy (DE) images without any NR filtering.Conclusion: The results indicated the significance of investigating, and evaluating suitable DEI performance, for DE images in chest radiography applications. Additionally, all the NR filtering methods were effective at reducing noise in the resultant DE images.

BackgroundSegmentation of the ulna and radius is a crucial step for the measurement of bone mineral density (BMD) in dual-energy X-ray imaging in patients suspected of having osteoporosis.PurposeThis work aimed to propose a deep learning approach for the accurate automatic segmentation of the ulna and radius in dual-energy X-ray imaging.Methods and materialsWe developed a deep learning model with residual block (Resblock) for the segmentation of the ulna and radius. Three hundred and sixty subjects were included in the study, and five-fold cross-validation was used to evaluate the performance of the proposed network. The Dice coefficient and Jaccard index were calculated to evaluate the results of segmentation in this study.ResultsThe proposed network model had a better segmentation performance than the previous deep learning-based methods with respect to the automatic segmentation of the ulna and radius. The evaluation results suggested that the average Dice coefficients of the ulna and radius were 0.9835 and 0.9874, with average Jaccard indexes of 0.9680 and 0.9751, respectively.ConclusionThe deep learning-based method developed in this study improved the segmentation performance of the ulna and radius in dual-energy X-ray imaging.

Dual-energy X-ray imaging is an important method of medical imaging, capable of not only obtaining spatial information of imaging object but also disclosing its chemical components, and has many applications in clinic. The current computation methods of dual-energy imaging are still based on the model of mono-energy spectrum imaging with some linear calibration, while they are incapable to reflect correctly the physical characteristics of dual-energy imaging and obstruct deeper research in this field. The article presents a new medical X-ray imaging model in accordance with physics of imaging and its corresponding computational method. The computation process includes two steps: first, to compute two attenuation parameters that have clear physical meaning: equivalent electron density and attenuation parameter of photoemission; then to compute the components of high- and low-density mass through a group of simple equation with two variables. Experiments showed that such method has quite a satisfactory precision in theory, that is, the solutions of parameters under different exposure voltages and thickness of tissue for several main tissues of human body are much low in deviations, whose quotient of standard deviation divided by mean are mostly under 0.1%, and at most 0.32%. The method provides not only a new computational way for dual-energy X-ray imaging, but also a feasible analysis for its nature. In addition, the method can be used to linearly rectify data of dual-energy CT and analyze the chemical component of reconstructed object by means of parameters clear in physics.

Dual-energy X-ray imaging (DEXI) is a cutting-edge technology that provides more detailed material-specific information than the traditional single-energy X-ray imaging strategy. Herein, we designed and fabricated a top-filter-bottom (TFB) sandwich structure scintillator for high-resolution DEXI within a single exposure. More specifically, the low- and high-energy X-ray photons were sequentially absorbed by the top and bottom scintillators and were efficiently converted into their corresponding emission colors. By discriminating between these different emission spectra of the transparent TFB sandwich structure scintillator, DEXI can provide not only unique X-ray energy information but also an exceptional resolution of approximately 18 lp/mm on stacked images that surpasses most of the reported single-layer organic- and metal halide-based scintillators. The conceptual demonstrations of decomposition and reconstruction in DEXI were also realized on several biological imaging objects. This breakthrough research paves the way for the development of scintillator architectures specifically designed for DEXI.

Optimizing dual energy X-ray image enhancement using a novel hybrid fusionmethod.

Dual-energy X-ray imaging can provide material-specific image information, which is very useful in inspection tasks. Accurate and efficient material decomposition is desirable in such tasks, and we developed a fast and efficient dual-energy calibration method for high-energy X-ray cargo inspection. We designed a calibration phantom consisting of a half cylinder of lead and a half cylinder of carbon. We used a least-squares method to determine the material decomposition formula from the calibration-phantom data. To test the feasibility of the proposed method, we designed a cargo phantom in a simulation study. Material decomposition was successfully conducted, so we expect the proposed calibration method to play an important role in high-energy X-ray imaging for cargo inspection.

Wearing safety helmets can effectively reduce the risk of head injuries for construction workers in high-altitude falls. In order to address the low detection accuracy of existing safety helmet detection algorithms for small targets and complex environments in various scenes, this study proposes an improved safety helmet detection algorithm based on YOLOv8, named YOLOv8n. For data augmentation, the mosaic data augmentation method is employed, which generates many tiny targets. In the backbone network, a coordinate attention (CA) mechanism is added to enhance the focus on safety helmet regions in complex backgrounds, suppress irrelevant feature interference, and improve detection accuracy. In the neck network, a slim-neck structure fuses features of different sizes extracted by the backbone network, reducing model complexity while maintaining accuracy. In the detection layer, a small target detection layer is added to enhance the algorithm’s learning ability for crowded small targets. Experimental results indicate that, through these algorithm improvements, the detection performance of the algorithm has been enhanced not only in general scenarios of real-world applicability but also in complex backgrounds and for small targets at long distances. Compared to the YOLOv8n algorithm, YOLOv8n in precision, recall, mAP50, and mAP50-95 metrics, respectively. Additionally, YOLOv8n-SLIM-CA reduces the model parameters by 6.98% and the computational load by 9.76%. It is capable of real-time and accurate detection of safety helmet wear. Comparison with other mainstream object detection algorithms validates the effectiveness and superiority of this method.

The spatial distributions of bone and soft tissue in human body are separated by independent component analysis (ICA) of dual-energy x-ray images. It is because of the dual energy imaging model¡-s conformity to the ICA model that we can apply this method: (1) the absorption in body is mainly caused by photoelectric absorption and Compton scattering; (2) they take place simultaneously but are mutually independent; and (3) for monochromatic x-ray sources the total attenuation is achieved by linear combination of these two absorption. Compared with the conventional method, the proposed one needs no priori information about the accurate x-ray energy magnitude for imaging, while the results of the separation agree well with the conventional one.

The intelligent identification of coal gangue on industrial conveyor belts is a crucial technology for the precise sorting of coal gangue. To address the issues in coal gangue detection algorithms, such as high false negative rates, complex network structures, and substantial model weights, an optimized coal gangue detection algorithm based on YOLOv5s is proposed. In the backbone network, a feature refinement module is employed for feature extraction, enhancing the capability to extract features for coal and gangue. The improved BIFPN structure is employed as the feature pyramid, augmenting the model’s capability for cross-scale feature fusion. In the prediction layer, the ESIOU is utilized as the bounding box regression loss function to rectify the misalignment issue between predicted and actual box angles. This approach expedites the convergence speed of the network while concurrently enhancing the accuracy of coal gangue detection. Channel pruning is implemented on the network to diminish model computational complexity and weight, consequently augmenting detection speed. The experimental results demonstrate that the refined YOLOv5s coal gangue detection algorithm outperforms the original YOLOv5s algorithm, achieving a notable accuracy enhancement of 2.2% to reach 93.8%. Concurrently, a substantial reduction in model weight by 38.8% is observed, resulting in a notable 56.2% increase in inference speed. These advancements meet the detection requirements for scenarios involving mixed coal gangue.

Intelligent detection of coal gangue in mining Operations using multispectral imaging and enhanced RT-DETR algorithm for efficient sorting

We have developed a method that uses a large amount of <i>a priori</i> information to generate super resolution radiographs. We measured and modeled analytically the point spread function of a low-dose gas microstrip x-ray detector at several beam energies. We measured the relationship between the local image intensity and the noise variance in the radiographs. The soft-tissue signal in the images was modeled using a minimum-curvature filtering technique. These results were then combined into an image deconvolution procedure using wavelet filtering to reduce restoration noise while keeping the enhanced small-scale features. The method was applied to a resolution grid image to measure its effects on the detector’s modulation transfer function. The restored images of a radiological human-torso phantom revealed small-scale details on the bones that were not seen before, and this, with improved SNR and image contrast. Dual-energy imaging was integrated to the restoration process in order to generate separate high-resolution images of the bones, the soft tissues, and the mean atomic number. This information could be used to detect bone micro-fractures in athletes and to assess bone demineralization in seniors due to osteoporosis. Super resolution radiographs are easier to segment due to their enhanced contrasts and uniform backgrounds; the boundaries of the features of interest can be delimited with a sub-pixel accuracy. This is highly relevant to the morphometric analysis of complex bone structures like individual vertebrae. The restoration method can be automated for a clinical environment use.

Dual-energy imaging is based on the acquisition of two spectrally distinct attenuation measurements. The two most common techniques are the dual-kV technique and the dual-detector layer technique. More recently, another technique was introduced based on the simultaneous acquisition of photon-counting and current integration data (CIX) by means of a dedicated detector readout ASIC. All of the above methods have certain advantages and disadvantages. While depending on the particular realization (e.g., kVp switching, dual-tube systems in computed tomography), the dual-kV technique suffers from a time-lag between the two acquisitions and as a result from susceptibility to motion. The dual-layer technique usually offers less spectral separation and requires a dedicated detection system. The CIX technique suffers from a reduced dynamic range due to the limiting rate performance in the counting channel. In this paper we introduce yet another dual-energy technique, similar to the CIX, however, without the restrictions coming from the limited count rate. We propose dual-energy imaging based on simultaneous acquisition of the mean (DC) and variance (AC) components of the electrical detector signal, i.e., simultaneous integration-mode readout and Campbell-mode readout (fluctuation mode). The method is based on “Campbell's theorem” which states that the variance of the deviations from the mean detector signal is proportional to the second moment of the incoming x-ray energy spectrum. We compare in simulations the dual-energy performance of the proposed new technique with conventional dual-kV and dual-crystal techniques and present first experimental Campbell-mode CT images obtained from a scintillator crystal coupled to a photomultiplier tube. Moreover, we demonstrate the feasibility of separating iodine from calcium with the novel technique and compare it to the separability achieved with a dual-kV technique.

Automatic inspection of X-ray scans at security checkpoints can improve the public security. X-ray images are different from photographic images. They are transparent. They contain much less texture. They may be highly cluttered. Objects may undergo in- and out-of-plane rotations. On the other hand, scale and illumination change is less of an issue. More importantly, X-ray imaging provides extra information which are usually not available in regular images: dual-energy imaging, which provides material information about the objects; and multi-view imaging, which provides multiple images of objects from different viewing angles. Such peculiarities of X-ray images should be leveraged for high-performance object recognition systems to be deployed on X-ray scanners. To this end, we first present an extensive evaluation of standard local features for object detection on a large X-ray image dataset in a structured learning framework. Then, we propose two dense sampling methods as keypoint detector for textureless objects and extend the SPIN color descriptor to utilize the material information. Finally, we propose a multi-view branch-and-bound search algorithm for multi-view object detection. Through extensive experiments on three object categories, we show that object detection performance on X-ray images improves substantially with the help of extended features and multiple views.

Material detection is a vital need in dual-energy X-ray luggage inspection systems at security of airport and strategic places. In this paper, a novel material detection algorithm based on power density function (PDF) estimation of three material categories in dual-energy X-ray images is proposed. In this algorithm, PDF of each material category is estimated from grayscale values of a synthetic image that is called fused image, using Gaussian Mixture Models (GMM). The fused image is obtained from wavelet sub bands of high energy and low energy X-ray images. High and low energy X-ray images enhance using two background removing and denoising stages as a preprocessing procedure. The proposed algorithm is evaluated on real images that have been captured from a dual-energy X-ray luggage inspection system. The obtained results show that the proposed algorithm is effective and operative in detecting of metallic, organic and mixed materials with acceptable accuracy.