Excellent Diagnostic Performance Research Articles

Synthetic MRI and diffusion-weighted imaging for differentiating nasopharyngeal lymphoma from nasopharyngeal carcinoma: combination with morphological features.

To investigate the feasibility of synthetic MRI (syMRI), diffusion-weighted imaging (DWI), and their combination with morphological features for differentiating nasopharyngeal lymphoma (NPL) from nasopharyngeal carcinoma (NPC). Sixty-nine patients with nasopharyngeal tumours (NPL, n = 22; NPC, n = 47) who underwent syMRI and DWI were retrospectively enrolled between October 2020 and May 2022. syMRI and DWI quantitative parameters (T1, T2, PD, ADC) and morphological features were obtained. Diagnostic performance was assessed by independent sample t-test, chi-square test, logistic regression analysis, receiver operating characteristic curve (ROC), and DeLong test. NPL has significantly lower T2, PD, and ADC values compared to NPC (all P < .05), whereas no significant difference was found in T1 value between these two entities (P > .05). The morphological features of tumour type, skull-base involvement, Waldeyer ring involvement, and lymph nodes involvement region were significantly different between NPL and NPC (all P < .05). The syMRI (T2 + PD) model has better diagnostic efficacy, with AUC, sensitivity, specificity, and accuracy of 0.875, 77.27%, 89.36%, and 85.51%. Compared with syMRI model, syMRI + Morph (PD + Waldeyer ring involvement + lymph nodes involvement region), syMRI + DWI (T2 + PD + ADC), and syMRI + DWI + Morph (PD + ADC + skull-base involvement + Waldeyer ring involvement) models can further improve the diagnostic efficiency (all P < .05). Furthermore, syMRI + DWI + Morph model has excellent diagnostic performance, with AUC, sensitivity, specificity, and accuracy of 0.986, 95.47%, 97.87%, and 97.10%, respectively. syMRI and DWI quantitative parameters were helpful in discriminating NPL from NPC. syMRI + DWI + Morph model has the excellent diagnostic efficiency in differentiating these two entities. syMRI + DWI + morphological feature method can differentiate NPL from NPC with excellent diagnostic performance.

Screening mitochondria-related biomarkers in skin and plasma of atopic dermatitis patients by bioinformatics analysis and machine learning.

There is a significant imbalance of mitochondrial activity and oxidative stress (OS) status in patients with atopic dermatitis (AD). This study aims to screen skin and peripheral mitochondria-related biomarkers, providing insights into the underlying mechanisms of mitochondrial dysfunction in AD. Public data were obtained from MitoCarta 3.0 and GEO database. We screened mitochondria-related differentially expressed genes (MitoDEGs) using R language and then performed GO and KEGG pathway analysis on MitoDEGs. PPI and machine learning algorithms were also used to select hub MitoDEGs. Meanwhile, the expression of hub MitoDEGs in clinical samples were verified. Using ROC curve analysis, the diagnostic performance of risk model constructed from these hub MitoDEGs was evaluated in the training and validation sets. Further computer-aided algorithm analyses included gene set enrichment analysis (GSEA), immune infiltration and mitochondrial metabolism, centered on these hub MitoDEGs. We also used real-time PCR and Spearman method to evaluate the relationship between plasma circulating cell-free mitochondrial DNA (ccf-mtDNA) levels and disease severity in AD patients. MitoDEGs in AD were significantly enriched in pathways involved in mitochondrial respiration, mitochondrial metabolism, and mitochondrial membrane transport. Four hub genes (BAX, IDH3A, MRPS6, and GPT2) were selected to take part in the creation of a novel mitochondrial-based risk model for AD prediction. The risk score demonstrated excellent diagnostic performance in both the training cohort (AUC = 1.000) and the validation cohort (AUC = 0.810). Four hub MitoDEGs were also clearly associated with the innate immune cells' infiltration and the molecular modifications of mitochondrial hypermetabolism in AD. We further discovered that AD patients had considerably greater plasma ccf-mtDNA levels than controls (U = 92.0, p< 0.001). Besides, there was a significant relationship between the up-regulation of plasma mtDNA and the severity of AD symptoms. The study highlights BAX, IDH3A, MRPS6 and GPT2 as crucial MitoDEGs and demonstrates their efficiency in identifying AD. Moderate to severe AD is associated with increased markers of mitochondrial damage and cellular stress (ccf=mtDNA). Our study provides data support for the variation in mitochondria-related functional characteristics of AD patients.

3DFRINet: A Framework for the Detection and Diagnosis of Fracture Related Infection in Low Extremities Based on 18F-FDG PET/CT 3D Images

Fracture related infection (FRI) is one of the most devastating complications after fracture surgery in the lower extremities, which can lead to extremely high morbidity and medical costs. Therefore, early comprehensive evaluation and accurate diagnosis of patients are critical for appropriate treatment, prevention of complications, and good prognosis. 18Fluoro-deoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) is one of the most commonly used medical imaging modalities for diagnosing FRI. With the development of deep learning, more neural networks have been proposed and become powerful computer-aided diagnosis tools in medical imaging. Therefore, a fully automated two-stage framework for FRI detection and diagnosis, 3DFRINet (Three Dimension FRI Network), is proposed for 18F-FDG PET/CT 3D imaging. The first stage can effectively extract and fuse the features of both modalities to accurately locate the lesion by the dual-branch design and attention module. The second stage reduces the dimensionality of the image by using the maximum intensity projection, which retains the effective features while reducing the computational effort and achieving excellent diagnostic performance. The diagnostic performance of lesions reached 91.55% accuracy, 0.9331 AUC, and 0.9250 F1 score. 3DFRINet has an advantage over six nuclear medicine experts in each classification metric. The statistical analysis shows that 3DFRINet is equivalent or superior to the primary nuclear medicine physicians and comparable to the senior nuclear medicine physicians. In conclusion, this study first proposed a method based on 18F-FDG PET/CT three-dimensional imaging for FRI location and diagnosis. This method shows superior lesion detection rate and diagnostic efficiency and therefore has good prospects for clinical application.

Comprehensive Gene Analysis Reveals Cuproptosis-Related Gene Signature Associated with M2 Macrophage in Staphylococcus aureus-Infected Osteomyelitis.

Osteomyelitis is a challenging disease in the field of bone infections, with its immune and molecular regulatory mechanisms still poorly understood. The aim of this study is to explore the value and potential mechanisms of cuproptosis-related genes (CRGs) in Staphylococcus aureus (S. aureus)-infected osteomyelitis from an immunological perspective. Initially, three transcriptomic datasets from public databases were integrated and analyzed, and consistent expression of CRGs in S. aureus-infected osteomyelitis was identified. Subsequently, immune infiltration analysis was performed, and M2 macrophage-related CRGs (M2R-CRGs) were further identified. Their potential molecular mechanisms were evaluated using Gene Set Variation Analysis (GSVA) and Gene Set Enrichment Analysis (GSEA). Finally, distinct osteomyelitis subtypes and diagnostic models based on characteristic M2R-CRGs were constructed. Through correlation analysis with immune cell infiltration, three characteristic M2R-CRGs (SLC31A1, DLD, and MTF1) were identified. Further analysis using unsupervised clustering and immune microenvironment analysis indicated that cluster 1 might activate pro-inflammatory responses, while cluster 2 was shown to exhibit anti-inflammatory effects in osteomyelitis. Compared to Cluster A, Cluster B demonstrated higher levels and a greater diversity of immune cell infiltrations in CRG-related molecular patterns, suggesting a potential anti-inflammatory role in osteomyelitis. A diagnostic model for S. aureus-infected osteomyelitis, based on the three M2R-CRGs, was constructed, exhibiting excellent diagnostic performance and validated with an independent dataset. Significant upregulation in mRNA and protein expression levels of the three M2R-CRGs was observed in rat models of S. aureus-infected osteomyelitis, aligning with bioinformatic results. The M2R-CRGs (SLC31A1, DLD, and MTF1) may be considered characteristic genes for early diagnosis and personalized immune therapy in patients with S. aureus-infected osteomyelitis.

Plasma-based lipidomics reveals potential diagnostic biomarkers for esophageal squamous cell carcinoma: a retrospective study.

Esophageal squamous cell carcinoma (ESCC) is highly prevalent and has a high mortality rate. Traditional diagnostic methods, such as imaging examinations and blood tumor marker tests, are not effective in accurately diagnosing ESCC due to their low sensitivity and specificity. Esophageal endoscopic biopsy, which is considered as the gold standard, is not suitable for screening due to its invasiveness and high cost. Therefore, this study aimed to develop a convenient and low-cost diagnostic method for ESCC using plasma-based lipidomics analysis combined with machine learning (ML) algorithms. Plasma samples from a total of 40 ESCC patients and 31 healthy controls were used for lipidomics study. Untargeted lipidomics analysis was conducted through liquid chromatography-mass spectrometry (LC-MS) analysis. Differentially expressed lipid features were filtered based on multivariate and univariate analysis, and lipid annotation was performed using MS-DIAL software. A total of 99 differential lipids were identified, with 15 up-regulated lipids and 84 down-regulated lipids, suggesting their potential as diagnostic targets for ESCC. In the single-lipid plasma-based diagnostic model, nine specific lipids (FA 15:4, FA 27:1, FA 28:7, FA 28:0, FA 36:0, FA 39:0, FA 42:0, FA 44:0, and DG 37:7) exhibited excellent diagnostic performance, with an area under the curve (AUC) exceeding 0.99. Furthermore, multiple lipid-based ML models also demonstrated comparable diagnostic ability for ESCC. These findings indicate plasma lipids as a promising diagnostic approach for ESCC.

Exploring the diagnostic value of endothelial cell and angiogenesis-related genes in Hashimoto's thyroiditis based on transcriptomics and single cell RNA sequencing

(1) BackgroundHashimoto's thyroiditis (HT) can cause angiogenesis in the thyroid gland. However, the molecular mechanism of endothelial cells and angiogenesis related genes (ARGs) has not been extensively studied in HT. (2) MethodsThe HRA001684, GSE29315 and GSE163203 datasets were included in this study. Using single-cell analysis, weighted gene co-expression network analysis (WGCNA), functional enrichment analysis, machine learning algorithms and expression analysis for exploration. And receiver operator characteristic (ROC) curves was draw. Gene set enrichment analysis (GSEA) was utilized to investigate the biological function of the biomarkers. Meanwhile, we investigated into the relationship between biomarkers and different types of immune cells. Additionally, the expression of biomarkers in the TCGA-TC dataset was examined and the mRNA-drug interaction network was constructed. (3) ResultsWe found 14 cell subtypes were obtained in HT samples after single-cell analysis. A total of 5 biomarkers (CD52, CD74, CD79A, HLA-B and RGS1) were derived, and they had excellent diagnostic performance. Then, 27 drugs targeting biomarkers were predicted. The expression analysis showed that CD74 and HLA-B were significantly up-regulated in HT samples. (4) ConclusionIn this study, 5 biomarkers (CD52, CD74, CD79A, HLA-B and RGS1) were screened and their expressions in endothelial cells was compared to offer a new reference for the recognition and management of HT.

Diagnostic accuracy of artificial intelligence assisted clinical imaging in the detection of oral potentially malignant disorders and oral cancer: a systematic review and meta-analysis.

The objective of this study is to examine the application of artificial intelligence (AI) algorithms in detecting oral potentially malignant disorders (OPMD) and oral cancerous lesions, and to evaluate the accuracy variations among different imaging tools employed in these diagnostic processes. A systematic search was conducted in four databases: Embase, Web of Science, PubMed, and Scopus. The inclusion criteria included studies using machine learning algorithms to provide diagnostic information on specific oral lesions, prospective or retrospective design, and inclusion of OPMD. Sensitivity and specificity analyses were also required. Forest plots were generated to display overall diagnostic odds ratio (DOR), sensitivity, specificity, negative predictive values, and summary receiver operating characteristic (SROC) curves. Meta-regression analysis was conducted to examine potential differences among different imaging tools. The overall DOR for AI-based screening of OPMD and oral mucosal cancerous lesions from normal mucosa was 68.438 (95% CI= [39.484-118.623], I2 =86%). The area under the SROC curve was 0.938, indicating excellent diagnostic performance. AI-assisted screening showed a sensitivity of 89.9% (95% CI= [0.866-0.925]; I2 =81%), specificity of 89.2% (95% CI= [0.851-0.922], I2 =79%), and a high negative predictive value of 89.5% (95% CI= [0.851-0.927], I2 =96%). Meta-regression analysis revealed no significant difference among the three image tools. After generating a GOSH plot, the DOR was calculated to be 49.30, and the area under the SROC curve was 0.877. Additionally, sensitivity, specificity, and negative predictive value were 90.5% (95% CI [0.873-0.929], I2 =4%), 87.0% (95% CI [0.813-0.912], I2 =49%) and 90.1% (95% CI [0.860-0.931], I2 =57%), respectively. Subgroup analysis showed that clinical photography had the highest diagnostic accuracy. AI-based detection using clinical photography shows a high DOR and is easily accessible in the current era with billions of phone subscribers globally. This indicates that there is significant potential for AI to enhance the diagnostic capabilities of general practitioners to the level of specialists by utilizing clinical photographs, without the need for expensive specialized imaging equipment.

Metabolomic profiles predict clinical severity in patients with obstructive sleep apnea-hypopnea syndrome.

Obstructive sleep apnea-hypopnea syndrome (OSAHS) poses a significant health hazard, intermittent hypoxia inflicts damage throughout the body and is considered a critical risk factor for metabolic disorders. The aim of this study was to establish a metabolic profile for patients with OSAHS using nontargeted metabolomics detection techniques, providing a basis for OSAHS diagnosis and novel biological marker identification. 45 patients with OSAHS composed the OSAHS group, and 44 healthy volunteers composed the control group. Nontargeted metabolomics technology was used to analyze participants' urinary metabolites. Differentially abundant metabolites were screened and correlated through hierarchical clustering analysis. We constructed a composite metabolite diagnostic model using a random forest model. Simultaneously, we analyzed the relationships between 20 metabolites involved in model construction and OSAHS severity. The urinary metabolomics pattern of the OSAHS group exhibited significant changes, demonstrating noticeable differences in metabolic products. Urinary metabolite analysis revealed differences between the mild-to-moderate OSAHS and severe OSAHS groups. The composite metabolite model constructed in this study demonstrated excellent diagnostic performance not only in distinguishing healthy control participants from patients with mild-to-moderate OSAHS (area under the curve = 0.78) and patients with severe OSAHS (area under the curve = 0.78), but also in discriminating between patients with mild-to-moderate and severe OSAHS (area under the curve = 0.71). This study comprehensively analyzed the urinary metabolomic characteristics of patients with OSAHS. The established composite metabolite model provides robust support for OSAHS diagnosis and severity assessment. Twenty metabolites associated with OSAHS disease severity offer a new perspective for diagnosis. Wang X, Zhao J, Wang X, Zhang L. Metabolomic profiles predict clinical severity in patients with obstructive sleep apnea-hypopnea syndrome. J Clin Sleep Med. 2024;20(9):1445-1453.

OHCA-GCN: A novel graph convolutional network-based fault diagnosis method for complex systems via supervised graph construction and optimization

Fault diagnosis is crucial for ensuring the safe and stable operation of complex systems. Recently, graph convolutional network (GCN)-based fault diagnosis method has emerged as a hot research topic due to its ability to effectively handle the association information inherent in the collected dataset. Regarding the method, a fundamental challenge is the construction of the association graph, conventional construction methods struggle to capture the intricate relationships between nodes with complex coupling. Besides, they operate in an unsupervised learning mode, lacking the ability to evaluate and adjust the constructed graph. To handle this challenge, a novel graph convolutional network-based fault diagnosis method via supervised graph construction and optimization (OHCA-GCN) is proposed. Specifically, the supervised orthogonalized-autoencoder is proposed to construct the association graph. Then, a high-order correlation analysis-based graph optimization strategy is proposed to ensure graph sparsity and alleviate the over-smoothing issue. To validate the effectiveness of the proposed method, experiments are carried out on a pulse rectifier dataset from a hardware-in-the-loop platform. The results show that the proposed method exhibits the excellent diagnostic performance compared with the existing methods.

Identification of hub genes and establishment of a diagnostic model in tuberculosis infection

Tuberculosis (TB) poses significant challenges due to its high transmissibility within populations and intrinsic resistance to treatment, rendering it a formidable respiratory disease with a substantial susceptibility burden. This study was designed to identify new potential therapeutic targets for TB and establish a diagnostic model. mRNA expression data for TB were from GEO database, followed by conducting differential expression analysis. The top 50 genes with differential expression were subjected to GO and KEGG enrichment analyses. To establish a PPI network, the STRING database was utilized, and hub genes were identified utilizing five algorithms (EPC, MCC, MNC, Radiality, and Stress) within the cytoHubba plugin of Cytoscape software. Furthermore, a hub gene co-expression network was constructed using the GeneMANIA database. Consistency clustering was performed on hub genes, and ssGSEA was utilized to analyze the extent of immune infiltration in different subgroups. LASSO analysis was employed to construct a diagnostic model, and ROC curves were used for validation. Through the analysis of GEO data, a total of 159 genes were identified as differentially expressed. Further, GO and KEGG enrichment analyses revealed that these genes were mainly enriched in viral defense, symbiotic defense, and innate immune response-related pathways. Hub genes, including DDX58, IFIT2, IFIH1, RSAD2, IFI44L, OAS2, OAS1, OASL, IFIT1, IFIT3, MX1, STAT1, and ISG15, were identified using cytoHubba analysis of the PPI network. The GeneMANIA analysis unmasked that the co-expression rate of hub genes was 81.55%, and the physical interaction rate was 12.27%. Consistency clustering divided TB patients into two subgroups, and ssGSEA revealed different degrees of immune infiltration in different subgroups. LASSO analysis identified IFIT1, IFIT2, IFIT3, IFIH1, RSAD2, OAS1, OAS2, and STAT1 as eight immune-related key genes, and a diagnostic model was constructed. The ROC curve demonstrated that the model exhibited excellent diagnostic performance. DDX58, IFIT2, IFIH1, RSAD2, IFI44L, OAS2, OAS1, OASL, IFIT1, IFIT3, MX1, STAT1, and ISG15 were hub genes in TB, and the diagnostic model based on eight immune-related key genes exhibited good diagnostic performance.

Coupled scRNA-seq and Bulk-seq reveal the role of HMMR in hepatocellular carcinoma.

Hyaluronan-mediated motility receptor (HMMR) is overexpressed in multiple carcinomas and influences the development and treatment of several cancers. However, its role in hepatocellular carcinoma (HCC) remains unclear. The "limma" and "GSVA" packages in R were used to perform differential expression analysis and to assess the activity of signalling pathways, respectively. InferCNV was used to infer copy number variation (CNV) for each hepatocyte and "CellChat" was used to analyse intercellular communication networks. Recursive partitioning analysis (RPA) was used to re-stage HCC patients. The IC50 values of various drugs were evaluated using the "pRRophetic" package. In addition, quantitative reverse transcription polymerase chain reaction (qRT-PCR) was performed to confirm HMMR expression in an HCC tissue microarray. Flow cytometry (FCM) and cloning, Edu and wound healing assays were used to explore the capacity of HMMR to regulate HCC tumour. Multiple cohort studies and qRT-PCR demonstrated that HMMR was overexpressed in HCC tissue compared with normal tissue. In addition, HMMR had excellent diagnostic performance. HMMR knockdown inhibited the proliferation and migration of HCC cells in vitro. Moreover, high HMMR expression was associated with "G2M checkpoint" and "E2F targets" in bulk RNA and scRNA-seq, and FCM confirmed that HMMR could regulate the cell cycle. In addition, HMMR was involved in the regulation of the tumour immune microenvironment via immune cell infiltration and intercellular interactions. Furthermore, HMMR was positively associated with genomic heterogeneity with patients with high HMMR expression potentially benefitting more from immunotherapy. Moreover, HMMR was associated with poor prognosis in patients with HCC and the re-staging by recursive partitioning analysis (RPA) gave a good prognosis prediction value and could guide chemotherapy and targeted therapy. The results of the present study show that HMMR could play a role in the diagnosis, prognosis, and treatments of patients with HCC based on bulk RNA-seq and scRAN-seq analyses and is a promising molecular marker for HCC.

Construction of a diagnostic model based on random forest and artificial neural network for peri-implantitis.

This study aimed to reveal critical genes regulating peri-implantitis during its development and construct a diagnostic model by using random forest (RF) and artificial neural network (ANN). GSE-33774, GSE106090, and GSE57631 datasets were obtained from the GEO database. The GSE33774 and GSE106090 datasets were analyzed for differential expression and functional enrichment. The protein-protein interaction networks (PPI) and RF screened vital genes. A diagnostic model for peri-implantitis was established using ANN and validated on the GSE33774 and GSE57631 datasets. A transcription factor-gene interaction network and a transcription factor-micro-RNA (miRNA) regulatory network were also established. A total of 124 differentially expressed genes (DEGs) involved in the regulation of peri-implantitis were screened. Enrichment analysis showed that DEGs were mainly associated with immune receptor activity and cytokine receptor activity and were mainly involved in processes such as leukocyte and neutrophil migration. The PPI and RF screened six essential genes, namely, CD38, CYBB, FCGR2A, SELL, TLR4, and CXCL8. The receiver operating characteristic curve (ROC) indicated that the ANN model had an excellent diagnostic performance. FOXC1, GATA2, and NF-κB1 may be essential transcription factors in peri-implantitis, and hsa-miR-204 may be a key miRNA. The diagnostic model of peri-implantitis constructed by RF and ANN has high confidence, and CD38, CYBB, FCGR2A, SELL, TLR4, and CXCL8 are potential diagnostic markers. FOXC1, GATA2, and NF-κB1 may be essential transcription factors in peri-implantitis, and hsa-miR-204 plays a vital role as a critical miRNA.

Left atrial reservoir longitudinal strain and its incremental value to the left ventricular global longitudinal strain in predicting anthracycline-induced cardiotoxicity.

Left ventricular global longitudinal strain (LVGLS) has been recommended by current guidelines for diagnosing anthracycline-induced cardiotoxicity. However, little is known about the early changes in left atrial (LA) morphology and function in this population. Our study aimed to evaluate the potential usefulness of LA indices and their incremental value to LVGLS with three-dimensional echocardiography (3DE) in the early detection of subclinical cardiotoxicity in patients with lymphoma receiving anthracycline. A total of 80 patients with diffuse large B-cell lymphoma who received six cycles of anthracycline-based treatment were enrolled. Echocardiography was performed at baseline (T0), after four cycles (T1), and after the completion of six cycles of chemotherapy (T2). Left ventricular ejection fraction (LVEF), LVGLS, LA volumes, LA emptying fraction (LAEF), LA active emptying fraction (LAAEF), and LA reservoir longitudinal strain (LASr) were quantified with 3DE. Left atrioventricular global longitudinal strain (LAVGLS) was calculated as the sum of peak LASr and the absolute value of peak LVGLS (LAVGLS=LASr+|LVGLS|). LV cardiotoxicity was defined as a new LVEF reduction by ≥10 percentage points to an LVEF of ≤50%. Fourteen (17.5%) patients developed LV cardiotoxicity at T2. LA volumes, LAEF, and LAAEF remained stable over time. Impairment of LASr (28.35±5.03vs. 25.04±4.10, p<.001), LVGLS (-22.77±2.45vs. -20.44±2.62, p<.001), and LAVGLS (51.12±5.63vs. 45.61±5.22, p<.001) was observed by the end of the fourth cycle of chemotherapy (T1). Statistically significant declines in LVEF (61.30±4.73vs. 57.08±5.83, p<.001) were only observed at T2. The relative decrease in LASr (ΔLASr), LVGLS (ΔLVGLS), and LAVGLS (ΔLAVGLS) from T0 to T1 were predictors of LV cardiotoxicity. A ΔLASr of>19.75% (sensitivity, 71.4%; specificity, 87.9%; area under the curve (AUC),.842; p<.001), a ΔLVGLS of>13.19% (sensitivity, 78.6%; specificity, 74.2%; AUC,.763; p<.001), and a ΔLAVGLS of>16.80% (sensitivity, 78.6%; specificity, 93.9%; AUC,.905; p<.001) predicted subsequent LV cardiotoxicity at T2, with the AUC of ΔLAVGLS significantly larger than that of ΔLVGLS (.905vs..763, p=.027). Compared to ΔLVGLS, ΔLAVGLS showed improved specificity (93.9%vs. 74.2%, p=.002) and maintained sensitivity in predicting LV cardiotoxicity. LASr could predict anthracycline-induced LV cardiotoxicity with excellent diagnostic performance. Incorporating LASr into LVGLS (LAVGLS) led to a significantly improved specificity and maintained sensitivity in predicting LV cardiotoxicity.

Fully automated deep learning system for osteoporosis screening using chest computed tomography images.

Osteoporosis, a disease stemming from bone metabolism irregularities, affects approximately 200 million people worldwide. Timely detection of osteoporosis is pivotal in grappling with this public health challenge. Deep learning (DL), emerging as a promising methodology in the field of medical imaging, holds considerable potential for the assessment of bone mineral density (BMD). This study aimed to propose an automated DL framework for BMD assessment that integrates localization, segmentation, and ternary classification using various dominant convolutional neural networks (CNNs). In this retrospective study, a cohort of 2,274 patients underwent chest computed tomography (CT) was enrolled from January 2022 to June 2023 for the development of the integrated DL system. The study unfolded in 2 phases. Initially, 1,025 patients were selected based on specific criteria to develop an automated segmentation model, utilizing 2 VB-Net networks. Subsequently, a distinct cohort of 902 patients was employed for the development and testing of classification models for BMD assessment. Then, 3 distinct DL network architectures, specifically DenseNet, ResNet-18, and ResNet-50, were applied to formulate the 3-classification BMD assessment model. The performance of both phases was evaluated using an independent test set consisting of 347 individuals. Segmentation performance was evaluated using the Dice similarity coefficient; classification performance was appraised using the receiver operating characteristic (ROC) curve. Furthermore, metrics such as the area under the curve (AUC), accuracy, and precision were meticulously calculated. In the first stage, the automatic segmentation model demonstrated excellent segmentation performance, with mean Dice surpassing 0.93 in the independent test set. In the second stage, both the DenseNet and ResNet-18 demonstrated excellent diagnostic performance in detecting bone status. For osteoporosis, and osteopenia, the AUCs were as follows: DenseNet achieved 0.94 [95% confidence interval (CI): 0.91-0.97], and 0.91 (95% CI: 0.87-0.94), respectively; ResNet-18 attained 0.96 (95% CI: 0.92-0.98), and 0.91 (95% CI: 0.87-0.94), respectively. However, the ResNet-50 model exhibited suboptimal diagnostic performance for osteopenia, with an AUC value of only 0.76 (95% CI: 0.69-0.80). Alterations in tube voltage had a more pronounced impact on the performance of the DenseNet. In the independent test set with tube voltage at 100 kVp images, the accuracy and precision of DenseNet decreased on average by approximately 14.29% and 18.82%, respectively, whereas the accuracy and precision of ResNet-18 decreased by about 8.33% and 7.14%, respectively. The state-of-the-art DL framework model offers an effective and efficient approach for opportunistic osteoporosis screening using chest CT, without incurring additional costs or radiation exposure.

Performance of anterior segment OCT-based algorithms in the opportunistic screening for primary angle-closure disease

PurposeThis study aimed to investigate the performance of deep learning algorithms in the opportunistic screening for primary angle-closure disease (PACD) using combined anterior segment parameters. MethodsThis was an observational, cross-sectional hospital-based study. Patients with PACD and healthy controls who underwent comprehensive eye examinations, including gonioscopy and anterior segment optical coherence tomography (ASOCT) examinations under both light and dark conditions, were consecutively enrolled from the Department of Ophthalmology at the Beijing Tongren Hospital between November 2020 and June 2022. The anterior chamber, anterior chamber angle, iris, and lens parameters were assessed using ASOCT. To build the prediction models, backward logistic regression was utilized to select the variables to discriminate patients with PACD from normal participants, and the area under the receiver operating characteristic curve was used to evaluate the efficacy of the opportunistic screening. ResultsThe data from 199 patients (199 eyes) were included in the final analysis and divided into two groups: PACD (109 eyes) and controls (90 eyes). Angle opening distance at 500 μm, anterior chamber area, and iris curvature measured in the light condition were included in the final prediction models. The area under the receiver operating characteristic curve was 0.968, with a sensitivity of 91.74 % and a specificity of 91.11 %. ConclusionASOCT-based algorithms showed excellent diagnostic performance in the opportunistic screening for PACD. These results provide a promising basis for future research on the development of an angle-closure probability scoring system for PACD screening.

Partial transfer learning method based on MDWCAN for rolling bearing fault diagnosis under noisy conditions

Domain adaptation shows excellent diagnostic performance for transfer bearing fault diagnosis (FD) in noise-free scenarios, where the training and test data label spaces are the same. However, in actual engineering, collecting test data for all health states is difficult and the vibration signal is susceptible to noise interference, which limits its application in real industry. Therefore, how to effectively source domain outlier samples and suppress irrelevant noise poses a challenge to the effectiveness of existing FD methods based on domain adaptation. To address the above issues, a novel transfer learning model named multi-scale denoising weighted conditional adversarial network (MDWCAN) is developed for partial transfer FD problem under noisy conditions. Firstly, a global multimodal denoising module is proposed to form a new feature extractor with multi-scale convolutional modules, which can enhance important features and weaken interference features. Secondly, a new loss function is proposed, in which the weight function is introduced into the conditional adversarial function to suppress the negative influence of source domain outlier samples. Finally, experimental results on two bearing datasets show that MDWCAN outperforms other methods.

Exploring the Role of Extracellular Vesicles in the Pathogenesis of Tuberculosis.

Tuberculosis (TB) remains a significant global health concern, necessitating accurate diagnosis and treatment monitoring. Extracellular vesicles (EVs), including exosomes, play crucial roles in disease progression, with their associated genes serving as potential biomarkers and therapeutic targets. Leveraging publicly available RNA-Seq datasets of TB patients and healthy controls (HCs), to identify differentially expressed genes (DEGs) and their associated protein-protein interaction networks and immune cell profiles, the common EV-related DEGs were identified and validated in the GSE42830 and GSE40553 datasets. We have identified nine common EV-related DEGs (SERPINA1, TNFAIP6, MAPK14, STAT1, ITGA2B, VAMP5, CTSL, CEACAM1, and PLAUR) upregulated in TB patients. Immune cell infiltration analysis revealed significant differences between TB patients and HCs, highlighting increased proportions of various immune cells in TB patients. These DEGs are involved in crucial cellular processes and pathways related to exocytosis and immune response regulation. Notably, VAMP5 exhibited excellent diagnostic performance (AUC-0.993, sensitivity-93.8%, specificity-100%), with potential as a novel biomarker for TB. The EV-related genes can serve as novel potential biomarkers that can distinguish between TB and HCs. VAMP5, which functions in exosome biogenesis and showed significant upregulation in TB, can be targeted for therapeutic interventions and treatment outcomes.

Clinicopathological correlation of cerebrospinal fluid alpha-synuclein seed amplification assay in a behavioral neurology autopsy cohort.

Lewy body disease (LBD) is a common primary or co-pathology in neurodegenerative syndromes. An alpha-synuclein seed amplification assay (αSyn-SAA) is clinically available, but clinical performance, especially lower sensitivity in amygdala-predominant cases, is not well understood. Antemortem CSF from neuropathology-confirmed LBD cases was tested with αSyn-SAA (N=56). Diagnostic performance and clinicopathological correlations were examined. Similar to prior reports, sensitivity was 100% for diffuse and transitional LBD (9/9), and overall specificity was 96.3% (26/27). Sensitivity was lower in amygdala-predominant (6/14, 42.8%) and brainstem-predominant LBD (1/6, 16.7%), but early spread outside these regions (without meeting criteria for higher stage) was more common in αSyn-SAA-positive cases (6/7, 85.7%) than negative (2/13, 15.4%). In this behavioral neurology cohort, αSyn-SAA had excellent diagnostic performance for cortical LBD. In amygdala- and brainstem-predominant cases, sensitivity was lower, but positivity was associated with anatomical spread, suggesting αSyn-SAA detects early LBD progression in these cohorts. A cerebrospinal fluid alpha-synuclein assay detects cortical LBD with high sensitivity/specificity. Positivity in prodromal stages of LBD was associated with early cortical spread. The assay provides precision diagnosis of LBD that could support clinical trials. The assay can also identify LBD co-pathology, which may impact treatment responses.

ALT to qHBsAg ratio predicts long-term HBsAg seroclearance after entecavir cessation in Chinese patients with chronic hepatitis B

Factors predicting HBsAg seroclearance after treatment cessation, irrespective of nucleos(t)ide analogue (NA) resumption, have important clinical implications. We evaluated predictors of long-term HBsAg seroclearance after entecavir cessation. This study followed-up Chinese patients with chronic hepatitis B from two previous studies of entecavir cessation. All patients were non-cirrhotic, HBeAg-negative, with undetectable HBV DNA (<20IU/ml) at end-of-treatment (EOT). They were monitored closely for 48 weeks with regular HBV DNA, quantitative HBsAg (qHBsAg) and alanine aminotransferase (ALT) measurements. Entecavir was resumed at HBV DNA >2,000IU/ml, irrespective of ALT levels. After the initial 48 weeks, patients were assessed every 6 months, regardless of entecavir resumption, to monitor for HBsAg seroclearance. A total of 194 patients (63.4% male, mean age 49.9 years, on entecavir for a median of 47.2 months) were recruited; 94 (48.5%) and 158 (81.4%) patients had EOT qHBsAg <100IU/ml and <1,000IU/ml, respectively; 151 (77.8%) patients were eventually resumed on entecavir. After follow-up for a median of 70.7 (51.0-118.2) months, 28 (14.4%) patients had HBsAg seroclearance. qHBsAg levels at weeks 36 and 48 after EOT independently predicted HBsAg seroclearance (both p<0.01), whereas qHBsAg from EOT to week 24 only trended towards statistical significance. The ratio of ALT/qHBsAg at all time points from EOT to week 48 independently predicted HBsAg seroclearance (hazard ratios ranging from 1.003-1.028, all p<0.01) with excellent diagnostic performance (area under the receiver-operating characteristic curve 0.799-0.933, negative predictive value >90% at different time points), regardless of whether entecavir was resumed. The ALT/qHBsAg ratio after entecavir cessation predicts HBsAg seroclearance, even in patients who were resumed on treatment. Its use may mitigate the risk of severe hepatitis flares in patients managed by observation without treatment resumption. Current predictors of HBsAg seroclearance after finite nucleos(t)ide analogue (NA) therapy have suboptimal predictive value. We demonstrated that the ALT/qHBsAg ratio may be able to reflect the balance between host control and virological activity. The ALT/qHBsAg ratio at different time points from end-of-treatment till week 48 independently and accurately predicted HBsAg seroclearance in patients who have stopped entecavir. The ALT/qHBsAg ratio may be utilized by clinicians for patient selection and retreatment decisions in finite NA therapy.

Exploring the diagnostic value of ultrasound radiomics for neonatal respiratory distress syndrome

BackgroundNeonatal respiratory distress syndrome (NRDS) is a prevalent cause of respiratory failure and death among newborns, and prompt diagnosis is imperative. Historically, diagnosis of NRDS relied mostly on typical clinical manifestations, chest X-rays, and CT scans. However, recently, ultrasound has emerged as a valuable and preferred tool for aiding NRDS diagnosis. Nevertheless, evaluating lung ultrasound imagery necessitates rigorous training and may be subject to operator-dependent bias, limiting its widespread use. As a result, it is essential to investigate a new, reliable, and operator-independent diagnostic approach that does not require subjective factors or operator expertise. This article aims to explore the diagnostic potential of ultrasound-based radiomics in differentiating NRDS from other non-NRDS lung disease.MethodsA total of 150 neonatal lung disease cases were consecutively collected from the department of neonatal intensive care unit of the Quanzhou Maternity and Children’s Hospital, Fujian Province, from September 2021 to October 2022. Of these patients, 60 were diagnosed with NRDS, whereas 30 were diagnosed with neonatal pneumonia, meconium aspiration syndrome (MAS), and transient tachypnea (TTN). Two ultrasound images with characteristic manifestations of each lung disease were acquired and divided into training (n = 120) and validation cohorts (n = 30) based on the examination date using an 8:2 ratio. The imaging texture features were extracted using PyRadiomics and, after the screening, machine learning models such as random forest (RF), logistic regression (LR), K-nearest neighbors (KNN), support vector machine (SVM), and multilayer perceptron (MLP) were developed to construct an imaging-based diagnostic model. The diagnostic efficacy of each model was analyzed. Lastly, we randomly selected 282 lung ultrasound images and evaluated the diagnostic efficacy disparities between the optimal model and doctors across differing levels of expertise.ResultsTwenty-two imaging-based features with the highest weights were selected to construct a predictive model for neonatal respiratory distress syndrome. All models exhibited favorable diagnostic performances. Analysis of the Youden index demonstrated that the RF model had the highest score in both the training (0.99) and validation (0.90) cohorts. Additionally, the calibration curve indicated that the RF model had the best calibration (P = 0.98). When compared to the diagnostic performance of experienced and junior physicians, the RF model had an area under the curve (AUC) of 0.99; however, the values for experienced and junior physicians were 0.98 and 0.85, respectively. The difference in diagnostic efficacy between the RF model and experienced physicians was not statistically significant (P = 0.24), whereas that between the RF model and junior physicians was statistically significant (P < 0.0001).ConclusionThe RF model exhibited excellent diagnostic performance in the analysis of texture features based on ultrasound radiomics for diagnosing NRDS.