Retrieving keyframes most relevant to text from small intestine videos with given labels can efficiently and accurately locate pathological regions. However, training directly on raw video data is extremely slow, while learning visual representations from image-text datasets leads to computational inconsistency. To tackle this challenge, a small bowel video keyframe retrieval based on multi-modal contrastive learning (KRCL) is proposed. This framework fully utilizes textual information from video category labels to learn video features closely related to text, while modeling temporal information within a pretrained image-text model. It transfers knowledge learned from image-text multimodal models to the video domain, enabling interaction among medical videos, images, and text data. Experimental results on the hyper-spectral and Kvasir dataset for gastrointestinal disease detection (Hyper-Kvasir) and the Microsoft Research video-to-text (MSR-VTT) retrieval dataset demonstrate the effectiveness and robustness of KRCL, with the proposed method achieving state-of-the-art performance across nearly all evaluation metrics.
Humans ; Video Recording ; Intestine, Small/diagnostic imaging* ; Machine Learning ; Image Processing, Computer-Assisted/methods* ; Algorithms

The orientation of the acetabular cup in hip joint anteroposterior radiograph is a key factor in evaluating the postoperative outcomes of total hip arthroplasty (THA). Currently, measurement of the acetabular cup anteversion angle primarily relies on manual drawing of auxiliary lines by orthopedic surgeons and calculations using scientific calculators. This study proposes an automated computer-aided measurement method for the acetabular cup anteversion angle based on hip joint anteroposterior radiograph. The proposed method segments hip prosthesis images using an improved Otsu algorithm, identifies feature points at the acetabular cup opening by combining circle-fitting theory and the cup's geometric characteristics, and fits an ellipse to the cup opening to calculate the anteversion angle. A total of 104 hip joint anteroposterior radiographs, including 71 right-sided and 81 left-sided prostheses, were analyzed. Two orthopedic surgeons independently measured the postoperative anteversion angles, and the results were compared with computer-generated measurements for correlation analysis. Spearman and Pearson correlation analyses demonstrated significant correlations between the proposed method and manual measurements for both the right group ( r = 0.795, P < 0.01) and the left group ( r = 0.859, P < 0.01). This method provides a reliable reference for orthopedic surgeons to assess postoperative prognosis.
Humans ; Acetabulum/anatomy & histology* ; Arthroplasty, Replacement, Hip/methods* ; Algorithms ; Hip Prosthesis ; Hip Joint/diagnostic imaging* ; Radiography ; Image Processing, Computer-Assisted/methods*

Objective·To develop an early diagnostic model for small cell lung cancer(SCLC)based on differences in serum metabolite expression profiles between patients with SCLC and those with benign pulmonary diseases,using machine learning algorithms.Methods·Serum samples were collected from 29 SCLC patients and 67 patients with benign lung diseases at Shanghai General Hospital,Shanghai Jiao Tong University School of Medicine,as the training cohort.An independent external validation cohort included 20 SCLC patients and 40 patients with benign lung diseases from Gansu Provincial Cancer Hospital.A total of 69 serum metabolites were quantitatively analyzed using liquid chromatography-tandem mass spectrometry(LC-MS/MS).The XGBoost Classifier was employed to rank metabolite importance,and a forward feature selection strategy based on XGBoost was used to identify a subset of key metabolites.Diagnostic models were constructed using AdaBoost,random forest(RF),and light gradient boosting machine(LGBM)algorithms.Model performance was assessed using receiver operating characteristic(ROC)curves and the area under the curve(AUC),and validated on the external test cohort.Results·Principal component analysis(PCA)and orthogonal projections to latent structures-discriminant analysis(OPLS-DA)of the training cohort revealed distinct metabolic profiles between SCLC and benign lung disease patients.Based on feature importance rankings,six key metabolites were selected to construct the MTB-6 diagnostic model.Among the models,AdaBoost achieved the best performance,with an AUC of 0.943,sensitivity of 75.0%,and specificity of 90.9%in the training cohort.In the external test cohort,the model demonstrated robust performance with an AUC of 0.921,sensitivity of 80.0%,and specificity of 87.5%.Conclusion·The MTB-6 model,based on six serum metabolites and the AdaBoost algorithm,exhibits excellent diagnostic performance and holds potential for the differential diagnosis of SCLC and benign pulmonary diseases.

Objective·To develop an early diagnostic model for small cell lung cancer(SCLC)based on differences in serum metabolite expression profiles between patients with SCLC and those with benign pulmonary diseases,using machine learning algorithms.Methods·Serum samples were collected from 29 SCLC patients and 67 patients with benign lung diseases at Shanghai General Hospital,Shanghai Jiao Tong University School of Medicine,as the training cohort.An independent external validation cohort included 20 SCLC patients and 40 patients with benign lung diseases from Gansu Provincial Cancer Hospital.A total of 69 serum metabolites were quantitatively analyzed using liquid chromatography-tandem mass spectrometry(LC-MS/MS).The XGBoost Classifier was employed to rank metabolite importance,and a forward feature selection strategy based on XGBoost was used to identify a subset of key metabolites.Diagnostic models were constructed using AdaBoost,random forest(RF),and light gradient boosting machine(LGBM)algorithms.Model performance was assessed using receiver operating characteristic(ROC)curves and the area under the curve(AUC),and validated on the external test cohort.Results·Principal component analysis(PCA)and orthogonal projections to latent structures-discriminant analysis(OPLS-DA)of the training cohort revealed distinct metabolic profiles between SCLC and benign lung disease patients.Based on feature importance rankings,six key metabolites were selected to construct the MTB-6 diagnostic model.Among the models,AdaBoost achieved the best performance,with an AUC of 0.943,sensitivity of 75.0%,and specificity of 90.9%in the training cohort.In the external test cohort,the model demonstrated robust performance with an AUC of 0.921,sensitivity of 80.0%,and specificity of 87.5%.Conclusion·The MTB-6 model,based on six serum metabolites and the AdaBoost algorithm,exhibits excellent diagnostic performance and holds potential for the differential diagnosis of SCLC and benign pulmonary diseases.

Abstract: Inflammatory bowel disease (IBD), whose pathogenesis remains elusive, is a group of autoimmune diseases characterized by chronic, progressive, and lifelong inflammation of the digestive tract. The pathogenesis of IBD remains elusive. Although a number of drugs have been developed to treat IBD, their effects are merely anti-inflammatory. In addition, current treatments for IBD are easily susceptible to resistance in clinical practice. Mesenchymal stem cells (MSCs) have been reported to have the ability to migrate to the site of inflammation, with potent immunoregulatory effects, and to rebalance the immune microenvironment and restore the integrity of the epithelial barrier with significant value of application, particularly for patients who are refractory to classic medicines. In this paper, we reviewed the clinical applications, mechanisms and engineerable properties of MSC products and their exosomes to provide some reference for the use of MSCs and their exosomes in the treatment of IBD.

As a pathological vasodilation disease,intracranial aneurysm is an important cause of hemorrhagic stroke,and the specific mechanism of intracranial aneurysm formation is not very clear.The rupture of intracranial aneurysms often causes subarachnoid hemorrhage,leaving patients with severe sequelae and even death.Multiple morphological indicators based on aneurysm neck formation are important for assessing aneurysm stability and rupture risk.With the development of technology,the combination of neck-related parameters of intracranial aneurysms and clinical information of patients to make comprehensive diagnosis and treatment decisions is helpful for the accurate assessment of intracranial aneurysms and the further exploration of automated auxiliary evaluation systems.In this article,the authors reviewed the measurement of intracranial aneurysm neck-related parameters and their clinical applications in recent years and summarized and analyzed a variety of computer-aided aneurysm neck segmentation algorithms,hoping to provide a reference for future research on the accurate measurement and application of intracranial aneurysms and to provide more scientific and accurate morphological quantitative information for the formulation of clinical diagnosis and treatment plans.

Objective:To isolate and identify SARS-CoV-2 epidemic strains and analyze the sequence characteristics of the virus strains following serial passages.Methods:Eleven nasopharyngeal swabs positive for SARS-CoV-2 antigen were collected from December 2022. Quantitative real-time PCR was used to detect SARS-CoV-2 nucleic acid, and positive specimens were inoculated onto Vero cells for virus isolation. The isolated strains were identified by Western blot and indirect immunofluorescence assay. The morphology of the isolated strains was observed using transmission electron microscopy. Nucleic acid was extracted from the isolates and passaged viruses for further sequencing and analysis.Results:All 11 specimens tested positive for SARS-CoV-2 using quantitative real-time PCR. SARS-CoV-2 strains were successfully isolated from seven specimens, and could be adaptively cultured, passaged, and expanded on Vero cells, achieving a peak titer exceeding 10 6.25 50% cell culture infectious dose (CCID 50)/ml. Western blot and indirect immunofluorescence results showed that the isolates could be specifically recognized by monoclonal antibodies and convalescent serum against SARS-CoV-2. Transmission electron microscopy revealed oval-shaped viral particles with diameters of approximately 100 nm. Next-generation sequencing of the viral isolates demonstrated a sequence homology greater than 99.50% with the Wuhan-Hu-1 reference strain (NC_045512) and 99.98% among the seven isolated strains, and all of the isolates belonged to the Omicron BF.7 variant. Sequence analysis after continuous passage and plaque purification of the BJ-NVSI-20230005 isolate showed that compared with passages 1-3, passages 4-6 had one nucleotide site mutation (C→T) in the ORF1ab gene and a deletion of 3 bp in the E gene, which resulted in a change from leucine to phenylalanine and the deletion of valine, respectively. Polymorphisms were observed in the sequences of plaque-purified clones. Conclusions:The seven successfully isolated SARS-CoV-2 strains all belong to the SARS-CoV-2 BF.7 variant, which is consistent with the prevalence trend in mainland China in December 2022.

Nuclear receptor corepressor (NCoR1) interacts with various nuclear receptors and regulates the anabolism and catabolism of lipids. An imbalance in lipid/energy homeostasis is also an important factor in obesity and metabolic syndrome development. In this study, we found that the deletion of NCoR1 in intestinal epithelial cells (IECs) mainly activated the nuclear receptor PPARα and attenuated metabolic syndrome by stimulating thermogenesis. The increase in brown adipose tissue thermogenesis was mediated by gut-derived tricarboxylic acid cycle intermediate succinate, whose production was significantly enhanced by PPARα activation in the fed state. Additionally, NCoR1 deletion derepressed intestinal LXR, increased cholesterol excretion, and impaired duodenal lipid absorption by decreasing bile acid hydrophobicity, thereby reversing the possible negative effects of intestinal PPARα activation. Therefore, the simultaneous regulatory effect of intestinal NCoR1 on both lipid intake and energy expenditure strongly suggests that it is a promising target for developing metabolic syndrome treatment.

Objective To observe the saturation of peripheral oxygen(SpO2) fluctuation for early exer-cise induced desaturation in chronic obstructive pulmonary disease(COPD) patients ready for discharge and capable of basic self-care and analyze its risk factors.Methods A total of 142 COPD patients ready for discharge and capable of basic self-care,hospitalized in the Department of Pulmonary and Critical Care Medicine at the Second People's Hospital of Hefei,affiliated to Bengbu Medical Universi-ty,between May 2021 and May 2024,were selected.Based on whether exercise induced desaturation occurred during the 6-minute walk test(6MWT) and the timing of its onset,all patients were random-ly divided into a non-exercise induced desaturation(NEID) group,an early desaturation(ED) group,and a non-early desaturation(NED) group.The general data,lung function,and SpO2 fluctuation were compared among the three groups.Generalized estimating equation was used to analyze the SpO2 fluctu-ation for the occurrence of ED,and multivariable logistic regression was applied to analyze the risk factors for ED.Moreover,the receiver operating characteristic(ROC) curve was employed to evaluate the predictive value of these factors.Results Compared with the NEID group,the ED group had a low-er forced expiratory volume in the first second to the predicted value ratio(FEV1％pred),and the NED group had a higher proportion of patients complicated with emphysema(both P<0.05).During exercise,the ED group exhibited significantly lower mean SpO2(SpO2mean),minimum SpO2(SpO2min),the gap be-tween resting saturation of peripheral oxygen(SpO2rest)and SpO2min (?SpO2) compared to the other two groups(P<0.001 for all).The generalized estimating equation showed that there were significant differ-ences in the inter-group effect,time effect,and interaction effect of SpO2 among the three groups(P<0.001 for all).Moreover,SpO2 values of ED group were significantly lower than the other two groups at all exercise time points(P<0.001 for all).Univariate and multivariate logistic regression analyses showed that ?SpO2[OR=1.169;95％CI(1.011～1.352);P<0.05]was a risk factor for ED,while SpO2mean[OR=0.776;95％CI(0.637～0.947);P<0.05]was a protective factor.Meanwhile,the ROC curve for ?SpO2 predicting ED had an area under the curve (AUC) of 0.829,with a sensitivity of 0.714 and a speci-ficity of 0.785.Conclusion COPD patients ready for discharge and capable of basic self-care show more pronounced desaturation during exercise and greater SpO2 fluctuations when early desaturation oc-curs.?SpO2 is a risk factor for ED and has predictive value,which can be used for clinical diagno-sis and treatment.

Objective To observe the saturation of peripheral oxygen(SpO2) fluctuation for early exer-cise induced desaturation in chronic obstructive pulmonary disease(COPD) patients ready for discharge and capable of basic self-care and analyze its risk factors.Methods A total of 142 COPD patients ready for discharge and capable of basic self-care,hospitalized in the Department of Pulmonary and Critical Care Medicine at the Second People's Hospital of Hefei,affiliated to Bengbu Medical Universi-ty,between May 2021 and May 2024,were selected.Based on whether exercise induced desaturation occurred during the 6-minute walk test(6MWT) and the timing of its onset,all patients were random-ly divided into a non-exercise induced desaturation(NEID) group,an early desaturation(ED) group,and a non-early desaturation(NED) group.The general data,lung function,and SpO2 fluctuation were compared among the three groups.Generalized estimating equation was used to analyze the SpO2 fluctu-ation for the occurrence of ED,and multivariable logistic regression was applied to analyze the risk factors for ED.Moreover,the receiver operating characteristic(ROC) curve was employed to evaluate the predictive value of these factors.Results Compared with the NEID group,the ED group had a low-er forced expiratory volume in the first second to the predicted value ratio(FEV1％pred),and the NED group had a higher proportion of patients complicated with emphysema(both P<0.05).During exercise,the ED group exhibited significantly lower mean SpO2(SpO2mean),minimum SpO2(SpO2min),the gap be-tween resting saturation of peripheral oxygen(SpO2rest)and SpO2min (?SpO2) compared to the other two groups(P<0.001 for all).The generalized estimating equation showed that there were significant differ-ences in the inter-group effect,time effect,and interaction effect of SpO2 among the three groups(P<0.001 for all).Moreover,SpO2 values of ED group were significantly lower than the other two groups at all exercise time points(P<0.001 for all).Univariate and multivariate logistic regression analyses showed that ?SpO2[OR=1.169;95％CI(1.011～1.352);P<0.05]was a risk factor for ED,while SpO2mean[OR=0.776;95％CI(0.637～0.947);P<0.05]was a protective factor.Meanwhile,the ROC curve for ?SpO2 predicting ED had an area under the curve (AUC) of 0.829,with a sensitivity of 0.714 and a speci-ficity of 0.785.Conclusion COPD patients ready for discharge and capable of basic self-care show more pronounced desaturation during exercise and greater SpO2 fluctuations when early desaturation oc-curs.?SpO2 is a risk factor for ED and has predictive value,which can be used for clinical diagno-sis and treatment.