Artificial intelligence assistance for fetal development: evaluation of an automated software for biometry measurements in the mid-trimester.

BACKGROUND: This study presents CUPID, an advanced automated measurement software based on Artificial Intelligence (AI), designed to evaluate nine fetal biometric parameters in the mid-trimester. Our primary objective was to assess and compare the CUPID performance of experienced senior and junior radiologists. MATERIALS AND METHODS: This prospective cross-sectional study was conducted at Shenzhen University General Hospital between September 2022 and June 2023, and focused on mid-trimester fetuses. All ultrasound images of the six standard planes, that enabled the evaluation of nine biometric measurements, were included to compare the performance of CUPID through subjective and objective assessments. RESULTS: There were 642 fetuses with a mean (±SD) age of 22 ± 2.82 weeks at enrollment. In the subjective quality assessment, out of 642 images representing nine biometric measurements, 617-635 images (90.65-96.11%) of CUPID caliper placements were determined to be accurately placed and did not require any adjustments. Whereas, for the junior category, 447-691 images (69.63-92.06%) were determined to be accurately placed and did not require any adjustments. In the objective measurement indicators, across all nine biometric parameters and estimated fetal weight (EFW), the intra-class correlation coefficients (ICC) (0.843-0.990) and Pearson correlation coefficients (PCC) (0.765-0.978) between the senior radiologist and CUPID reflected good reliability compared with the ICC (0.306-0.937) and PCC (0.566-0.947) between the senior and junior radiologists. Additionally, the mean absolute error (MAE), percentage error (PE), and average error in days of gestation were lower between the senior and CUPID compared to the difference between the senior and junior radiologists. The specific differences are as follows: MAE (0.36-2.53 mm, 14.67 g) compared to (0.64- 8.13 mm, 38.05 g), PE (0.94-9.38%) compared to (1.58-16.04%), and average error in days (3.99-7.92 days) compared to (4.35-11.06 days). In the time-consuming task, CUPID only takes 0.05-0.07 s to measure nine biometric parameters, while senior and junior radiologists require 4.79-11.68 s and 4.95-13.44 s, respectively. CONCLUSIONS: CUPID has proven to be highly accurate and efficient software for automatically measuring fetal biometry, gestational age, and fetal weight, providing a precise and fast tool for assessing fetal growth and development.

Glutamine Metabolism Promotes Renal Fibrosis through Regulation of Mitochondrial Energy Generation and Mitochondrial Fission.

Fibroblast activation and proliferation is an essential phase in the progression of renal fibrosis. Despite the recognized significance of glutamine metabolism in cellular growth and proliferation, its precise pathophysiological relevance in renal fibrosis remains uncertain. Therefore, this study aims to investigate the involvement of glutamine metabolism in fibroblast activation and its possible mechanism. Our findings highlight the importance of glutamine metabolism in fibroblast activation and reveal that patients with severe fibrosis exhibit elevated serum glutamine levels and increased expression of kidney glutamine synthetase. Furthermore, the deprivation of glutamine metabolism in vitro and in vivo could inhibit fibroblast activation, thereby ameliorating renal fibrosis. It was also detected that glutamine metabolism is crucial for maintaining mitochondrial function and morphology. These effects may partially depend on the metabolic intermediate α-ketoglutaric acid. Moreover, glutamine deprivation led to upregulated mitochondrial fission in fibroblasts and the activation of the mammalian target of rapamycin / mitochondrial fission process 1 / dynamin-related protein 1 pathway. Thus, these results provide compelling evidence that the modulation of glutamine metabolism initiates the regulation of mitochondrial function, thereby facilitating the progression of renal fibrosis. Consequently, targeting glutamine metabolism emerges as a novel and promising avenue for therapeutic intervention and prevention of renal fibrosis.

Isolation, identification, and pathogenicity of Pseudomonas glycinae causing ginseng bacterial soft rot in China.

By tissue separation method, tie-back experiment, and hypersensitive response test in potato, strain XJFL-1 was isolated and identified as the pathogen of ginseng bacterial soft rot in Liaoning Provence, China. The morphological characteristics of XJFL-1 were conformed to the Pseudomonads genus. Microbial fatty acid identification showed the principal cellular fatty acid traits of XLFJ-1 corresponded with Pseudomonas spp. API 50CH test results allowed the differentiation of strain XJFL-1 and MS586T from other closely related Pseudomonas species. The molecular identification, including 16S rRNA analysis and multilocus sequence typing (MLST) analysis, showed that XJFL-1 was in the same branch as P. glycinae MS586T. The genome of XJFL-1 was 6,296,473 bp, with an average guanine/cytosine (G + C) content of 60.72 %. Comparative genomics analysis using ANIb and GGDC algorithms indicated that the maximum value was observed between XJFL-1 and P. glycinae MS586T. The above morphological, cell morphology, and molecular biological identification results supported to identification of XJFL-1 as P. glycinae. This is the first report of P. glycinae as the plant pathogen causing ginseng bacterial root rot in China, which complements the biological significance of the species to a certain extent, enriches the pathogens of ginseng bacterial soft rot, and provides a theoretical basis for further investigation.

The HIF-1/ BNIP3 pathway mediates mitophagy to inhibit the pyroptosis of fibroblast-like synoviocytes in rheumatoid arthritis.

BACKGROUND: Synovial hypoxia, a critical pathological characteristic of rheumatoid arthritis (RA), significantly contributes to synovitis and synovial hyperplasia. In response to hypoxic conditions, fibroblast-like synoviocytes (FLS) undergo adaptive changes involving gene expression modulation, with hypoxia-inducible factors (HIF) playing a pivotal role. The regulation of BCL2/adenovirus e1B 19 kDa protein interacting protein 3 (BNIP3) and nucleotide-binding oligomerization segment-like receptor family 3 (NLRP3) expression has been demonstrated to be regulated by HIF-1. The objective of this study was to examine the molecular mechanism that contributes to the aberrant activation of FLS in response to hypoxia. Specifically, the interaction between BNIP3-mediated mitophagy and NLRP3-mediated pyroptosis was conjointly highlighted. METHODS: The research methodology employed Western blot and immunohistochemistry techniques to identify the occurrence of mitophagy in synovial tissue affected by RA. Additionally, the levels of mitophagy under hypoxic conditions were assessed using Western blot, immunofluorescence, quantitative polymerase chain reaction (qPCR), and CUT&Tag assays. Pyroptosis was observed through electron microscopy, fluorescence microscopy, and Western blot analysis. Furthermore, the quantity of reactive oxygen species (ROS) was measured. The silencing of HIF-1α and BNIP3 was achieved through the transfection of short hairpin RNA (shRNA) into cells. RESULTS: In the present study, a noteworthy increase in the expression of BNIP3 and LC3B was observed in the synovial tissue of patients with RA. Upon exposure to hypoxia, FLS of RA exhibited BNIP3-mediated mitophagy and NLRP3 inflammasome-mediated pyroptosis. It appears that hypoxia regulates the expression of BNIP3 and NLRP3 through the transcription factor HIF-1. Additionally, the activation of mitophagy has been observed to effectively inhibit hypoxia-induced pyroptosis by reducing the intracellular levels of ROS. CONCLUSION: In summary, the activation of FLS in RA patients under hypoxic conditions involves both BNIP3-mediated mitophagy and NLRP3 inflammasome-mediated pyroptosis. Additionally, mitophagy can suppress hypoxia-induced FLS pyroptosis by eliminating ROS and inhibiting the HIF-1α/NLRP3 pathway.

LaVO4: Eu3+ nano-islands onto silica for achieving fluorescence enhancement and their detection of Fe3+ ions and anti-counterfeiting applications.

Rare earth (RE) composite fluorescent materials are favored by researchers in the field of anti-counterfeiting and ion sensing due to their fascinating optical properties. Ultra-small RE fluorescent nanoparticles are anchored on inorganic carriers by a simple preparation method to improve luminous intensity and hydrophilicity, which has not been explored yet. Herein, LaVO4: Eu3+ nano-islands anchored on silica with high fluorescence intensity and easy formation of stable colloidal solution is designed. Through a simple and mild hydrothermal approach, ultra-small LaVO4: Eu3+ nano-islands are highly dispersed on the surface of hierarchical hollow silica sphere (HHSS) to expose more luminescent centers. Remarkably, the stable HHSS@LaVO4: Eu3+ colloidal solution displayed highly sensitive and selective sensor for Fe3+ ions. The "island-sea synergy" structure formed by the LaVO4: Eu3+ nano-islands and the surrounding silica surface makes HHSS@LaVO4: Eu3+ to be an outstanding sensor for the effective detection of iron ions in water. In addition, HHSS@LaVO4: Eu3+ phosphor exhibit unique properties for anti-counterfeiting and encryption applications. These findings provide a promising strategy for the carrierisation of RE luminescent materials to improve optical properties and enable broader applications.

hIgD-Fc-Ig fusion protein regulates T cell functions by inhibiting TCR signaling pathway in adjuvant arthritis rats.

This study aimed to investigate the effect of hIgD-Fc-Ig on TCR-Lck-Erk activated by IgD in adjuvant arthritis (AA) rats. Wistar rats were divided into the normal, AA model, hIgD-Fc-Ig (1 mg/kg, 3 mg/kg and 9 mg/kg) and Etanercept (3 mg/kg) groups. The overall index of AA rats was measured every 3 days. The pathologic examination of knee joints and the proliferation of the spleen and thymus of AA rats were detected by H&E staining and CCK-8. The blood flow signal of knee joints of experimental rats was examined by US. The articular bone injury was detected by X-ray. The changes in PBMCs and spleen T cell subsets were detected by flow cytometry. The expression of CD3ε, p-Lck, p-Zap70, Ras, and p-Erk in rat spleens was detected by immunofluorescence and WB. Rat spleen T cells or Jurkat cells treated by IgD to observe the effect of hIgD-Fc-Ig on TCR and its downstream protein expression. The results showed that hIgD-Fc-Ig had a therapeutic effect on AA rats by reducing the secondary inflammation, improving pathological changes. hIgD-Fc-Ig can reduce the ratio of Th cells of PBMCs of AA rats, the ratio of Th, Th1, Th17 cells and increase the ratio of Th2, Treg cells of AA rat spleens. hIgD-Fc-Ig could down-regulate the expression of CD3ε, p-Lck, p-Zap70, Ras, p-Erk in vivo or in vitro. In conclusion, hIgD-Fc-Ig could alleviate the symptoms of AA rats and regulate T cells through TCR-Lck-Erk signaling pathway and maybe a new promising biological agent for RA.

Avoiding Unnecessary Systematic Biopsy in Clinically Significant Prostate Cancer: Comparison Between MRI-Based Radiomics Model and PI-RADS Category.

BACKGROUND: MRI-targeted biopsy (MRTB) improves the clinically significant prostate cancer (csPCa) detection rate with fewer biopsy cores in men with suspected PCa. However, whether concurrent systematic biopsy (SB) can be avoided in patients undergoing MRTB remains unclear. PURPOSE: To evaluate the potential value of MRI-based radiomics models in avoiding unnecessary SB in biopsy-naïve patients. STUDY TYPE: Retrospective. POPULATION: A total of 226 patients (mean age 66.6 ± 9.02 years) with suspicion of PCa (PI-RADS score ≥ 3) and received combined cognitive MRTB with SB were retrospectively recruited and randomly divided into training (N = 180) and test (N = 46) cohorts at an 8:2 ratio. FIELD STRENGTH/SEQUENCE: A 3.0 T, biparametric MRI (bpMRI) including T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) map. ASSESSMENT: The whole prostate gland (PG) and the index lesion (IL) were delineated. Three radiomics models of bpMRIPG , bpMRIIL , and bpMRIPG+IL were constructed, respectively, and the performance of each radiomics model was compared with that of PI-RADS assessment. STATISTICAL TESTS: The least absolute shrinkage and selection operator (LASSO) regression method was used to select texture features. The area under the curve (AUC) and decision curve analysis were used to estimate the models. RESULTS: The bpMRIPG+IL radiomics model exhibited good discrimination, calibration, and net benefits, which would reduce the SB biopsy in 71.2% and 71.4% of men with PI-RADS ≥ 5 lesions in the training and test cohorts, respectively. DATA CONCLUSION: A bpMRIPG+IL radiomics model may outperform PI-RADS category in help reducing unnecessary SB in biopsy-naïve patients. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 6.

Machine learning-based combined nomogram for predicting the risk of pulmonary invasive fungal infection in severely immunocompromised patients.

Background: Early and accurate diagnosis of invasive fungal infection (IFI) is pivotal for the initiation of effective antifungal therapy for patients with hematologic malignancies. Methods: This retrospective study involved 235 patients with hematologic malignancies and pulmonary infections diagnosed as IFIs (n=118) or bacterial pneumonia (n=117). Patients were randomly divided into training (n=188) and validation (n=47) datasets. Four feature selection methods with nine classifiers were implemented to select the optimal machine learning (ML) model using five-fold cross-validation. A radiomic signature was constructed using a linear ML algorithm, and a radiomic score (Radscore) was calculated. The combined model was developed with the Radscore, the significant clinical and radiologic factors were selected using multivariable logistic regression, and the results were presented as a clinical radiomic nomogram. A prospective pilot study was also conducted to compare the classification performance of the combined nomogram with practicing radiologists. Results: Significant differences were found in the Radscore between IFI and bacterial pneumonia patients in the training (0.683 vs. -0.724, P<0.001) and validation set (0.353 vs. -0.717, P=0.002). The combined model showed good discrimination performance in the validation cohort [area under the curve (AUC) =0.844] and outperformed the clinical (AUC =0.696) and radiomics (AUC =0.767) model alone (both P<0.05). Conclusions: The clinical radiomic nomogram can serve as a promising predictive tool for IFI in patients with hematologic malignancies.

A Cascaded Multi-Task Generative Framework for Detecting Aortic Dissection on 3-D Non-Contrast-Enhanced Computed Tomography.

Contrast-enhanced computed tomography (CE-CT) is the gold standard for diagnosing aortic dissection (AD). However, contrast agents can cause allergic reactions or renal failure in some patients. Moreover, AD diagnosis by radiologists using non-contrast-enhanced CT (NCE-CT) images has poor sensitivity. To address this issue, we propose a novel cascaded multi-task generative framework for AD detection using NCE-CT volumes. The framework includes a 3D nnU-Net and a 3D multi-task generative architecture (3D MTGA). Specifically, the 3D nnU-Net was employed to segment aortas from NCE-CT volumes. The 3D MTGA was then employed to simultaneously synthesize CE-CT volumes, segment true & false lumen, and classify the patient as AD or non-AD. A theoretical formulation demonstrated that the 3D MTGA could increase the Jensen-Shannon Divergence (JSD) between AD and non-AD for each NCE-CT volume, thus indirectly improving the AD detection performance. Experiments also showed that the proposed framework could achieve an average accuracy of 0.831, a sensitivity of 0.938, and an F1-score of 0.847 in comparison with seven state-of-the-art classification models used by three radiologists with junior, intermediate, and senior experiences, respectively. The experimental results indicate that the proposed framework obtains superior performance to state-of-the-art models in AD detection. Thus, it has great potential to reduce the misdiagnosis of AD using NCE-CT in clinical practice. The source codes and supplementary materials for our framework are available at https://github.com/yXiangXiong/CMTGF.

Genome-Resolved Metagenomic Analysis of Groundwater: Insights into Arsenic Mobilization in Biogeochemical Interaction Networks.

High-arsenic (As) groundwaters, a worldwide issue, are critically controlled by multiple interconnected biogeochemical processes. However, there is limited information on the complex biogeochemical interaction networks that cause groundwater As enrichment in aquifer systems. The western Hetao basin was selected as a study area to address this knowledge gap, offering an aquifer system where groundwater flows from an oxidizing proximal fan (low dissolved As) to a reducing flat plain (high dissolved As). The key microbial interaction networks underpinning the biogeochemical pathways responsible for As mobilization along the groundwater flow path were characterized by genome-resolved metagenomic analysis. Genes associated with microbial Fe(II) oxidation and dissimilatory nitrate reduction were noted in the proximal fan, suggesting the importance of nitrate-dependent Fe(II) oxidation in immobilizing As. However, genes catalyzing microbial Fe(III) reduction (omcS) and As(V) detoxification (arsC) were highlighted in groundwater samples downgradient flow path, inferring that reductive dissolution of As-bearing Fe(III) (oxyhydr)oxides mobilized As(V), followed by enzymatic reduction to As(III). Genes associated with ammonium oxidation (hzsABC and hdh) were also positively correlated with Fe(III) reduction (omcS), suggesting a role for the Feammox process in driving As mobilization. The current study illustrates how genomic sequencing tools can help dissect complex biogeochemical systems, and strengthen biogeochemical models that capture key aspects of groundwater As enrichment.

Preparation and adsorption performance of functionalization cellulose-based composite aerogel.

Herein, functionalization cellulose-based composite aerogels with the addition of carboxyl cellulose nanofibers (CNF), montmorillonite (MMT) and polyethyleneimine (PEI) were fabricated by solution blending and freeze-drying technology. MMT was blended into the cellulose framework as a reinforcing agent. PEI combined with cellulose through amidation reaction, and the synergism of hydrogen bond and chemical bond helped the CNF/MMT/PEI composite aerogels (CMP) with good mechanical properties. The morphology, chemical structure and thermal stability of the CMP were characterized. The adsorption properties and mechanism of the CMP were discussed, using Congo red (CR) dye as an adsorbate. The results showed that the CMP formed a three-dimensional network structure with abundant pores. The addition of PEI regulated the surface charge distribution of cellulose and improved the adsorption performance of CMP for CR with the adsorption capacity of 3114 mg/g calculated by the Langmuir model. The adsorption process of CMP-30 for CR was more in line with the pseudo-second-order kinetic model and Langmuir isotherm model, indicating chemical adsorption of a single molecular layer. After functionalized by octadecyl trichlorosilane (OTS), the contact angle of the aerogel surface was 151.80°. Meanwhile, the CMP-30 was transformed from hydrophilic and lipophilic properties to hydrophobic and lipophilic properties.

[Research on real-time detection system of catheter delivering force in vascular interventional robots].

In existing vascular interventional surgical robots, it is difficult to accurately detect the delivery force of the catheter/guidewire at the slave side. Aiming to solve this problem, a real-time force detection system was designed for vascular interventional surgical (VIS) robots based on catheter push force. Firstly, the transfer process of catheter operating forces in the slave end of the interventional robot was analyzed and modeled, and the design principle of the catheter operating force detection system was obtained. Secondly, based on the principle of stress and strain, a torque sensor was designed and integrated into the internal transmission shaft of the slave end of the interventional robot, and a data acquisition and processing system was established. Thirdly, an ATI high-precision torque sensor was used to build the experimental platform, and the designed sensor was tested and calibrated. Finally, sensor test experiments under ideal static/dynamic conditions and simulated catheter delivery tests based on actual human computed tomography (CT) data and vascular model were carried out. The results showed that the average relative detection error of the designed sensor system was 1.26% under ideal static conditions and 1.38% under ideal dynamic stability conditions. The system can detect on-line catheter operation force at high precision, which is of great significance towards improving patient safety in interventional robotic surgery.

The ROS/GRK2/HIF-1α/NLRP3 Pathway Mediates Pyroptosis of Fibroblast-Like Synoviocytes and the Regulation of Monomer Derivatives of Paeoniflorin.

Hypoxia is an important factor in the development of synovitis in rheumatoid arthritis (RA). The previous study of the research group found that monomeric derivatives of paeoniflorin (MDP) can alleviate joint inflammation in adjuvant-induced arthritis (AA) rats by inhibiting macrophage pyroptosis. This study revealed increased levels of hypoxia-inducible factor- (HIF-) 1α and N-terminal p30 fragment of GSDMD (GSDMD-N) in fibroblast-like synoviocytes (FLS) of RA patients and AA rats, while MDP significantly inhibited their expression. Subsequently, FLS were exposed to a hypoxic environment or treated with cobalt ion in vitro. Western blot and immunofluorescence analysis showed increased expression of G protein-coupled receptor kinase 2 (GRK2), HIF-1α, nucleotide-binding oligomerization segment-like receptor family 3 (NLRP3), ASC, caspase-1, cleaved-caspase-1, and GSDMD-N. Electron microscopy revealed FLS pyroptosis after exposure in hypoxia. Next, corresponding shRNAs were transferred into FLS to knock down hypoxia-inducible factor- (HIF-) 1α, and in turn, NLRP3 and western blot results confirmed the same. The enhanced level of GSDMD was reversed under hypoxia by inhibiting NLRP3 expression. Knockdown and overexpression of GRK2 in FLS revealed GRK2 to be a positive regulator of HIF-1α. Levels of GRK2 and HIF-1α were inhibited by eliminating excess reactive oxygen species (ROS). Furthermore, MDP reduced FLS pyroptosis through targeted inhibition of GRK2 phosphorylation. According to these findings, hypoxia induces FLS pyroptosis through the ROS/GRK2/HIF-1α/NLRP3 pathway, while MDP regulates this pathway to reduce FLS pyroptosis.

Automatic machine learning based on native T1 mapping can identify myocardial fibrosis in patients with hypertrophic cardiomyopathy.

OBJECTIVES: To investigate the feasibility of automatic machine learning (autoML) based on native T1 mapping to predict late gadolinium enhancement (LGE) status in hypertrophic cardiomyopathy (HCM). METHODS: Ninety-one HCM patients and 44 healthy controls who underwent cardiovascular MRI were enrolled. The native T1 maps of HCM patients were classified as LGE ( +) or LGE (-) based on location-matched LGE images. An autoML pipeline was implemented using the tree-based pipeline optimization tool (TPOT) for 3 binary classifications: LGE ( +) and LGE (-), LGE (-) and control, and HCM and control. TPOT modeling was repeated 10 times to obtain the optimal model for each classification. The diagnostic performance of the best models by slice and by case was evaluated using sensitivity, specificity, accuracy, and microaveraged area under the curve (AUC). RESULTS: Ten prediction models were generated by TPOT for each of the 3 binary classifications. The diagnostic accuracy obtained with the best pipeline in detecting LGE status in the testing cohort of HCM patients was 0.80 by slice and 0.79 by case. In addition, the TPOT model also showed discriminability between LGE (-) patients and control (accuracy: 0.77 by slice; 0.78 by case) and for all HCM patients and controls (accuracy: 0.88 for both). CONCLUSIONS: Native T1 map analysis based on autoML correlates with LGE ( +) or (-) status. The TPOT machine learning algorithm could be a promising method for predicting myocardial fibrosis, as reflected by the presence of LGE in HCM patients without the need for late contrast-enhanced MRI sequences. KEY POINTS: • The tree-based pipeline optimization tool (TPOT) is a machine learning algorithm that could help predict late gadolinium enhancement (LGE) status in patients with hypertrophic cardiomyopathy. • The TPOT could serve as an adjuvant method to detect LGE by using information from native T1 maps, thus avoiding the need for contrast agent. • The TPOT also detects native T1 map alterations in LGE-negative patients with hypertrophic cardiomyopathy.

A fully automatic artificial intelligence-based CT image analysis system for accurate detection, diagnosis, and quantitative severity evaluation of pulmonary tuberculosis.

OBJECTIVES: An accurate and rapid diagnosis is crucial for the appropriate treatment of pulmonary tuberculosis (TB). This study aims to develop an artificial intelligence (AI)-based fully automated CT image analysis system for detection, diagnosis, and burden quantification of pulmonary TB. METHODS: From December 2007 to September 2020, 892 chest CT scans from pathogen-confirmed TB patients were retrospectively included. A deep learning-based cascading framework was connected to create a processing pipeline. For training and validation of the model, 1921 lesions were manually labeled, classified according to six categories of critical imaging features, and visually scored regarding lesion involvement as the ground truth. A "TB score" was calculated based on a network-activation map to quantitively assess the disease burden. Independent testing datasets from two additional hospitals (dataset 2, n = 99; dataset 3, n = 86) and the NIH TB Portals (n = 171) were used to externally validate the performance of the AI model. RESULTS: CT scans of 526 participants (mean age, 48.5 ± 16.5 years; 206 women) were analyzed. The lung lesion detection subsystem yielded a mean average precision of the validation cohort of 0.68. The overall classification accuracy of six pulmonary critical imaging findings indicative of TB of the independent datasets was 81.08-91.05%. A moderate to strong correlation was demonstrated between the AI model-quantified TB score and the radiologist-estimated CT score. CONCLUSIONS: The proposed end-to-end AI system based on chest CT can achieve human-level diagnostic performance for early detection and optimal clinical management of patients with pulmonary TB. KEY POINTS: • Deep learning allows automatic detection, diagnosis, and evaluation of pulmonary tuberculosis. • Artificial intelligence helps clinicians to assess patients with tuberculosis. • Pulmonary tuberculosis disease activity and treatment management can be improved.

Understanding the motivational mechanisms behind the usage frequency of ride-hailing during COVID-19 pandemic.

Introduction: This study aimed to explore the factors influencing people's utilization of ride-hailing services, particularly in the context of the COVID-19 pandemic. Methods: A two-stage survey was conducted among the same group of passengers pre and post COVID-19 pandemic, resulting in a total of 670 valid samples. Exploratory factor analysis (EFA) was applied to the data, followed by the ordered probit and ordered logit models to identify the motivational factors behind passengers' frequency of using ride-hailing. Results: The findings indicated that trust and loyalty were the most influential factors in determining passengers' frequency of using ride-hailing services. However, passengers' perception of the COVID-19 pandemic did not have a significant effect on the frequency of using ride-hailing. Discussion: This research provides empirical evidence and policy implications for understanding people's usage of the ride-hailing services in the context of public-health emergency.

A Cascaded Deep Learning Framework for Detecting Aortic Dissection Using Non-contrast Enhanced Computed Tomography.

Aortic dissection (AD) is a rare but potentially fatal disease with high mortality. The aim of this study is to synthesize contrast enhanced computed tomography (CE-CT) images from non-contrast CT (NCE-CT) images for detecting aortic dissection. In this paper, a cascaded deep learning framework containing a 3D segmentation network and a synthetic network was proposed and evaluated. A 3D segmentation network was firstly used to segment aorta from NCE-CT images and CE-CT images. A conditional generative adversarial network (CGAN) was subsequently employed to map the NCE-CT images to the CE-CT images non-linearly for the region of aorta. The results of the experiment suggest that the cascaded deep learning framework can be used for detecting the AD and outperforms CGAN alone.

Deep Learning for Accurate Segmentation of Venous Thrombus from Black-Blood Magnetic Resonance Images: A Multicenter Study.

OBJECTIVE: Deep vein thrombosis (DVT) is the third-largest cardiovascular disease, and accurate segmentation of venous thrombus from the black-blood magnetic resonance (MR) images can provide additional information for personalized DVT treatment planning. Therefore, a deep learning network is proposed to automatically segment venous thrombus with high accuracy and reliability. METHODS: In order to train, test, and external test the developed network, total images of 110 subjects are obtained from three different centers with two different black-blood MR techniques (i.e., DANTE-SPACE and DANTE-FLASH). Two experienced radiologists manually contoured each venous thrombus, followed by reediting, to create the ground truth. 5-fold cross-validation strategy is applied for training and testing. The segmentation performance is measured on pixel and vessel segment levels. For the pixel level, the dice similarity coefficient (DSC), average Hausdorff distance (AHD), and absolute volume difference (AVD) of segmented thrombus are calculated. For the vessel segment level, the sensitivity (SE), specificity (SP), accuracy (ACC), and positive and negative predictive values (PPV and NPV) are used. RESULTS: The proposed network generates segmentation results in good agreement with the ground truth. Based on the pixel level, the proposed network achieves excellent results on testing and the other two external testing sets, DSC are 0.76, 0.76, and 0.73, AHD (mm) are 4.11, 6.45, and 6.49, and AVD are 0.16, 0.18, and 0.22. On the vessel segment level, SE are 0.95, 0.93, and 0.81, SP are 0.97, 0.92, and 0.97, ACC are 0.96, 0.94, and 0.95, PPV are 0.97, 0.82, and 0.96, and NPV are 0.97, 0.96, and 0.94. CONCLUSIONS: The proposed deep learning network is effective and stable for fully automatic segmentation of venous thrombus on black blood MR images.

Diagnostic Performance of 2D and 3D T2WI-Based Radiomics Features With Machine Learning Algorithms to Distinguish Solid Solitary Pulmonary Lesion.

OBJECTIVE: To evaluate the performance of 2D and 3D radiomics features with different machine learning approaches to classify SPLs based on magnetic resonance(MR) T2 weighted imaging (T2WI). MATERIAL AND METHODS: A total of 132 patients with pathologically confirmed SPLs were examined and randomly divided into training (n = 92) and test datasets (n = 40). A total of 1692 3D and 1231 2D radiomics features per patient were extracted. Both radiomics features and clinical data were evaluated. A total of 1260 classification models, comprising 3 normalization methods, 2 dimension reduction algorithms, 3 feature selection methods, and 10 classifiers with 7 different feature numbers (confined to 3-9), were compared. The ten-fold cross-validation on the training dataset was applied to choose the candidate final model. The area under the receiver operating characteristic curve (AUC), precision-recall plot, and Matthews Correlation Coefficient were used to evaluate the performance of machine learning approaches. RESULTS: The 3D features were significantly superior to 2D features, showing much more machine learning combinations with AUC greater than 0.7 in both validation and test groups (129 vs. 11). The feature selection method Analysis of Variance(ANOVA), Recursive Feature Elimination(RFE) and the classifier Logistic Regression(LR), Linear Discriminant Analysis(LDA), Support Vector Machine(SVM), Gaussian Process(GP) had relatively better performance. The best performance of 3D radiomics features in the test dataset (AUC = 0.824, AUC-PR = 0.927, MCC = 0.514) was higher than that of 2D features (AUC = 0.740, AUC-PR = 0.846, MCC = 0.404). The joint 3D and 2D features (AUC=0.813, AUC-PR = 0.926, MCC = 0.563) showed similar results as 3D features. Incorporating clinical features with 3D and 2D radiomics features slightly improved the AUC to 0.836 (AUC-PR = 0.918, MCC = 0.620) and 0.780 (AUC-PR = 0.900, MCC = 0.574), respectively. CONCLUSIONS: After algorithm optimization, 2D feature-based radiomics models yield favorable results in differentiating malignant and benign SPLs, but 3D features are still preferred because of the availability of more machine learning algorithmic combinations with better performance. Feature selection methods ANOVA and RFE, and classifier LR, LDA, SVM and GP are more likely to demonstrate better diagnostic performance for 3D features in the current study.