Multi-scale variational autoencoder for imputation of missing values in untargeted metabolomics using whole-genome sequencing data.

BACKGROUND: Missing data is a common challenge in mass spectrometry-based metabolomics, which can lead to biased and incomplete analyses. The integration of whole-genome sequencing (WGS) data with metabolomics data has emerged as a promising approach to enhance the accuracy of data imputation in metabolomics studies. METHOD: In this study, we propose a novel method that leverages the information from WGS data and reference metabolites to impute unknown metabolites. Our approach utilizes a multi-scale variational autoencoder to jointly model the burden score, polygenetic risk score (PGS), and linkage disequilibrium (LD) pruned single nucleotide polymorphisms (SNPs) for feature extraction and missing metabolomics data imputation. By learning the latent representations of both omics data, our method can effectively impute missing metabolomics values based on genomic information. RESULTS: We evaluate the performance of our method on empirical metabolomics datasets with missing values and demonstrate its superiority compared to conventional imputation techniques. Using 35 template metabolites derived burden scores, PGS and LD-pruned SNPs, the proposed methods achieved R2-scores > 0.01 for 71.55 % of metabolites. CONCLUSION: The integration of WGS data in metabolomics imputation not only improves data completeness but also enhances downstream analyses, paving the way for more comprehensive and accurate investigations of metabolic pathways and disease associations. Our findings offer valuable insights into the potential benefits of utilizing WGS data for metabolomics data imputation and underscore the importance of leveraging multi-modal data integration in precision medicine research.

A Staged Approach using Machine Learning and Uncertainty Quantification to Predict the Risk of Hip Fracture.

Hip fractures present a significant healthcare challenge, especially within aging populations, where they are often caused by falls. These fractures lead to substantial morbidity and mortality, emphasizing the need for timely surgical intervention. Despite advancements in medical care, hip fractures impose a significant burden on individuals and healthcare systems. This paper focuses on the prediction of hip fracture risk in older and middle-aged adults, where falls and compromised bone quality are predominant factors. We propose a novel staged model that combines advanced imaging and clinical data to improve predictive performance. By using convolutional neural networks (CNNs) to extract features from hip DXA images, along with clinical variables, shape measurements, and texture features, our method provides a comprehensive framework for assessing fracture risk. The study cohort included 547 patients, with 94 experiencing hip fracture. A staged machine learning-based model was developed using two ensemble models: Ensemble 1 (clinical variables only) and Ensemble 2 (clinical variables and DXA imaging features). This staged approach used uncertainty quantification from Ensemble 1 to decide if DXA features are necessary for further prediction. Ensemble 2 exhibited the highest performance, achieving an Area Under the Curve (AUC) of 0.9541, an accuracy of 0.9195, a sensitivity of 0.8078, and a specificity of 0.9427. The staged model also performed well, with an AUC of 0.8486, an accuracy of 0.8611, a sensitivity of 0.5578, and a specificity of 0.9249, outperforming Ensemble 1, which had an AUC of 0.5549, an accuracy of 0.7239, a sensitivity of 0.1956, and a specificity of 0.8343. Furthermore, the staged model suggested that 54.49% of patients did not require DXA scanning. It effectively balanced accuracy and specificity, offering a robust solution when DXA data acquisition is not always feasible. Statistical tests confirmed significant differences between the models, highlighting the advantages of the advanced modeling strategies. Our staged approach offers a cost-effective holistic view of patients' health. It could identify individuals at risk with a high accuracy but reduce the unnecessary DXA scanning. Our approach has great promise to guide interventions to prevent hip fractures with reduced cost and radiation.

A novel method combining gated SPECT and vectorcardiography to guide left ventricular lead placement to improve response to cardiac resynchronization therapy: A proof of concept study.

BACKGROUND: The segment of the latest mechanical contraction (LMC) does not always overlap with the site of the latest electrical activation (LEA). By integrating both mechanical and electrical dyssynchrony, this proof-of-concept study aimed to propose a new method for recommending left ventricular (LV) lead placements, with the goal of enhancing response to cardiac resynchronization therapy (CRT). METHODS: The LMC segment was determined by single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) phase analysis. The LEA site was detected by vectorcardiogram. The recommended segments for LV lead placement were as follows: (1) the LMC viable segments that overlapped with the LEA site; (2) the LMC viable segments adjacent to the LEA site; (3) If no segment met either of the above, the LV lateral wall was recommended. The response was defined as ≥15% reduction in left ventricular end-systolic volume (LVESV) 6-months after CRT. Patients with LV lead located in the recommended site were assigned to the recommended group, and those located in the non-recommended site were assigned to the non-recommended group. RESULTS: The cohort comprised of 76 patients, including 54 (71.1%) in the recommended group and 22 (28.9%) in the non-recommended group. Among the recommended group, 74.1% of the patients responded to CRT, while 36.4% in the non-recommended group were responders (P = .002). Compared to pacing at the non-recommended segments, pacing at the recommended segments showed an independent association with an increased response by univariate and multivariable analysis (odds ratio 5.00, 95% confidence interval 1.73-14.44, P = .003; odds ratio 7.33, 95% confidence interval 1.53-35.14, P = .013). Kaplan-Meier curves showed that pacing at the recommended LV lead position demonstrated a better long-term prognosis. CONCLUSION: Our findings indicate that pacing at the recommended segments, by integrating of mechanical and electrical dyssynchrony, is significantly associated with an improved CRT response and better long-term prognosis.

Radiomics Nomogram Derived from Gated Myocardial Perfusion SPECT for Identifying Ischemic Cardiomyopathy.

Personalized management involving heart failure (HF) etiology is crucial for better prognoses. We aim to evaluate the utility of a radiomics nomogram based on gated myocardial perfusion imaging (GMPI) in distinguishing ischemic from non-ischemic origins of HF. A total of 172 heart failure patients with reduced left ventricular ejection fraction (HFrEF) who underwent GMPI scan were divided into training (n = 122) and validation sets (n = 50) based on chronological order of scans. Radiomics features were extracted from the resting GMPI. Four machine learning algorithms were used to construct radiomics models, and the model with the best performances were selected to calculate the Radscore. A radiomics nomogram was constructed based on the Radscore and independent clinical factors. Finally, the model performance was validated using operating characteristic curves, calibration curve, decision curve analysis, integrated discrimination improvement values (IDI), and the net reclassification index (NRI). Three optimal radiomics features were used to build a radiomics model. Total perfusion deficit (TPD) was identified as the independent factors of conventional GMPI metrics for building the GMPI model. In the validation set, the radiomics nomogram integrating the Radscore, age, systolic blood pressure, and TPD significantly outperformed the GMPI model in distinguishing ischemic cardiomyopathy (ICM) from non-ischemic cardiomyopathy (NICM) (AUC 0.853 vs. 0.707, p = 0.038). IDI analysis indicated that the nomogram improved diagnostic accuracy by 28.3% compared to the GMPI model in the validation set. By combining radiomics signatures with clinical indicators, we developed a GMPI-based radiomics nomogram that helps to identify the ischemic etiology of HFrEF.

Purine salvage promotes treatment resistance in H3K27M-mutant diffuse midline glioma.

BACKGROUND: Diffuse midline gliomas (DMG), including diffuse intrinsic pontine gliomas (DIPGs), are a fatal form of brain cancer. These tumors often carry a driver mutation on histone H3 converting lysine 27 to methionine (H3K27M). DMG-H3K27M are characterized by altered metabolism and resistance to standard of care radiation (RT) but how the H3K27M mediates the metabolic response to radiation and consequent treatment resistance is uncertain. METHODS: We performed metabolomics on irradiated and untreated H3K27M isogenic DMG cell lines and observed an H3K27M-specific enrichment for purine synthesis pathways. We profiled the expression of purine synthesis enzymes in publicly available patient data and our models, quantified purine synthesis using stable isotope tracing, and characterized the in vitro and in vivo response to de novo and salvage purine synthesis inhibition in combination with RT. RESULTS: DMG-H3K27M cells activate purine metabolism in an H3K27M-specific fashion. In the absence of genotoxic treatment, H3K27M-expressing cells have higher relative activity of de novo synthesis and apparent lower activity of purine salvage demonstrated via stable isotope tracing of key metabolites in purine synthesis and by lower expression of hypoxanthine-guanine phosphoribosyltransferase (HGPRT), the rate-limiting enzyme of purine salvage into IMP and GMP. Inhibition of de novo guanylate synthesis radiosensitized DMG-H3K27M cells in vitro and in vivo. Irradiated H3K27M cells upregulated HGPRT expression and hypoxanthine-derived guanylate salvage but maintained high levels of guanine-derived salvage. Exogenous guanine supplementation decreased radiosensitization in cells treated with combination RT and de novo purine synthesis inhibition. Silencing HGPRT combined with RT markedly suppressed DMG-H3K27M tumor growth in vivo. CONCLUSIONS: Our results indicate that DMG-H3K27M cells rely on highly active purine synthesis, both from the de novo and salvage synthesis pathways. However, highly active salvage of free purine bases into mature guanylates can bypass inhibition of the de novo synthetic pathway. We conclude that inhibiting purine salvage may be a promising strategy to overcome treatment resistance in DMG-H3K27M tumors.

Mechanical guidance to self-organization and pattern formation of stem cells.

The self-organization of stem cells (SCs) constitutes the fundamental basis of the development of biological organs and structures. SC-driven patterns are essential for tissue engineering, yet unguided SCs tend to form chaotic patterns, impeding progress in biomedical engineering. Here, we show that simple geometric constraints can be used as an effective mechanical modulation approach that promotes the development of controlled self-organization and pattern formation of SCs. Using the applied SC guidance with geometric constraints, we experimentally uncover a remarkable deviation in cell aggregate orientation from a random direction to a specific orientation. Subsequently, we propose a dynamic mechanical framework, including cells, the extracellular matrix (ECM), and the culture environment, to characterize the specific orientation deflection of guided cell aggregates relative to initial geometric constraints, which agrees well with experimental observation. Based on this framework, we further devise various theoretical strategies to realize complex biological patterns, such as radial and concentric structures. Our study highlights the key role of mechanical factors and geometric constraints in governing SCs' self-organization. These findings yield critical insights into the regulation of SC-driven pattern formation and hold great promise for advancements in tissue engineering and bioactive material design for regenerative application.

A new method of modeling the multi-stage decision-making process of CRT using machine learning with uncertainty quantification.

Aims: Current machine learning-based (ML) models usually attempt to utilize all available patient data to predict patient outcomes while ignoring the associated cost and time for data acquisition. The purpose of this study is to create a multi-stage machine learning model to predict cardiac resynchronization therapy (CRT) response for heart failure (HF) patients. This model exploits uncertainty quantification to recommend additional collection of single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) variables if baseline clinical variables and features from electrocardiogram (ECG) are not sufficient. Methods: 218 patients who underwent rest-gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at a 6±1 month follow-up. A multi-stage ML model was created by combining two ensemble models: Ensemble 1 was trained with clinical variables and ECG; Ensemble 2 included Ensemble 1 plus SPECT MPI features. Uncertainty quantification from Ensemble 1 allowed for multi-stage decision-making to determine if the acquisition of SPECT data for a patient is necessary. The performance of the multi-stage model was compared with that of Ensemble models 1 and 2. Results: The response rate for CRT was 55.5% (n = 121) with overall male gender 61.0% (n = 133), an average age of 62.0±11.8, and LVEF of 27.7±11.0. The multi-stage model performed similarly to Ensemble 2 (which utilized the additional SPECT data) with AUC of 0.75 vs. 0.77, accuracy of 0.71 vs. 0.69, sensitivity of 0.70 vs. 0.72, and specificity 0.72 vs. 0.65, respectively. However, the multi-stage model only required SPECT MPI data for 52.7% of the patients across all folds. Conclusions: By using rule-based logic stemming from uncertainty quantification, the multi-stage model was able to reduce the need for additional SPECT MPI data acquisition without sacrificing performance.

Vision SLAM algorithm for wheeled robots integrating multiple sensors.

Wheeled robots play a crucial role in driving the autonomy and intelligence of robotics. However, they often encounter challenges such as tracking loss and poor real-time performance in low-texture environments. In response to these issues, this research proposes a real-time localization and mapping algorithm based on the fusion of multiple features, utilizing point, line, surface, and matrix decomposition characteristics. Building upon this foundation, the algorithm integrates multiple sensors to design a vision-based real-time localization and mapping algorithm for wheeled robots. The study concludes with experimental validation on a two-wheeled robot platform. The results indicated that the multi-feature fusion algorithm achieved the highest average accuracy in both conventional indoor datasets (84.57%) and sparse-feature indoor datasets (82.37%). In indoor scenarios, the vision-based algorithm integrating multiple sensors achieved an average accuracy of 85.4% with a processing time of 64.4 ms. In outdoor scenarios, the proposed algorithm exhibited a 14.51% accuracy improvement over a vision-based algorithm without closed-loop detection. In summary, the proposed method demonstrated outstanding accuracy and real-time performance, exhibiting favorable application effects across various practical scenarios.

A meta-analysis of predictive value of blood biomarkers in gestational trophoblastic neoplasia.

Background: Neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) have been reported to play a diagnostic and predictive role in gestational trophoblastic disease. However, the conclusions are still ambiguous. This meta-analysis aimed to evaluate the combined predictive value of NLR and PLR in the malignant progression of gestational trophoblastic disease. Method: Electronic databases including PubMed, Embase, the Cochrane Library, Web of Science, Chinese National Knowledge Infrastructure, Wanfang and China Biomedical Literature Database were searched for the relevant literature published up to 1 October 2022. Study selection and data extraction were performed independently by two reviewers. All analyses were performed using Revman, MetaDisc and STATA software. Results: A total of 858 patients from five studies were included in this meta-analysis. The pooled sensitivity and specificity of NLR were 0.8 (95% CI: 0.71-0.88) and 0.73 (95% CI: 0.69-0.76), respectively, and the area under curve of the summary receiver operating curve was 0.81. The pooled sensitivity and specificity of PLR were 0.87 (95% CI: 0.75-0.95) and 0.49 (95% CI: 0.44-0.54), respectively, and the area under curve of the summary receiver operating curve was 0.88. I2 statistic and Deek's funnel plot showed no heterogeneity and publication bias. Conclusion: NLR can accurately predict the progression from hydatidiform mole to gestational trophoblastic neoplasia and is a promising biomarker in further follow-up.

A new hip fracture risk index derived from FEA-computed proximal femur fracture loads and energies-to-failure.

Hip fracture risk assessment is an important but challenging task. Quantitative CT-based patient-specific finite element (FE) analysis (FEA) incorporates bone geometry and bone density in the proximal femur. We developed a global FEA-computed fracture risk index to increase the prediction accuracy of hip fracture incidence. PURPOSE: Quantitative CT-based patient-specific finite element (FE) analysis (FEA) incorporates bone geometry and bone density in the proximal femur to compute the force (fracture load) and energy necessary to break the proximal femur in a particular loading condition. The fracture loads and energies-to-failure are individually associated with incident hip fracture, and provide different structural information about the proximal femur. METHODS: We used principal component analysis (PCA) to develop a global FEA-computed fracture risk index that incorporates the FEA-computed yield and ultimate failure loads and energies-to-failure in four loading conditions of 110 hip fracture subjects and 235 age- and sex-matched control subjects from the AGES-Reykjavik study. Using a logistic regression model, we compared the prediction performance for hip fracture based on the stratified resampling. RESULTS: We referred the first principal component (PC1) of the FE parameters as the global FEA-computed fracture risk index, which was the significant predictor of hip fracture (p-value < 0.001). The area under the receiver operating characteristic curve (AUC) using PC1 (0.776) was higher than that using all FE parameters combined (0.737) in the males (p-value < 0.001). CONCLUSIONS: The global FEA-computed fracture risk index increased hip fracture risk prediction accuracy in males.

CLCLSA: Cross-omics linked embedding with contrastive learning and self attention for integration with incomplete multi-omics data.

Integration of heterogeneous and high-dimensional multi-omics data is becoming increasingly important in understanding etiology of complex genetic diseases. Each omics technique only provides a limited view of the underlying biological process and integrating heterogeneous omics layers simultaneously would lead to a more comprehensive and detailed understanding of diseases and phenotypes. However, one obstacle faced when performing multi-omics data integration is the existence of unpaired multi-omics data due to instrument sensitivity and cost. Studies may fail if certain aspects of the subjects are missing or incomplete. In this paper, we propose a deep learning method for multi-omics integration with incomplete data by Cross-omics Linked unified embedding with Contrastive Learning and Self Attention (CLCLSA). Utilizing complete multi-omics data as supervision, the model employs cross-omics autoencoders to learn the feature representation across different types of biological data. The multi-omics contrastive learning is employed, which maximizes the mutual information between different types of omics. In addition, the feature-level self-attention and omics-level self-attention are employed to dynamically identify the most informative features for multi-omics data integration. Finally, a Softmax classifier is employed to perform multi-omics data classification. Extensive experiments were conducted on four public multi-omics datasets. The experimental results indicate that our proposed CLCLSA produces promising results in multi-omics data classification using both complete and incomplete multi-omics data.

Multi-View Variational Autoencoder for Missing Value Imputation in Untargeted Metabolomics.

Background: Missing data is a common challenge in mass spectrometry-based metabolomics, which can lead to biased and incomplete analyses. The integration of whole-genome sequencing (WGS) data with metabolomics data has emerged as a promising approach to enhance the accuracy of data imputation in metabolomics studies. Method: In this study, we propose a novel method that leverages the information from WGS data and reference metabolites to impute unknown metabolites. Our approach utilizes a multi-view variational autoencoder to jointly model the burden score, polygenetic risk score (PGS), and linkage disequilibrium (LD) pruned single nucleotide polymorphisms (SNPs) for feature extraction and missing metabolomics data imputation. By learning the latent representations of both omics data, our method can effectively impute missing metabolomics values based on genomic information. Results: We evaluate the performance of our method on empirical metabolomics datasets with missing values and demonstrate its superiority compared to conventional imputation techniques. Using 35 template metabolites derived burden scores, PGS and LD-pruned SNPs, the proposed methods achieved R2-scores > 0.01 for 71.55% of metabolites. Conclusion: The integration of WGS data in metabolomics imputation not only improves data completeness but also enhances downstream analyses, paving the way for more comprehensive and accurate investigations of metabolic pathways and disease associations. Our findings offer valuable insights into the potential benefits of utilizing WGS data for metabolomics data imputation and underscore the importance of leveraging multi-modal data integration in precision medicine research.

GTP Signaling Links Metabolism, DNA Repair, and Responses to Genotoxic Stress.

How cell metabolism regulates DNA repair is incompletely understood. Here, we define a GTP-mediated signaling cascade that links metabolism to DNA repair and has significant therapeutic implications. GTP, but not other nucleotides, regulates the activity of Rac1, a guanine nucleotide-binding protein, which promotes the dephosphorylation of serine 323 on Abl-interactor 1 (Abi-1) by protein phosphatase 5 (PP5). Dephosphorylated Abi-1, a protein previously not known to activate DNA repair, promotes nonhomologous end joining. In patients and mouse models of glioblastoma, Rac1 and dephosphorylated Abi-1 mediate DNA repair and resistance to standard-of-care genotoxic treatments. The GTP-Rac1-PP5-Abi-1 signaling axis is not limited to brain cancer, as GTP supplementation promotes DNA repair and Abi-1-S323 dephosphorylation in nonmalignant cells and protects mouse tissues from genotoxic insult. This unexpected ability of GTP to regulate DNA repair independently of deoxynucleotide pools has important implications for normal physiology and cancer treatment. SIGNIFICANCE: A newly described GTP-dependent signaling axis is an unexpected link between nucleotide metabolism and DNA repair. Disrupting this pathway can overcome cancer resistance to genotoxic therapy while augmenting it can mitigate genotoxic injury of normal tissues. This article is featured in Selected Articles from This Issue, p. 5.

Multi-view information fusion using multi-view variational autoencoder to predict proximal femoral fracture load.

Background: Hip fracture occurs when an applied force exceeds the force that the proximal femur can support (the fracture load or "strength") and can have devastating consequences with poor functional outcomes. Proximal femoral strengths for specific loading conditions can be computed by subject-specific finite element analysis (FEA) using quantitative computerized tomography (QCT) images. However, the radiation and availability of QCT limit its clinical usability. Alternative low-dose and widely available measurements, such as dual energy X-ray absorptiometry (DXA) and genetic factors, would be preferable for bone strength assessment. The aim of this paper is to design a deep learning-based model to predict proximal femoral strength using multi-view information fusion. Results: We developed new models using multi-view variational autoencoder (MVAE) for feature representation learning and a product of expert (PoE) model for multi-view information fusion. We applied the proposed models to an in-house Louisiana Osteoporosis Study (LOS) cohort with 931 male subjects, including 345 African Americans and 586 Caucasians. We performed genome-wide association studies (GWAS) to select 256 genetic variants with the lowest p-values for each proximal femoral strength and integrated whole genome sequence (WGS) features and DXA-derived imaging features to predict proximal femoral strength. The best prediction model for fall fracture load was acquired by integrating WGS features and DXA-derived imaging features. The designed models achieved the mean absolute percentage error of 18.04%, 6.84% and 7.95% for predicting proximal femoral fracture loads using linear models of fall loading, nonlinear models of fall loading, and nonlinear models of stance loading, respectively. Conclusion: The proposed models are capable of predicting proximal femoral strength using WGS features and DXA-derived imaging features. Though this tool is not a substitute for predicting FEA using QCT images, it would make improved assessment of hip fracture risk more widely available while avoiding the increased radiation exposure from QCT.

Rewiring of cortical glucose metabolism fuels human brain cancer growth.

The brain avidly consumes glucose to fuel neurophysiology. Cancers of the brain, such as glioblastoma (GBM), lose aspects of normal biology and gain the ability to proliferate and invade healthy tissue. How brain cancers rewire glucose utilization to fuel these processes is poorly understood. Here we perform infusions of 13 C-labeled glucose into patients and mice with brain cancer to define the metabolic fates of glucose-derived carbon in tumor and cortex. By combining these measurements with quantitative metabolic flux analysis, we find that human cortex funnels glucose-derived carbons towards physiologic processes including TCA cycle oxidation and neurotransmitter synthesis. In contrast, brain cancers downregulate these physiologic processes, scavenge alternative carbon sources from the environment, and instead use glucose-derived carbons to produce molecules needed for proliferation and invasion. Targeting this metabolic rewiring in mice through dietary modulation selectively alters GBM metabolism and slows tumor growth. Significance: This study is the first to directly measure biosynthetic flux in both glioma and cortical tissue in human brain cancer patients. Brain tumors rewire glucose carbon utilization away from oxidation and neurotransmitter production towards biosynthesis to fuel growth. Blocking these metabolic adaptations with dietary interventions slows brain cancer growth with minimal effects on cortical metabolism.

The influence of arm positions on mechanical dyssynchrony measured by gated myocardial perfusion imaging.

Background: In routine procedures, patient's arms are positioned above their heads to avoid potential attenuation artifacts and reduced image quality during gated myocardial perfusion imaging (G-MPI). However, it is difficult to achieve this action in the acute period following pacemaker implantation. This study aimed to explore the influence of arm positioning on myocardial perfusion imaging (MPI) in different types of heart disease. Methods: This study was conducted retrospectively. A total of 123 patients were enrolled and underwent resting G-MPI using a standard protocol with arms positioned above their heads and again with their arms at their sides. All individuals were divided into 3 groups: the normal group, the obstructive coronary artery disease (O-CAD) group, and the dilated cardiomyopathy (DCM) group. The G-MPI data were measured by QGS software and Emory Reconstruction Toolbox, including left ventricular ejection fraction (LVEF), end-diastolic volume (EDV), end-systolic volume (ESV), extent, total perfusion deficit (TPD), summed rest score (SRS), scar burden, phase standard deviation (SD), and phase histogram bandwidth (BW). Results: In total, extent, TPD, EDV, ESV, LVEF, systolic SD, systolic BW, diastolic SD, and diastolic BW were all significantly different between the 2 arm positions (all P<0.01). On the Bland-Altman analysis, both EDV and ESV with the arm-down position were significantly underestimated (P<0.001). Meanwhile, TPD, extent, and LVEF with the arm-down position were significantly overestimated (P<0.05). Systolic SD, systolic BW, diastolic SD, and diastolic BW were systematically overestimated (P<0.001). In the DCM group (n=52), EDV, ESV, systolic SD, systolic BW, diastolic SD, and diastolic BW were identified as significantly different by the paired t-test between the 2 arm positions (P<0.05). In the O-CAD group (n=32), scar burden, ESV, LVEF, and diastolic BW were significantly different between the 2 arm positions (P<0.05). Conclusions: Systolic and diastolic dyssynchrony parameters and most left ventricular (LV) functional parameters were significantly influenced by arm position in both normal individuals and patients with heart failure (HF) with different pathophysiologies. More attention should be given to LV dyssynchrony data during clinical evaluation of cardiac resynchronization therapy (CRT) implantation procedure.

Spatial-temporal V-Net for automatic segmentation and quantification of right ventricle on gated myocardial perfusion SPECT images.

BACKGROUND: Functional assessment of right ventricle (RV) using gated myocardial perfusion single-photon emission computed tomography (MPS) heavily relies on the precise extraction of right ventricular contours. PURPOSE: In this paper, we present a new deep-learning-based model integrating both the spatial and temporal features in gated MPS images to perform the segmentation of the RV epicardium and endocardium. METHODS: By integrating the spatial features from each cardiac frame of the gated MPS and the temporal features from the sequential cardiac frames of the gated MPS, we developed a Spatial-Temporal V-Net (ST-VNet) for automatic extraction of RV endocardial and epicardial contours. In the ST-VNet, a V-Net is employed to hierarchically extract spatial features, and convolutional long-term short-term memory (ConvLSTM) units are added to the skip-connection pathway to extract the temporal features. The input of the ST-VNet is ECG-gated sequential frames of the MPS images and the output is the probability map of the epicardial or endocardial masks. A Dice similarity coefficient (DSC) loss which penalizes the discrepancy between the model prediction and the manual annotation was adopted to optimize the segmentation model. RESULTS: Our segmentation model was trained and validated on a retrospective dataset with 45 subjects, and the cardiac cycle of each subject was divided into eight gates. The proposed ST-VNet achieved a DSC of 0.8914 and 0.8157 for the RV epicardium and endocardium segmentation, respectively. The mean absolute error, the mean squared error, and the Pearson correlation coefficient of the RV ejection fraction (RVEF) between the manual annotation and the model prediction were 0.0609, 0.0830, and 0.6985. CONCLUSION: Our proposed ST-VNet is an effective model for RV segmentation. It has great promise for clinical use in RV functional assessment.

Adaptive rewiring of purine metabolism promotes treatment resistance in H3K27M-mutant diffuse midline glioma.

Background: Diffuse midline gliomas (DMG), including diffuse intrinsic pontine gliomas (DIPGs), are a fatal form of brain cancer. These tumors often carry a driver mutation on histone H3 converting lysine 27 to methionine (H3K27M). DMG-H3K27M are characterized by altered metabolism and resistance to standard of care radiation (RT), but how the H3K27M mediates the metabolic response to radiation and consequent treatment resistance is uncertain. Methods: We performed metabolomics on irradiated and untreated H3K27M isogenic DMG cell lines and observed an H3K27M-specific enrichment for purine synthesis pathways. We profiled the expression of purine synthesis enzymes in publicly available patient data and in our models, quantified purine synthetic flux using stable isotope tracing, and characterized the in vitro and in vivo response to de novo and salvage purine synthesis inhibition in combination with RT. Results: DMG-H3K27M cells activate purine metabolism in an H3K27M-specific fashion. In the absence of genotoxic treatment, H3K27M-expressing cells have higher relative activity of de novosynthesis and lower activity of purine salvage due to decreased expression of the purine salvage enzymes. Inhibition of de novo synthesis radiosensitized DMG-H3K27M cells in vitro and in vivo. Irradiated H3K27M cells adaptively upregulate purine salvage enzyme expression and pathway activity. Silencing the rate limiting enzyme in purine salvage, hypoxanthine guanine phosphoribosyl transferase (HGPRT) when combined with radiation markedly suppressed DMG-H3K27M tumor growth in vivo. Conclusions: H3K27M expressing cells rely on de novo purine synthesis but adaptively upregulate purine salvage in response to RT. Inhibiting purine salvage may help overcome treatment resistance in DMG-H3K27M tumors.

Identification of circRNAs and circRNA-mRNA network of Epinephelus coioides during Singapore grouper iridovirus infection.

Circular RNA (circRNA), one of the important non-coding RNA molecules with a closed-loop structure, plays a key regulatory role in cell processing. In this study, circRNAs of Epinephelus coioides, an important marine cultured fish in China, were isolated and characterized, and the network of circRNAs and mRNA was explored during Singapore grouper iridovirus (SGIV) infection, one of the most important double stranded DNA virus pathogens of marine fish. 10 g of raw data was obtained by high-throughput sequencing, and 2599 circRNAs were classified. During SGIV infection, 123 and 37 circRNAs occurred differential expression in spleen and spleen cells, indicating that circRNAs would be involved in the viral infection. GO annotation and KEGG demonstrated that circRNAs could target E. coioides genes to regulate cell activity and the activation of immune factors. The results provide some insights into the circRNAs mediated immune regulatory network during bony fish virus infection.

EAGMN: Coronary artery semantic labeling using edge attention graph matching network.

Coronary artery disease (CAD) is one of the primary causes leading deaths worldwide. The presence of atherosclerotic lesions in coronary arteries is the underlying pathophysiological basis of CAD, and accurate extraction of individual arterial branches using invasive coronary angiography (ICA) is crucial for stenosis detection and CAD diagnosis. However, deep-learning-based models face challenges in generating semantic segmentation for coronary arteries due to the morphological similarity among different types of arteries. To address this challenge, we propose an innovative approach called the Edge Attention Graph Matching Network (EAGMN) for coronary artery semantic labeling. Inspired by the learning process of interventional cardiologists in interpreting ICA images, our model compares arterial branches between two individual graphs generated from different ICAs. We begin with extracting individual graphs based on the vascular tree obtained from the ICA. Each node in the individual graph represents an arterial segment, and the EAGMN aims to learn the similarity between nodes from the two individual graphs. By converting the coronary artery semantic segmentation task into a graph node similarity comparison task, identifying the node-to-node correspondence would assign semantic labels for each arterial branch. More specifically, the EAGMN utilizes the association graph constructed from the two individual graphs as input. A graph attention module is employed for feature embedding and aggregation, while a decoder generates the linear assignment for node-to-node semantic mapping. Based on the learned node-to-node relationships, unlabeled coronary arterial segments are classified using the labeled coronary arterial segments, thereby achieving semantic labeling. A dataset with 263 labeled ICAs is used to train and validate the EAGMN. Experimental results indicate the EAGMN achieved a weighted accuracy of 0.8653, a weighted precision of 0.8656, a weighted recall of 0.8653 and a weighted F1-score of 0.8643. Furthermore, we employ ZORRO to provide interpretability and explainability of the graph matching for artery semantic labeling. These findings highlight the potential of the EAGMN for accurate and efficient coronary artery semantic labeling using ICAs. By leveraging the inherent characteristics of ICAs and incorporating graph matching techniques, our proposed model provides a promising solution for improving CAD diagnosis and treatment.