QUIZ: An arbitrary volumetric point matching method for medical image registration.

Rigid pre-registration involving local-global matching or other large deformation scenarios is crucial. Current popular methods rely on unsupervised learning based on grayscale similarity, but under circumstances where different poses lead to varying tissue structures, or where image quality is poor, these methods tend to exhibit instability and inaccuracies. In this study, we propose a novel method for medical image registration based on arbitrary voxel point of interest matching, called query point quizzer (QUIZ). QUIZ focuses on the correspondence between local-global matching points, specifically employing CNN for feature extraction and utilizing the Transformer architecture for global point matching queries, followed by applying average displacement for local image rigid transformation.We have validated this approach on a large deformation dataset of cervical cancer patients, with results indicating substantially smaller deviations compared to state-of-the-art methods. Remarkably, even for cross-modality subjects, it achieves results surpassing the current state-of-the-art.

COVID-19 Detection via Ultra-Low-Dose X-ray Images Enabled by Deep Learning.

The detection of Coronavirus disease 2019 (COVID-19) is crucial for controlling the spread of the virus. Current research utilizes X-ray imaging and artificial intelligence for COVID-19 diagnosis. However, conventional X-ray scans expose patients to excessive radiation, rendering repeated examinations impractical. Ultra-low-dose X-ray imaging technology enables rapid and accurate COVID-19 detection with minimal additional radiation exposure. In this retrospective cohort study, ULTRA-X-COVID, a deep neural network specifically designed for automatic detection of COVID-19 infections using ultra-low-dose X-ray images, is presented. The study included a multinational and multicenter dataset consisting of 30,882 X-ray images obtained from approximately 16,600 patients across 51 countries. It is important to note that there was no overlap between the training and test sets. The data analysis was conducted from 1 April 2020 to 1 January 2022. To evaluate the effectiveness of the model, various metrics such as the area under the receiver operating characteristic curve, receiver operating characteristic, accuracy, specificity, and F1 score were utilized. In the test set, the model demonstrated an AUC of 0.968 (95% CI, 0.956-0.983), accuracy of 94.3%, specificity of 88.9%, and F1 score of 99.0%. Notably, the ULTRA-X-COVID model demonstrated a performance comparable to conventional X-ray doses, with a prediction time of only 0.1 s per image. These findings suggest that the ULTRA-X-COVID model can effectively identify COVID-19 cases using ultra-low-dose X-ray scans, providing a novel alternative for COVID-19 detection. Moreover, the model exhibits potential adaptability for diagnoses of various other diseases.

An energy-friendly alternative in the large-scale production of soybean oil.

Soybean oil is widely used as cooking oil, whereas the soybean cake is a valuable ingredient for animal food. The extraction of soybean oil is an energy-intensive process, with additional significant impact on the environment via the wastewater and hexane emissions. The research investigated different ways to minimize the energy consumption. In a traditional process, both direct (live) steam and indirect steam heating (jackets, tubular exchangers) are used to deliver the required heat duty. Direct steam injection is restricted to the first evaporator and the stripper, for a total of 620 kg/h. Indirect steam is also applied in the evaporators for a total of 6.44 MW. The desolventizing process requires a steam energy input of 8.15 MW. Integration of a heat exchanger network in the evaporation and stripping part of the process reduces the amount of direct steam usage from 620 kg/h to 270 kg/h and of the indirect heat duty from 6.44 to 5.05 MW. In the cake desolventizing part of the process, the energy requirement is reduced from 8.15 to 2.12 MW. The overall gross energy saving is hence ∼50%. The improvements moreover reduce both the waste water loadings by 56.5% and the CO2 emissions by 62.5%. Hexane emissions are moreover significantly (>90%) reduced.

Towards an energy-friendly and cleaner solvent-extraction of vegetable oil.

The extraction of vegetable oils is an energy-intensive process. It has moreover a significant environmental impact through hexane emissions and through the production of organic-loaded wastewater. A rice bran oil process was selected as the basis, since full data were available. By using Aspen Plus v8.2 simulation, with additional scripts, several improvements were examined, such as using heat exchanger networks, integrating a Vapor Recompression Heat Pump after the evaporation and stripping, and examining a nitrogen stripping of hexane in the rice bran meal desolventizing unit followed by a gas membrane to recover hexane. Energy savings by the different individual and combined improvements are calculated, and result in a 94.2% gain in steam consumption and a 73.8% overall energy saving. The power consumption of the membrane unit reduces the overall energy savings by about 5%. Hexane separation and enrichment by gas membranes facilitates its condensation and re-use, while achieving a reduction of hexane emissions by over 50%. Through the considerable reduction of required steam flow rates, 61% of waste water is eliminated, mostly as organic-loaded steam condensate. Through overall energy savings, 52% of related CO2 emissions are eliminated.

Experiments support an improved model for particle transport in fluidized beds.

The upwards flow of particles in an Upflow Bubbling Fluidized Bed (UBFB) is studied experimentally and modelled from pressure drop considerations and energy loss equations. For Geldart group A powders tested, the upward solid flux, G s , in the tube can be expressed in terms of the applied superficial gas velocity, the free fall (terminal) velocity of the particles during their hindered settling, KU t , the pressure exerted at the base of the conveyor tube, and the tube length. The model expression [Formula: see text] can be used for design purposes, with K, the correction factor for hindered settling of the particles, approximately equal to 0.1 at high G s -values, but a function of the solids fraction in the upward conveying. The energy efficiency of the system increases with increasing U and Gs. The model equation was tentatively applied to predict the effects of particle size, tube length and operation in Circulating Fluidized Bed mode. It is demonstrated that the UBFB is an efficient and flexible way of transporting particles upwards, with limited particle attrition or tube erosion due to the low gas velocity applied.

Gold nanoparticle surface deposition induced quantum efficiency enhancement for Si-multi-pixel photon counters.

With recent development of nanotechnology, novel devices with nanostructures arise to improve the performance of photodetectors. Here, we demonstrated that by surface decoration with gold nanoparticles on the active area, the quantum detection efficiency of a multi-pixel photon counter was increased due to surface plasmon resonance enhancement. The deposited gold nano-particles actually brought about almost the same enhancement factor for any photon-number fields. As a result, the photon-number-resolving capability of the multi-pixel photon counter was well reserved with the gold nano-particle deposition induced efficiency augment. This result provides guidance to the development of the high-efficiency photon-number-resolving detectors.

Laser ranging at 1550 nm with 1-GHz sine-wave gated InGaAs/InP APD single-photon detector.

We demonstrated a laser ranging system with single photon detection at 1550 nm. The single-photon detector was a 1-GHz sine-wave gated InGaAs/InP avalanche photodiode. In daylight, 8-cm depth resolution was achieved directly by using a time-of-flight approach based on time-correlated single photon counting measurement. This system presented a potential for low energy level and eye-safe laser ranging system in long-range measurement.