Brainomaly: Unsupervised Neurologic Disease Detection Utilizing Unannotated T1-weighted Brain MR Images.

Harnessing the power of deep neural networks in the medical imaging domain is challenging due to the difficulties in acquiring large annotated datasets, especially for rare diseases, which involve high costs, time, and effort for annotation. Unsupervised disease detection methods, such as anomaly detection, can significantly reduce human effort in these scenarios. While anomaly detection typically focuses on learning from images of healthy subjects only, real-world situations often present unannotated datasets with a mixture of healthy and diseased subjects. Recent studies have demonstrated that utilizing such unannotated images can improve unsupervised disease and anomaly detection. However, these methods do not utilize knowledge specific to registered neuroimages, resulting in a subpar performance in neurologic disease detection. To address this limitation, we propose Brainomaly, a GAN-based image-to-image translation method specifically designed for neurologic disease detection. Brainomaly not only offers tailored image-to-image translation suitable for neuroimages but also leverages unannotated mixed images to achieve superior neurologic disease detection. Additionally, we address the issue of model selection for inference without annotated samples by proposing a pseudo-AUC metric, further enhancing Brainomaly's detection performance. Extensive experiments and ablation studies demonstrate that Brainomaly outperforms existing state-of-the-art unsupervised disease and anomaly detection methods by significant margins in Alzheimer's disease detection using a publicly available dataset and headache detection using an institutional dataset. The code is available from https://github.com/mahfuzmohammad/Brainomaly.

The usage and costs of national drug price-negotiated anticancer medicines in a first-tier city in Northeast China: a study based on health insurance data.

BACKGROUND: The National Drug Price Negotiation (NDPN) policy has entered a normalisation stage, aiming to alleviate, to some extent, the disease-related and economic burdens experienced by cancer patients. This study analysed the use and subsequent burden of anticancer medicines among cancer patients in a first-tier city in northeast China. METHODS: We assessed the usage of 64 negotiated anticancer medicines using the data on the actual drug deployment situation, the frequency of medical insurance claims and actual medication costs. The affordability of these medicines was measured using the catastrophic health expenditure (CHE) incidence and intensity of occurrence. Finally, we used the defined daily doses (DDDs) and defined daily doses cost (DDDc) as indicators to evaluate the actual use of these medicines in the region. RESULTS: During the study period, 63 of the 64 medicines were readily available. From the perspective of drug usage, the frequency of medical insurance claims for negotiated anticancer medicines and medication costs showed an increasing trend from 2018 to 2021. Cancer patients typically sought medical treatment at tertiary hospitals and purchased medicines at community pharmacies. The overall quantity and cost of medications for patients covered by the Urban Employee Basic Medical Insurance (UEBMI) were five times higher than those covered by the Urban and Rural Resident Medical Insurance (URRMI). The frequency of medical insurance claims and medication costs were highest for lung and breast cancer patients. Furthermore, from 2018 to 2021, CHE incidence showed a decreasing trend (2.85-1.60%) under urban patients' payment capability level, but an increasing trend (11.94%-18.42) under rural patients' payment capability level. The average occurrence intensities for urban (0.55-1.26 times) and rural (1.27-1.74 times) patients showed an increasing trend. From the perspective of drug utilisation, the overall DDD of negotiated anticancer medicines showed an increasing trend, while the DDDc exhibited a decreasing trend. CONCLUSION: This study demonstrates that access to drugs for urban cancer patients has improved. However, patients' medical behaviours are affected by some factors such as hospital level and type of medical insurance. In the future, the Chinese Department of Health Insurance Management should further improve its work in promoting the fairness of medical resource distribution and strengthen its supervision of the nation's health insurance funds.

Facile Estimation of Surface Oxygen Vacancies in Co3O4 Catalysts with a Colorimetric Method.

Oxygen vacancy (Ov) is known to act as an active center of the metal oxide. Quantification of surface Ov is vital for understanding the quantitative structure-activity relationship. Facile quantification characterization of surface Ov is highly desirable but still challenging. In this study, we presented a simple colorimetric method for rapidly quantifying surface Ov. As an example of metal oxide nanoparticles, Co3O4 was used to catalyze the 3,3',5,5'-tetramethylbenzidine (TMB)-H2O2 colorimetric reaction. It was found that the absorbance of the TMB-H2O2 system was dependent on the surface Ov amount in Co3O4. The investigation of the mechanism showed that the Ov-dependent absorbance would be attributed to the activity of surface Ov to easily adsorb and dissociate H2O2 into a hydroxyl radical (•OH). The absorbance signal of the TMB-H2O2 system acted as a probe to estimate the surface Ov. This colorimetric measurement could be completed in less than 20 min. The Ov concentrations obtained by the proposed colorimetric method matched well with those obtained by X-ray photoelectron spectroscopy. This method does not require any complex operation and expensive equipment and can be performed in any ordinary chemical laboratory. So, this colorimetric method is expected to become an alternative approach for quantifying the surface Ov in metal oxide nanoparticles. This method will provide essential insights into the rational design and application of Ov.

Ordinal Classification with Distance Regularization for Robust Brain Age Prediction.

Age is one of the major known risk factors for Alzheimer's Disease (AD). Detecting AD early is crucial for effective treatment and preventing irreversible brain damage. Brain age, a measure derived from brain imaging reflecting structural changes due to aging, may have the potential to identify AD onset, assess disease risk, and plan targeted interventions. Deep learning-based regression techniques to predict brain age from magnetic resonance imaging (MRI) scans have shown great accuracy recently. However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects. This weakens the reliability of predicted brain age as a valid biomarker for downstream clinical applications. Here, we reformulate the brain age prediction task from regression to classification to address the issue of systematic bias. Recognizing the importance of preserving ordinal information from ages to understand aging trajectory and monitor aging longitudinally, we propose a novel ORdinal Distance Encoded Regularization (ORDER) loss that incorporates the order of age labels, enhancing the model's ability to capture age-related patterns. Extensive experiments and ablation studies demonstrate that this framework reduces systematic bias, outperforms state-of-art methods by statistically significant margins, and can better capture subtle differences between clinical groups in an independent AD dataset. Our implementation is publicly available at https://github.com/jaygshah/Robust-Brain-Age-Prediction.

Label-free and portable detection of HIV-DNA by a handheld luminometer.

BACKGROUND: The human immunodeficiency virus (HIV) remains a major worldwide health problem. Nowadays, many methods have been developed for quantitative detecting human immunodeficiency virus DNA (HIV-DNA), such as fluorescence and colorimetry. However, these methods still have the disadvantages of being expensive and requiring professional technicians. Early diagnosis of pathogens is increasingly dependent on portable instruments and simple point-of-care testing (POCT). Therefore, it is meaningful and necessary to develop portable and cheap methods for detecting disease markers. RESULTS: In this work, a label-free chemiluminescence (CL) method was developed for detecting HIV-DNA via a handheld luminometer. To achieve label-free target detection, the CL catalyst, G-triplex-hemin DNAzyme (G3-hemin DNAzyme), was in-situ assembled in the presence of HIV-DNA. For improving sensitivity, HIV-DNA induced the cyclic strand displacement reaction (SDR), which can form three G3-hemin DNAzymes in one cycle. So, the chemiluminescence reaction between luminol and H2O2 was highly effectively catalyzed, and the CL intensity was linearly related with the concentration of HIV-DNA in the range of 0.05-10 nM with a detection limit of 29.0 pM. Due to the high specificity of hairpin DNA, single-base mismatch can be discriminated, which ensured the specific detection of HIV-DNA. SIGNIFICANCE: In-situ formation of G3-hemin DNAzyme led to label-free and selective detection without complex synthesis and functionalization. Therefore, it offers a cheap, selective, sensitive and portable method for detecting disease-related genes, which is promising for POCT of clinical diagnosis in resource-limited settings.

Multifunctional Manganese-Nucleotide Laccase-Mimicking Nanozyme for Degradation of Organic Pollutants and Visual Assay of Epinephrine via Smartphone.

As a natural green catalyst, laccase has extensive application in the fields of environmental monitoring and pollutant degradation. However, susceptibility to environmental influences and poor reusability seriously hinder its application. To address these concerns, for the first time, manganese ion replaced copper ion as the active center to coordinate with guanosine monophosphate (GMP) for synthesizing mimic laccase with high catalytic activity. Compared with natural laccase, the laccase-like nanozyme (Mn-GMPNS) demonstrated superior thermal stability, acid-base resistance, salt tolerance, reusability, and substrate universality. Benefiting from the high catalytic activity of Mn-GMPNS, epinephrine, a significant neurotransmitter and hormone associated with numerous diseases, was visually detected within 10 min and a portable assay by smartphone. More encouragingly, Mn-GMPNS can efficiently degrade dye pollutants, achieving a decolorization rate over 70% within 30 min. Thus, the coordination between manganese ion and nucleotide demonstrated the potential in rational design of nanozymes with high catalytic activity, low cost, good stability, and good biocompatibility.

A novel self-enhanced electrochemiluminescent aptamer sensor based on ternary nanocomposite PEI/RuSi-MWCNTs for the detection of profenofos residues in vegetables.

In this work, a novel ternary nanocomposite of PEI/RuSi-MWCNTs was designed and synthesized for the first time, which an ultrasensitive and self-enhanced electrochemiluminescent (ECL) aptasensor was developed for the detection of profenofos residues in vegetables. The self-enhanced complex PEI-Ru (II) enhanced the emission and stability of ECL, and the multi-walled carbon nanotubes (MWCNTs) acted as an excellent carrier and signal amplification. The PEI/RuSi-MWCNTs were characterized by scanning electron microscope (SEM), transmission electron microscope (TEM) and energy dispersive spectrometer (EDS). The incorporation of gold nanoparticles (AuNPs) improved the performance of the sensor and provided a platform for the immobilization of the aptamer. The results of the experiment showed that the presence of profenofos significantly suppressed the electrochemiluminescence intensity of the sensor. The detection sensitivity of the aptamer sensor was in the range of 1 × 10-2 to 1 × 103 ng/mL. Under optimal conditions, the limit of detection (LOD) of the sensor for profenofos was 1.482 × 10-3 ng/mL. The sensor had excellent stability, reproducibility and specificity. The recoveries of the sensor ranged from 92.29 % to 106.47 % in real sample tests.

Fluorescent aptasensor mediated with multiple ssDNA for sensitive detection of acetamiprid in vegetables based on magnetic Fe3O4/C-assisted separation.

Acetamiprid (ACE) is a highly effective broad-spectrum insecticide, and its widespread use is potentially harmful to human health and environmental safety. In this study, magnetic Fe3O4/carbon (Fe3O4/C), a derivative of metal-organic framework MIL-101 (Fe), was synthesized by a two-step calcination method. And a fluorescent sensing strategy was developed for the efficient and sensitive detection of ACE using Fe3O4/C and multiple complementary single-stranded DNA (ssDNA). By using aptamer with multiple complementary ssDNA, the immunity of interference of the aptasensor was improved, and the aptasensor showed high selectivity and sensitivity. When ACE was present, the aptamer (Apt) combined with ACE. The complementary strand of Apt (Cs1) combined with two short complementary strands of Cs1, fluorophore 6-carboxyfluorescein-labeled complementary strand (Cs2-FAM) and the other strand Cs3. The three strands formed a double-stranded structure, and fluorescence would not be quenched by Fe3O4/C. In the absence of ACE, Cs2-FAM would be in a single-chain state and would be adsorbed by Fe3O4/C, and the fluorescence of FAM would be quenched by Fe3O4/C via photoelectron transfer. This aptasensor sensitively detected ACE over a linear concentration range of 10-1000 nM with a limit of detection of 3.41 nM. The recoveries of ACE spiked in cabbage and celery samples ranged from 89.49% to 110.76% with high accuracy.

Naked-eye rapid recognition of tyrosine enantiomers using silver triangular nanoplates as colorimetric probe.

Recognizing and quantifying enantiomers of chiral molecule is of great importance in chemical, biological and pharmaceutical fields. Herein, we presented one simple-yet-efficient method of sensing tyrosine (Tyr) enantiomers. In this sensing, silver triangular nanoplates (AgTNPs) were used as colorimetric probes. L-Tyr quickly induced the color of AgTNPs solution to change from dark blue to light gray, whereas D-Tyr induced no change of the AgTNPs solution color. The obvious color change enables the naked eye to recognize Tyr enantiomer. The visual method was used to detect the enantiometric excess value of L-Tyr in the whole range (-100 % ∼ 100 %). This chiral sensing can be finished within 5 min using one simple ultraviolet-visible spectrometer or naked eye. Furthermore, the mechanism of this chiral sensing was explored. It was confirmed that this chiral sensing was based on AgTNPs' intrinsic chirality. This chiral sensing is rapid, simple, and low-cost, and has great potential for chiral determination of Tyr.

Entropy-driven catalysis-based lateral flow assay for sensitive detection of Alzheimer 's-associated MicroRNA.

Alzheimer's disease (AD) is a degenerative disease of the brain worldwide. Currently, there is no effective cure. But accurate and early diagnosis of AD is critical to the development of patient care and future treatments. MiRNA-16 has been considered as an effective diagnostic biomarker for AD because of its regulatory effect on key proteins of AD. Herein, a colorimetric lateral flow assay (LFA) was developed for sensitive detection of miRNA-16 based on entropy-driven catalysis (EDC) amplification strategy. MiRNA-16 triggered EDC and released more linker DNAs (LDNA) of sandwich structure. Thus, AuNPs were enriched at the T-line to enhance the colorimetric signal and improve the sensitivity of visual assay. It showed good specificity and sensitivity for detecting miRNA-16 with a detection limit of 1.01 pM. The practical detection of miRNA-16 in human serum obtained satisfactory result. Significantly, EDC achieved signal amplification in homogeneous solution without enzyme and DNA labeling, leading to a cheap and easy detection of miRNA-16. Therefore, it provided a portable and rapid assay for AD-related nucleic acid, which holds a potential for point-of-care testing (POCT) of AD.

Novel electrochemiluminescence aptasensor based on AuNPs-ABEI encapsulated TiO2 nanorod for the detection of acetamiprid residues in vegetables.

Gold nanoparticles (AuNPs)@N-(4-aminobutyl)-N-ethylisoluminol (ABEI)@Titanium dioxide nanorods (TiO2NRs) were used as sensing materials to produce a unique encapsulated nanostructure aptasensor for the detection of acetamiprid residues in this work. ABEI, an analog of luminol, was extensively used as an electrochemiluminescence (ECL) reagent. The ECL mechanism of ABEI- hydrogen peroxide (H2O2) system had connections to a number of oxygen-centered free radicals. TiO2NRs improved ECL response with high electron transfer and a specific surface area. AuNPs were easy to biolabel and could catalyze H2O2 to enhance ECL signal. AuNPs were wrapped around TiO2NRs by utilizing the reduction property of ABEI to form wrapped modified nanomaterials. The sulfhydryl-modified aptamer bound to the nanomaterial by forming gold-sulfur (Au-S) bonds. The aptamer selectively bound to its target with the addition of acetamiprid, which caused a considerable decrease in ECL intensity and enabled quantitative detection of acetamiprid. The aptasensor showed good stability, repeatability and specificity with a broad detection range (1×10-2-1×103 nM) and a lower limit of detection (3 pM) for acetamiprid residues in vegetables. Overall, this aptasensor presents a simple and highly sensitive method for ECL detecting acetamiprid, with potential applications in vegetable safety monitoring.

Surface Oxygen Vacancy-Rich Co3O4 Nanowires as an Effective Catalyst of Luminol-H2O2 Chemiluminescence for Sensitive Immunoassay.

Oxygen vacancy is one intrinsic defect in metal oxide materials. Interestingly, we herein found that the surface oxygen vacancy can significantly enhance the catalytic activity of Co3O4 nanowires in the luminol-H2O2 chemiluminescence (CL) reaction. 0.1 ng/mL Co3O4 nanowires containing 51.3% surface oxygen vacancies possessed ca. 2.5-fold catalytic activity of free Co2+ (the best metal ionic catalyst for the luminol-H2O2 CL reaction). The superior catalytic efficiency is attributed to the enhanced adsorption of H2O2 by surface oxygen vacancies, which in turn accelerates the cleavage of O-O bonds and generates •OH radicals. More importantly, the surface oxygen vacancy-rich Co3O4 nanowires retained about 90% catalytic activity after modification with antibodies. The surface oxygen vacancy-rich Co3O4 nanowires were used to label the secondary antibody, and one sandwich-type CL immunoassay of carcinoembryonic antigen was established. The detection limit was 0.3 ng/mL with a linear range of 1-10 ng/mL. This proof-of-concept work proves that surface oxygen vacancy-rich Co3O4 nanowires are suitable for labeling biomolecules in CL bioanalysis and biosensing.

Self-assembly of DNA-gold nanoaggregate for visual detection of thymidine kinase 1 (TK1) mRNA via lateral flow assay.

Nucleic acid lateral flow assay (NALFA) with gold nanoparticles (AuNPs) as colorimetric probes have been extensively adopted for point-of-care testing (POCT). However, the sensitivity of NALFA still needs to be improved. Herein, DNA-gold nanoaggregate (DNA-AuNA) was assembled as a signal amplification probe of NALFA for sensitive detection of tumor marker TK1 mRNA. Four functional oligonucleotides with complementary pairs were assembled to form DNA-AuNA that coupled more AuNPs to improve sensitivity. Thus, the limit of detection (LOD) was 0.36 pM, which is lower than that of conventional AuNPs-based NALFA. Moreover, the bioassay showed good reproducibility, stability, and specificity for detecting TK1 mRNA. The detection of TK1 mRNA in human serum was also satisfactory. Therefore, DNA-AuNA-based NALFA provides a sensitive method for portable detection of TK1 mRNA.

Carbon Vacancy-Enhanced Activity of Fe-N-C Single Atom Catalysts toward Luminol Chemiluminescence in the Absence of H2O2.

The classic luminol-H2O2 chemiluminescence (CL) systems suffer from easy self-decomposition of H2O2 at room temperature, hindering the practical applications of the luminol-H2O2 CL system. In this work, unexpectedly, we found that the carbon vacancy-modified Fe-N-C single atom catalysts (VC-Fe-N-C SACs) can directly trigger a luminol solution to generate strong CL emission in the absence of H2O2. The Fe-based SACs were prepared through the conventional pyrolysis of zeolitic imidazolate frameworks. The massive carbon vacancies were readily introduced into Fe-N-C SACs through a tannic acid-etching process. Carbon vacancy significantly enhanced the catalytic activity of Fe-N-C SACs on the CL reaction of luminol-dissolved oxygen. The VC-Fe-N-C SACs performed a 13.4-fold CL enhancement compared with the classic luminol-Fe2+ system. It was found that the introduction of a carbon vacancy could efficiently promote dissolved oxygen to convert to reactive oxygen species. As a proof of concept, the developed CL system was applied to detect alkaline phosphatase with a linear range of 0.005-1 U/L as well as a detection limit of 0.003 U/L. This work demonstrated that VC-Fe-N-C SAC is a highly efficient CL catalyst that can promote the analytic application of the luminol CL system.

Silver/copper bimetallic nanoclusters integrating with cryonase-assisted target recycling amplification detection of Salmonella typhimurium.

An unsophisticated fluorescence-enabled strategy is brought forward to process the highly sensitive fluorescence detection of Salmonella typhimurium (S. typhimurium) which based on polyethyleneimine (PEI)-templated silver/copper nanoclusters (Ag/CuNCs) (λ excitation = 334 nm and λ emission = 466 nm) with cryonase-assisted target recycling amplification. The Ag/CuNCs nanoclusters are synthesized as fluorescent materials due to their strong and stable fluorescence characteristics and are modified with S. typhimurium aptamers to form aptamer-Ag/CuNCs probes. The probes can be adsorbed on the surface of quenching agents-polydopamine nanospheres (PDANSs), thereby inducing fluorescence quenching of the probes. Once the aptamers are bound to the target, the aptamers/targets complexes are separated from the PDANSs surface, and the Ag/CuNCs recover the fluorescence signal. The released complexes will immediately be transformed into a substrate digested by cryonase (an enzyme that can digest all types of nucleic acids), and the released targets are bound to another aptamers to initiate the next round of cleavage. This reaction will be repeated continuously until all relevant aptamers are consumed and all Ag/CuNCs are released, resulting in a significant amplification of the fluorescence signal and improved sensitivity. Using Ag/CuNCs as fluorescent probes combined with cryonase-assisted amplification strategy, the fluorescence aptasensor is constructed with detection limits as low as 3.8 CFU mL-1, which is tenfold better than without the cryonase assistance. The method developed has been applied to milk, orange juice, chicken, and egg white samples with excellent selectivity and accuracy providing an approach for the early and rapid detection of S. typhimurium in food.

Multifunctional DNA nanoprobe for tumor-targeted synergistic therapy by integrating chemodynamic therapy with gene silencing.

Due to the high complexity, diversity and heterogeneity of tumor occurrence and development, multi-mode synergistic therapy is more effective than single treatment modes to improve the antitumor efficacy. Also, multifunctional probes are crucial to realize synergistic therapy. Herein, a multifunctional DNA tetrahedron nanoprobe was ingeniously designed to simultaneously achieve chemodynamic therapy (CDT) and gene silencing for synergistic antitumor. The multifunctional DNA tetrahedron nanoprobe, DNA tetrahedron-silver nanocluster-antagomir-21 (D-sgc8-DTNS-AgNCs-Anta-21), integrated a CDT reagent (DNA-AgNCs) and miRNA-21 inhibitor (Anta-21) with a specific recognition probe (aptamer). After targeted entry in cancer cells, D-sgc8-DTNS-AgNCs-Anta-21 silenced endogenous miRNA-21 by Anta-21 and produced highly toxic ˙OH by reacting with H2O2, which induced apoptosis in the tumor cells. The targeted recognition of aptamers led to the concentration-dependent death of HeLa cells. On the contrary, the cell survival rate of normal cells was basically unaffected with an increase in the concentration of D-sgc8-DTNS-AgNCs-Anta-21. Therefore, the diverse functions, biocompatibility and programmability of DNA provide a useful and easy way to assemble multifunctional probes for synergistic therapy.

Deep-learning based fast and accurate 3D CT deformable image registration in lung cancer.

BACKGROUND: Deformable Image Registration (DIR) is an essential technique required in many applications of radiation oncology. However, conventional DIR approaches typically take several minutes to register one pair of 3D CT images and the resulting deformable vector fields (DVFs) are only specific to the pair of images used, making it less appealing for clinical application. PURPOSE: A deep-learning-based DIR method using CT images is proposed for lung cancer patients to address the common drawbacks of the conventional DIR approaches and in turn can accelerate the speed of related applications, such as contour propagation, dose deformation, adaptive radiotherapy (ART), etc. METHODS: A deep neural network based on VoxelMorph was developed to generate DVFs using CT images collected from 114 lung cancer patients. Two models were trained with the weighted mean absolute error (wMAE) loss and structural similarity index matrix (SSIM) loss (optional) (i.e., the MAE model and the M+S model). In total, 192 pairs of initial CT (iCT) and verification CT (vCT) were included as a training dataset and the other independent 10 pairs of CTs were included as a testing dataset. The vCTs usually were taken 2 weeks after the iCTs. The synthetic CTs (sCTs) were generated by warping the vCTs according to the DVFs generated by the pre-trained model. The image quality of the synthetic CTs was evaluated by measuring the similarity between the iCTs and the sCTs generated by the proposed methods and the conventional DIR approaches, respectively. Per-voxel absolute CT-number-difference volume histogram (CDVH) and MAE were used as the evaluation metrics. The time to generate the sCTs was also recorded and compared quantitatively. Contours were propagated using the derived DVFs and evaluated with SSIM. Forward dose calculations were done on the sCTs and the corresponding iCTs. Dose volume histograms (DVHs) were generated based on dose distributions on both iCTs and sCTs generated by two models, respectively. The clinically relevant DVH indices were derived for comparison. The resulted dose distributions were also compared using 3D Gamma analysis with thresholds of 3 mm/3%/10% and 2 mm/2%/10%, respectively. RESULTS: The two models (wMAE and M+S) achieved a speed of 263.7±163 / 265.8±190 ms and a MAE of 13.15±3.8 / 17.52±5.8 HU for the testing dataset, respectively. The average SSIM scores of 0.987±0.006 and 0.988±0.004 were achieved by the two proposed models, respectively. For both models, CDVH of a typical patient showed that less than 5% of the voxels had a per-voxel absolute CT-number-difference larger than 55 HU. The dose distribution calculated based on a typical sCT showed differences of ≤2cGy[RBE] for clinical target volume (CTV) D95 and D5 , within ±0.06% for total lung V5 , ≤1.5cGy[RBE] for heart and esophagus Dmean , and ≤6cGy[RBE] for cord Dmax compared to the dose distribution calculated based on the iCT. The good average 3D Gamma passing rates (> 96% for 3 mm/3%/10% and > 94% for 2 mm/2%/10%, respectively) were also observed. CONCLUSION: A deep neural network-based DIR approach was proposed and has been shown to be reasonably accurate and efficient to register the initial CTs and verification CTs in lung cancer.

Impact of hyperkalemia on hospitalization days in advanced chronic kidney disease patients with Type-2 diabetes mellitus: A prospective study.

Objective: This study aimed to explore the impact of hyperkalemia at admission on hospitalization days (HDs) among advanced chronic kidney disease patients (CKD) with type two diabetes mellitus (T2DM) in China. Methods: A total of 270 CKD patients with T2DM were prospectively selected from January 1, 2020 to December 31, 2021. These patients were divided into Group-A (n = 150, serum potassium ≤ 5.5 mmol/L) and B (n = 120, serum potassium > 5.5 mmol/L). The comparison method between the two groups was taken. Linear correlation analysis was performed using the Spearman correlation method, and multivariate analysis was tested using linear regression. Results: The study found statistically significant result between the two groups (Group-A vs Group-B): HDs (7.4 (5.3-11.2) vs 12.1 (8.2-16.5), p < 0.001), renin-angiotensin-aldosterone system inhibitors (RAASIs) (36.2% vs 55.8%, p = 0.014), systolic blood pressure (148.35 ± 19.51 vs 162.26 ± 21.31, p < 0.05), estimated glomerular filtration (eGFR) (20.35) (18.31-25.26) vs13.4 (12.50-18.50), p < 0.001, N-terminal pro-B type natriuretic peptide (NT-proBNP) (2245.42 ± 61.09 vs 3163.39 ± 85.15,p < 0.001), and Hb (88.45 ± 12.35 vs 72.26 ± 14.2, p = 0.023). Correlation analysis showed that HDs were positively correlated with age, serum potassium, systolic blood pressure, and NT-proBNP, while negatively with eGFR and Hb. After adjusting for relevant confounding variables, the multivariable linear regression analysis showed that hyperkalemia was an independent risk factor for HDs. Conclusions: Hyperkalemia could be an independent risk factor increasing HDs of advanced CKD patients with T2DM.

Deep-Learning-based Fast and Accurate 3D CT Deformable Image Registration in Lung Cancer.

PURPOSE: In some proton therapy facilities, patient alignment relies on two 2D orthogonal kV images, taken at fixed, oblique angles, as no 3D on-the-bed imaging is available. The visibility of the tumor in kV images is limited since the patient's 3D anatomy is projected onto a 2D plane, especially when the tumor is behind high-density structures such as bones. This can lead to large patient setup errors. A solution is to reconstruct the 3D CT image from the kV images obtained at the treatment isocenter in the treatment position. METHODS: An asymmetric autoencoder-like network built with vision-transformer blocks was developed. The data was collected from 1 head and neck patient: 2 orthogonal kV images (1024x1024 voxels), 1 3D CT with padding (512x512x512) acquired from the in-room CT-on-rails before kVs were taken and 2 digitally-reconstructed-radiograph (DRR) images (512x512) based on the CT. We resampled kV images every 8 voxels and DRR and CT every 4 voxels, thus formed a dataset consisting of 262,144 samples, in which the images have a dimension of 128 for each direction. In training, both kV and DRR images were utilized, and the encoder was encouraged to learn the jointed feature map from both kV and DRR images. In testing, only independent kV images were used. The full-size synthetic CT (sCT) was achieved by concatenating the sCTs generated by the model according to their spatial information. The image quality of the synthetic CT (sCT) was evaluated using mean absolute error (MAE) and per-voxel-absolute-CT-number-difference volume histogram (CDVH). RESULTS: The model achieved a speed of 2.1s and a MAE of <40HU. The CDVH showed that <5% of the voxels had a per-voxel-absolute-CT-number-difference larger than 185 HU. CONCLUSION: A patient-specific vision-transformer-based network was developed and shown to be accurate and efficient to reconstruct 3D CT images from kV images.

Logic-Gates of Gas Pressure for Portable, Intelligent and Multiple Analysis of Metal Ions.

DNA logic gates have shown outstanding magic in intelligent biology applications, but it remains challenging to construct a portable, affordable and convenient DNA logic gate. Herein, logic gates of gas pressure were innovatively developed for multiplex analysis of metal ions. Hg2+ and Ag+ were input to interact specifically with the respective mismatched base pairs, which activated DNA extension reaction by polymerase and led to the enrichment of platinum nanoparticles for catalyzing the decomposition of peroxide hydrogen. Thus, the gas pressure obtained from a sealed well was used as output for detecting or identifying metal ions. Hg2+ and Ag+ were sensitively and selectively detected, and the assay of the real samples was also satisfactory. Based on this, DNA logic gates, including YES, NOT, AND, OR, NAND, NOR, INHIBIT, and XOR were successfully established using a portable and hand-held gas pressure meter as detector. So, the interactions between DNA and metal ions were intelligently transferred into the output of gas pressure, which made metal ions to be detected portably and identified intelligently. Given the remarkable merits of simplicity, logic operation, and portable output, the metal ion-driven DNA logic gate of gas pressure provides a promising way for intelligent and portable biosensing.