OBJECTIVES: We propose a Contrastive Regional Attention and Prior Knowledge-Infused U-Transformer model (CRAKUT) to address the challenges of imbalanced text distribution, lack of contextual clinical knowledge, and cross-modal information transformation to enhance the quality of generated radiology reports. METHODS: The CRAKUT model comprises 3 key components, including an image encoder that utilizes common normal images from the dataset for extracting enhanced visual features, an external knowledge infuser that incorporates clinical prior knowledge, and a U-Transformer that facilitates cross-modal information conversion from vision to language. The contrastive regional attention in the image encoder was introduced to enhance the features of abnormal regions by emphasizing the difference between normal and abnormal semantic features. Additionally, the clinical prior knowledge infuser within the text encoder integrates clinical history and knowledge graphs generated by ChatGPT. Finally, the U-Transformer was utilized to connect the multi-modal encoder and the report decoder in a U-connection schema, and multiple types of information were used to fuse and obtain the final report. RESULTS: We evaluated the proposed CRAKUT model on two publicly available CXR datasets (IU-Xray and MIMIC-CXR). The experimental results showed that the CRAKUT model achieved a state-of-the-art performance on report generation with a BLEU-4 score of 0.159, a ROUGE-L score of 0.353, and a CIDEr score of 0.500 in MIMIC-CXR dataset; the model also had a METEOR score of 0.258 in IU-Xray dataset, outperforming all the comparison models. CONCLUSIONS The proposed method has great potential for application in clinical disease diagnoses and report generation.
Humans ; Radiology Information Systems ; Radiology

The rapid identification of pathogenic microorganisms has become increasingly critical in clinical diagnostics and public health management. However, conventional detection methods are constrained by their limited analytical scope, suboptimal sensitivity, and time-consuming procedures, particularly in scenarios with unstable sample quality or low pathogen load, which frequently compromises diagnostic accuracy. In this context, high-throughput sequencing(HTS) technology has emerged as a pivotal technological approach in pathogen detection, leveraging its unparalleled throughput, ultrahigh sensitivity, and pan-pathogen detection capability. This article systematically reviews the technical principles of HTS, its specific applications in pathogen detection, and the corresponding data analysis methodologies, aiming to provide valuable insights and references for enhancing pathogen identification efficiency in clinical and epidemiological practice.

Objective To establish a clinical-CT model,and to observe its value for evaluating lymphovascular invasion(LVI)and/or perineural invasion(PNI)in esophageal squamous cell carcinoma(ESCC).Methods Data of 156 ESCC patients were retrospectively analyzed.The patients were divided into positive group(n=58,LVI[+]and/or PNI[+])and negative group(n=98,LVI[-]and PNI[-])according to postoperative pathological results.Clinical and CT data were compared between groups.Logistic regression analysis was performed to establish a model,and its efficacy of evaluating ESCC LVI and/or PNI was analyzed.Results Significant differences of carcinoembryonic antigen(CEA),carbohydrate antigen 199(CA199),tumor thickness,tumor volume and CT venous phase value(CTV),the difference between CTV and CT plain phase value(CTP)(△CTV-P)and venous phase enhancement rate(V％)were found between groups(all P＜0.05),and the area under the curve(AUC)of the above parameters for evaluating ESCC LVI and/or PNI was 0.702,0.690,0.731,0.744,0.621,0.631 and 0.599,respectively.CEA,CA199,tumor thickness,tumor volume and CTV were all independent predictive factors for ESCC LVI and/or PNI.A combined model was established based on the above features,and its accuracy,sensitivity and specificity for evaluating ESCC LVI and/or PNI was 82.05％,65.52％and 91.84％,respectively,with AUC of 0.838,higher than that of each single parameter(all P＜0.05).Conclusion The established clinical-CT model could effectively evaluate ESCC LVI and/or PNI.

Objective To observe the value of intratumoral and peritumoral CT radiomics for evaluating KRAS gene status in patients with colorectal adenocarcinoma.Methods Totally 245 patients with colorectal adenocarcinoma were retrospectively enrolled and divided into mutant group(n=139)and wild group(n=106)according to KRAS gene status,also divided into training set(n=171)and test set(n=74)at a ratio of 7∶3.Clinical data were compared between groups,and clinical factors were screened with logistic regression analysis to establish a clinical model.Based on enhanced venous phase CT images,intratumoral volume of interest(VOI),peritumoral VOI,and intratumoral+peritumoral VOI were delineated,radiomics features were extracted,and radiomics models were constructed.The combination model was constructed based on the best radiomics model combined with clinical factors.The value of each model for evaluating KRAS gene status in patients with colorectal adenocarcinoma was analyzed.Results Significant differences of patients’gender and carcinoembryonic antigen(CEA)were found between mutant group and wild group(both P＜0.05),which were independent impact factors of KRAS gene status in patients with colorectal adenocarcinoma(both P＜0.05).The area under the curve(AUC)of clinical model for evaluating KRAS gene status in patients with colorectal adenocarcinoma in training set and test set was 0.633 and 0.658,respectively.Intratumoral+peritumoral 3 mm model was the best radiomics model,with AUC of 0.921 and 0.894 in training set and test set,respectively.AUC of the combination model in training set and test set was 0.949 and 0.956,respectively.In training set,significant differences of AUC were found between clinical model and intratumoral+peritumoral 3 mm model,also between clinical model and combination model(both P＜0.001),while in test set,significant differences of AUC were found between each two models(all P＜0.05).Conclusion Intratumoral+peritumoral 3 mm radiomics based on enhanced venous phase CT could help to evaluate KRAS gene status in patients with colorectal adenocarcinoma.Combining with patients’gender and CEA could further improve efficacy of this model.

Objective To observe the value of contrast-enhanced CT radiomics combined with clinical and hematology indicators for predicting lymph node(LN)metastasis(LNM)of esophageal squamous cell carcinoma(ESCC).Methods Totally 218 ESCC patients were retrospectively enrolled.Stage pN1 and pN2 were clustering as LNM(n=90),while stage pN0 were taken as non-LNM(n=128).The patients were divided into training set(n=174)and test set(n=44)at the ratio of 8∶2.In training set,clinical and LN imaging features which could be used to independently judge LNM were screened and a clinical-imaging model was constructed.The hematological indicators that might be associated with ESCC LNM were screened,and a hematological model was constructed.Radiomics features in LN ROI and ESCC volume of interest(VOI)were extracted based on venous-phase contrast-enhanced CT images,and those might be associated with LNM were screened,and a radiomics model was constructed.Finally a combined model was constructed based on all the above features.The efficacy of each model for diagnosing LNM was evaluated with the area under the curve(AUC)of receiver operating characteristic curves,and the clinical net benefit was evaluated using decision curve analysis(DCA).Results Body mass index(BMI)and internal necrosis of target LN were both independent judging factors for ESCC LNM(both P＜0.05),and AUC of clinical-imaging model for diagnosing LNM in training and test sets was 0.747 and 0.687,respectively.Seven hematological indicators were included in hematological model,and AUC in training and test sets was 0.623 and 0.583,respectively.Ten LN radiomics features and 15 ESCC radiomics features were included in radiomics model,and AUC in training and test sets was 0.769 and 0.745,respectively.AUC of the combined model for diagnosing LNM in training and test sets was 0.822 and 0.739,respectively,better than other models in training set(all P＜0.05),but no significantly different in test set(all P＞0.05).DCA showed that combined model had higher net gain than the other models in 0.55-0.80 threshold probability interval.Conclusion Combined model based on venous-phase contrast-enhanced CT radiomics and clinical and hematology indicators could relatively effectively evaluate ESCC LNM,which might bring some promotions in clinical benefit.

OBJECTIVE To study the pharmacokinetics of small molecule inhibitor SYHA1809 in Beagle dogs. METHODS LC-MS/MS method was adopted. Beagle dogs were randomly divided into single intravenous administration group （3.75 mg/kg）， single low-dose intragastric administration group （3.75 mg/kg）， single medium-dose intragastric administration group （7.5 mg/kg）， single high-dose intragastric administration group （15 mg/kg） and multiple intragastric administration group （7.5 mg/kg， once a day， for 7 consecutive days）， with 6 dogs in each group， half male and half female. The plasma samples of Beagle dogs were collected in each group according to the set time point， and underwent LC-MS/MS quantitative analysis after preprocessing. The pharmacokinetic parameters were calculated by using Phoenix WinNonlin 8.0 software using obtained data. RESULTS After intravenous injection， CL of SYHA1809 in Beagle dogs was （2.70±0.48） mL/（min·kg）， steady-state distribution volume was 0.757 L/kg， and t1/2 was （3.35±1.36） h； after single intragastric administration of low-dose， medium-dose and high-dose of SYHA1809， average tmax was （0.53±0.02） h， and the blood drug concentration increased with the increase of dose； after single intragastric administration of 3.75 mg/kg SYHA1809， the absolute bioavailability was 83.5%； within the dose range of 3.75-15 mg/kg， the increase in cmax and AUC of SYHA1809 was positively correlated with the dose； after intragastric administration of 7.5 mg/kg SYHA1809 for 7 consecutive days， the pharmacokinetic parameters of SYHA1809 were comparable to those of a single intragastric administration of the same dose， with no statistically significant difference （P＞0.05）. CONCLUSIONS SYHA1809 is absorbed rapidly in Beagle dogs， shows the dose-dependent blood concentration， high bioavailability， no obvious accumulation after multiple intragastric administration， and good pharmacokinetic behavior.

Type 2 diabetes (T2D) is often accompanied with an induction of retinaldehyde dehydrogenase 1 (RALDH1 or ALDH1A1) expression and a consequent decrease in hepatic retinaldehyde (Rald) levels. However, the role of hepatic Rald deficiency in T2D progression remains unclear. In this study, we demonstrated that reversing T2D-mediated hepatic Rald deficiency by Rald or citral treatments, or liver-specific Raldh1 silencing substantially lowered fasting glycemia levels, inhibited hepatic glucogenesis, and downregulated phosphoenolpyruvate carboxykinase 1 (PCK1) and glucose-6-phosphatase (G6PC) expression in diabetic db/db mice. Fasting glycemia and Pck1/G6pc mRNA expression levels were strongly negatively correlated with hepatic Rald levels, indicating the involvement of hepatic Rald depletion in T2D deterioration. A similar result that liver-specific Raldh1 silencing improved glucose metabolism was also observed in high-fat diet-fed mice. In primary human hepatocytes and oleic acid-treated HepG2 cells, Rald or Rald + RALDH1 silencing resulted in decreased glucose production and downregulated PCK1/G6PC mRNA and protein expression. Mechanistically, Rald downregulated direct repeat 1-mediated PCK1 and G6PC expression by antagonizing retinoid X receptor α, as confirmed by luciferase reporter assays and molecular docking. These results highlight the link between hepatic Rald deficiency, glucose dyshomeostasis, and the progression of T2D, whilst also suggesting RALDH1 as a potential therapeutic target for T2D.

Drug-induced hyperglycemia/diabetes is a global issue. Some drugs induce hyperglycemia by activating the pregnane X receptor (PXR), but the mechanism is unclear. Here, we report that PXR activation induces hyperglycemia by impairing hepatic glucose metabolism due to inhibition of the hepatocyte nuclear factor 4-alpha (HNF4α)‒glucose transporter 2 (GLUT2) pathway. The PXR agonists atorvastatin and rifampicin significantly downregulated GLUT2 and HNF4α expression, and impaired glucose uptake and utilization in HepG2 cells. Overexpression of PXR downregulated GLUT2 and HNF4α expression, while silencing PXR upregulated HNF4α and GLUT2 expression. Silencing HNF4α decreased GLUT2 expression, while overexpressing HNF4α increased GLUT2 expression and glucose uptake. Silencing PXR or overexpressing HNF4α reversed the atorvastatin-induced decrease in GLUT2 expression and glucose uptake. In human primary hepatocytes, atorvastatin downregulated GLUT2 and HNF4α mRNA expression, which could be attenuated by silencing PXR. Silencing HNF4α downregulated GLUT2 mRNA expression. These findings were reproduced with mouse primary hepatocytes. Hnf4α plasmid increased Slc2a2 promoter activity. Hnf4α silencing or pregnenolone-16α-carbonitrile (PCN) suppressed the Slc2a2 promoter activity by decreasing HNF4α recruitment to the Slc2a2 promoter. Liver-specific Hnf4α deletion and PCN impaired glucose tolerance and hepatic glucose uptake, and decreased the expression of hepatic HNF4α and GLUT2. In conclusion, PXR activation impaired hepatic glucose metabolism partly by inhibiting the HNF4α‒GLUT2 pathway. These results highlight the molecular mechanisms by which PXR activators induce hyperglycemia/diabetes.

Objective To evaluate the feasibility and safety of tracheal extubation in operating room for patients with end-stage chronic obstructive pulmonary disease (COPD) after single-lung transplantation. Methods Clinical data of 57 recipients who underwent single-lung transplantation due to end-stage COPD were retrospectively analyzed. According to the evaluation indexes of tracheal extubation in operating room established by our hospital, 17 recipients eligible for tracheal extubation in operating room were assigned into the operating room extubation group (OR extubation group) and 40 recipients receiving tracheal extubation in intensive care unit (ICU) were allocated in the ICU extubation group. The evaluation results of intraoperative tracheal extubation and postoperative recovery were compared between two groups. Results Compared with the ICU extubation group, recipients in the OR extubation group had higher oxygenation index, lower arterial partial pressure of carbon dioxide (PaCO₂), lower blood lactic acid level, less fluctuation range of blood pressure and fewer cases receiving extracorporeal membrane oxygenation (ECMO) during operation (all P < 0.05). Two recipients in the OR extubation group received repeated tracheal intubation at 6 and 8 h after returning to ICU, and tracheal extubation at postoperative 6 and 9 d. In the OR extubation group, time of postoperative mechanical ventilation, length of postoperative ICU and hospital stay of the recipients were shorter than those in the ICU extubation group (all P < 0.05). The incidence of grade 3 primary graft dysfunction (PGD), atrial tachyarrhythmia, continuous renal replacement therapy and 1-year survival rate did not significantly differ between two groups (all P > 0.05). Conclusions The tracheal extubation regimen in the operating room for COPD patients after single-lung transplantation established by our hospital is safe and feasible, which shortens the time of postoperative mechanical ventilation, the length of postoperative ICU and hospital stay, whereas does not increase the incidence of postoperative complications.

Objective: To investigate the expression of miR-1269 in non-small-cell lung cancer (NSCLC) tissues, and to explore its effect on the cellular biological characteristics of NSCLC A549 cells and the underlying mechanism. Methods: 34 pairs of NSCLC tissues and the corresponding adjacent para-cancerous tissues obtained from the patients, who underwent surgery in the Department of Breast Surgery, the Fourth Hospital of Hebei Medical University from Jan. 2017 to Jan. 2018, were collected for this study. The expression level of miR-1269 in above tissue specimens was examined by real-time fluorescent quantitative PCR.After transfection with miR1269 mimics and mimics NC (negative control), the proliferation, migration and invasion of A549 cells were detected by MTS, Wound healing and Transwell assay, respectively; and the changes in cell cycle distribution of A549 cells were examined by flow cytometry. The bioinformatics tool was used to predict the possible target gene of miR-1269, and the regulation effect of miR-1269 on target gene was then validated by Western blotting and Dual-luciferase reporter assay. In the meanwhile, the protein expressions of cyclin depen dent kinase inhibitor p21, Cyclin D2, and EMT-related proteins (E-cadherin and ZEB2) in the transfected A549 cells were measured by Western blotting. Results: The expression level of miR-1269 in NSCLC tissues was significantly higher than that in paracancerous tissues (2.81±2.27 vs 1.61±1.36, P <0.05). The capacities of proliferation, migration and invasion ofA549 cells in miR-1269 mimics transfection group were significantly higher than those in mimics NC group and blank control group (all P <0.01). And the cell proportion at S-phase in miR-1269-mimics group was obviously higher than that in mimics NC group [(46.54±1.57)% vs (23.32±3.15)%， P<0.01]. Bioinformatics analysis showed that miR-1269 could combine with 3’UTR of FOXO1 gene. After transfection with miR-1269 mimics, the expression level and luciferase activity of FOXO1 protein in A549 cells were significantly reduced (all P <0.01). Moreover, the protein expressions of p21 and E-cadherin were significantly decreased after over-expression of miR-1269 (all P <0.05), while the expressions of ZEB2 and Cyclin D2 were up-regulated (all P <0.05). Conclusion: The expression level of miR-1269 in NSCLC tissues was significantly increased, and it could enhance the proliferation, cell cycle progression, migration and invasion ofA549 cells. The possible mechanism may be related to its targeted regulation of FOXO1.