Synthetic CT (sCT) generated from CBCT has proven effective in artifact reduction and CT number correction, facilitating precise radiation dose calculation. However, the quality of different regions in sCT images is severely imbalanced, with soft tissue region exhibiting notably inferior quality compared to others. To address this imbalance, we proposed a Multi-Task Attention Network (MuTA-Net) based on VGG-16, specifically focusing the enhancement of image quality in soft tissue region of sCT. First, we introduced a multi-task learning strategy that divides the sCT generation task into three sub-tasks: global image generation, soft tissue region generation and bone region segmentation. This approach ensured the quality of overall sCT image while enhancing the network's focus on feature extraction and generation for soft tissues region. The result of bone region segmentation task guided the fusion of sub-tasks results. Then, we designed an attention module to further optimize feature extraction capabilities of the network. Finally, by employing a results fusion module, the results of three sub-tasks were integrated, generating a high-quality sCT image. Experimental results on head and neck CBCT demonstrated that the sCT images generated by the proposed MuTA-Net exhibited a 12.52% reduction in mean absolute error in soft tissue region, compared to the best performance among the three comparative methods, including ResNet, U-Net, and U-Net++. It can be seen that MuTA-Net is suitable for high-quality sCT image generation and has potential application value in the field of CBCT guided adaptive radiation therapy.
Cone-Beam Computed Tomography/methods* ; Humans ; Image Processing, Computer-Assisted/methods* ; Artifacts ; Algorithms ; Bone and Bones/diagnostic imaging* ; Neural Networks, Computer

Prostate cancer (PCa) ranks as the second most prevalent malignancy among men worldwide. Early diagnosis, personalized treatment, and prognosis prediction of PCa play a crucial role in improving patients' survival rates. The advancement of artificial intelligence (AI), particularly the utilization of deep learning (DL) algorithms, has brought about substantial progress in assisting the diagnosis, treatment, and prognosis prediction of PCa. The introduction of the foundation model has revolutionized the application of AI in medical treatment and facilitated its integration into clinical practice. This review emphasizes the clinical application of AI in PCa by discussing recent advancements from both pathological and imaging perspectives. Furthermore, it explores the current challenges faced by AI in clinical applications while also considering future developments, aiming to provide a valuable point of reference for the integration of AI and clinical applications.
Humans ; Prostatic Neoplasms/diagnosis* ; Male ; Artificial Intelligence ; Deep Learning ; Prognosis

Objective To assess the clinical value of prognostic nutritional index(PNI)in predicting the prognosis of patients with advanced liver cancer treated with transarterial chemoembolization(TACE)combined with ablation therapy.Methods A total of 112 patients with advanced liver cancer,who received TACE combined with ablation at the Lishui Municipal Central Hospital of China from January 2020 to January 2024,were enrolled in this study.The general data,survival status,and survival time were collected.The Youden index of PNI was calculated using the receiver operating characteristic(ROC)curve model,and the optimal cutoff value was determined.Based on the optimal cutoff value,the patients were divided into low-PNI group and high-PNI group.The progression-free survival(PFS)and overall survival(OS)time were compared between the two groups,and the independent risk factors affecting PFS and OS were analyzed.Results The Youden index for PNI was 0.43,and the optimal cutoff value of PNI was 43.95.The low-PNI group included 65 patients,and the high-PNI group included 47 patients.There were no statistically significant differences in the baseline data between the two groups.The median PFS and the median OS in the high-PNI group were 13.21 months(95％CI=4.37-22.03)and 40.80 months(95％CI=31.55-50.05)respectively,which were longer than 9.20 months(95％CI=6.58-11.82)and 21.37 months(95％CI=16.56-26.17)respectively in the low-PNI group,the differences were statistically significant(both P＜0.05).The 6-month,one-year and 2-year PFS in the high-PNI group was 56.95％,47.25％and 33.87％respectively,which were higher than 43.95％,32.56％and 16.31％respectively in the low-PNI group.The one-year,2-year and 3-year cumulative survival rates in the high-PNI group were 80.77％,66.66％and 39.40％respectively,which were higher than 63.79％,34.31％and 27.75％respectively in the low-PNI group.Multivariate regression analysis indicated that the number of nodules,metastasis and PNI significantly affected OS,and metastasis and PNI strikingly affected PFS.High PNI was a protective factor for both PFS and OS.Conclusion For patients with advanced liver cancer treated with TACE combined with ablation therapy,PNI is an effective indicator for predicting the prognosis.

Objective To evaluate the combination score of albumin-bilirubin index(ALBI)and alkaline phosphatase(ALP)in predicting the prognosis of patients with cirrhosis complicated by portal hypertension after receiving transjugular intrahepatic portosystemic shunt(TIPS).Methods A total of 61 patients with cirrhosis complicated by portal hypertension,who received TIPS treatment at the Lishui Municipal Central Hospital of China from January 2016 to June 2024,were retrospectively collected.According to the Youden index of ALBI and ALP,the optimal cut-off values were calculated,and the patients were divided into low ALBI-low ALP group(0-point group),high ALBI-high ALP group(2-point group),and high ALBI-low ALP or low ALBI-high ALP group(one-point group).The efficacy of ALBI-ALP score in predicting the prognosis of patients was evaluated,and the survival rate and median survival time were compared between each other among the three groups.The independent risk factors affecting the survival time of patients were analyzed.Results The maximum Youden indexes of ALBI and ALP were 0.31 and 0.34 respectively,and the optimal cut-off values were-1.56 and 108.50 respectively.There were statistically significant differences in MELD score,Child-Pugh classification,and alanine aminotransferase level between each other among the three groups(all P＜0.05).The area under the ROC curve(AUC)of ALBI-ALP score was 0.77(95％ CI:0.66-0.89,P=0.000 2),which was better than 0.52 of the MELD score(95％ CI:0.37-0.67,P=0.77)as well as better than 0.57 of the Child-Pugh classification(95％ CI:0.43-0.72,P=0.34).The total mortality of patients was 49.18％.The mortality in the 0-point group was 11.11％(2/18),which was significantly lower than 59.46％(22/37)in the one-point group as well as than 100％(6/6)in the 2-point group,and the differences were statistically significant(x2=18.20,P＜0.001).In the 0-point group,as a large number of patients were still alive at the end of the study,the median survival time was unable to be calculated.The median survival time in the one-point group was 38.00 months(95％ CI:23.01-52.99 months),which in the 2-point group was only 1.00 month(95％ CI=0.00-2.60 months),the difference was statistically significant(x2=33.08,P＜0.000 1).In the 0-point group,one-point group and 2-point group,the one-year survival rates were 100％,66％ and 17％respectively,the 2-year survival rates were 100％,64％ and 17％ respectively,and the 3-year survival rates were 90％,53％ and 0％ respectively.Cox multivariate regression analysis showed that the combination score of ALBI and ALP(HR=7.11,95％ CI:2.95-17.15)was an independent risk factor for the survival time of patients with cirrhosis complicated by portal hypertension after receiving TIPS.Conclusion The combination score of ALBI and ALP can effectively predict the prognosis of patients with cirrhosis complicated by portal hypertension after receiving TIPS,and this score is an independent risk factor affecting the survival time of patients.

Diabetic peripheral neuropathy is a common complication of diabetes. There are various screening and assessment methods available, but most of them are not widely adopted in China. The diagnostic efficacy varies, making it somewhat challenging to choose the appropriate examination methods for conducting related clinical work and research. This article provides an overview of the existing screening and assessment methods for diabetic peripheral neuropathy and introduces and evaluates the latest research developments.

The aldo-keto reductase super family (AKRs) has a wide range of substrate specificity. However, the systematic identification of insect AKR gene family members has not been reported. In this study, bioinformatics methods were used to predict the phylogenetic evolution, physical and chemical properties, chromosome location, conserved motifs, and gene structure of AKR family members in Bombyx mori (BmAKR). Transcriptome data or quantitative real time polymerase chain reaction (qRT-PCR) were used to analyze the expression level of BmAKR genes during different organizational periods and silkworm eggs in different developmental states. Moreover, Western blotting was used to detect the expression level of the BmAKR in silkworm eggs. The results showed that 11 BmAKR genes were identified. These genes were distributed on 4 chromosomes of the silkworm genome, all of which had the (α/β) 8-barrel motif, and their physical and chemical characteristics were relatively similar. Phylogenetic analysis showed that the BmAKR genes could be divided into 2 subgroups (AKR1 and AKR2). Transcriptome data analysis showed that the expression of BmAKR genes were quite different in different tissues and periods. Moreover, the expression analysis of BmAKR genes in silkworm eggs showed that some genes were expressed significantly higher in nondiapause eggs than in diapause eggs; but another gene, BmAKR1-1, was expressed significantly higher in diapause eggs than in nondiapause eggs. The detection of protein level found that the difference trend of BmAKR1-1 in diapause eggs and non-diapause eggs was consistent with the results of qRT-PCR. In conclusion, BmAKR1-1 was screened out as candidates through the identification and analysis of the BmAKR genes in silkworm, which may regulate silkworm egg development is worthy of further investigation.
Animals ; Bombyx/metabolism* ; Phylogeny ; Diapause ; Genes, Insect ; Gene Expression Profiling ; Insect Proteins/metabolism*

OBJECTIVES: The automatic delineation of organs at risk (OARs) can help doctors make radiotherapy plans efficiently and accurately, and effectively improve the accuracy of radiotherapy and the therapeutic effect. Therefore, this study aims to propose an automatic delineation method for OARs in cervical cancer scenarios of both after-loading and external irradiation. At the same time, the similarity of OARs structure between different scenes is used to improve the segmentation accuracy of OARs in difficult segmentations. METHODS: Our ensemble model adopted the strategy of ensemble learning. The model obtained from the pre-training based on the after-loading and external irradiation was introduced into the integrated model as a feature extraction module. The data in different scenes were trained alternately, and the personalized features of the OARs within the model and the common features of the OARs between scenes were introduced. Computer tomography (CT) images for 84 cases of after-loading and 46 cases of external irradiation were collected as the train data set. Five-fold cross-validation was adopted to split training sets and test sets. The five-fold average dice similarity coefficient (DSC) served as the figure-of-merit in evaluating the segmentation model. RESULTS: The DSCs of the OARs (the rectum and bladder in the after-loading images and the bladder in the external irradiation images) were higher than 0.7. Compared with using an independent residual U-net (convolutional networks for biomedical image segmentation) model [residual U-net (Res-Unet)] delineate OARs, the proposed model can effectively improve the segmentation performance of difficult OARs (the sigmoid in the after-loading CT images and the rectum in the external irradiation images), and the DSCs were increased by more than 3%. CONCLUSIONS Comparing to the dedicated models, our ensemble model achieves the comparable result in segmentation of OARs for different treatment options in cervical cancer radiotherapy, which may be shorten time for doctors to sketch OARs and improve doctor's work efficiency.
Female ; Humans ; Image Processing, Computer-Assisted/methods* ; Machine Learning ; Organs at Risk/radiation effects* ; Radiotherapy Planning, Computer-Assisted/methods* ; Uterine Cervical Neoplasms/radiotherapy*

Objective: : EID3 (EP300-interacting inhibitor of differentiation) was identified as a novel member of EID family and plays a pivotal role in colorectal cancer development. However, its role in glioma remained elusive. In current study, we identified EID3 as a novel oncogenic molecule in human glioma and is critical for glioma cell survival, proliferation and invasion. Methods: : A total of five patients with glioma were recruited in present study and fresh glioma samples were removed from patients. Four weeks old male non-obese diabetic severe combined immune deficiency (NOD/SCID) mice were used as transplant recipient models. The subcutaneous tumor size was calculated and recorded every week with vernier caliper. EID3 and AMP-activated protein kinase α1 (AMPKα1) expression levels were confirmed by real-time polymerase chain reaction and Western blot assays. Colony formation assays were performed to evaluate cell proliferation. Methyl thiazolyl tetrazolium (MTT) assays were performed for cell viability assessment. Trypan blue staining approach was applied for cell death assessment. Cell Apoptosis DNA ELISA Detection Kit was used for apoptosis assessment. Results: : EID3 was preferentially expressed in glioma tissues/cells, while undetectable in astrocytes, neuronal cells, or normal brain tissues. EID3 knocking down significantly hindered glioma cell proliferation and invasion, as well as induced reduction of cell viability, apoptosis and cell death. EID3 knocking down also greatly inhibited tumor growth in SCID mice. Knocking down of AMPKα1 could effectively rescue glioma cells from apoptosis and cell death caused by EID3 absence, indicating that AMPKα1 acted as a key downstream regulator of EID3 and mediated suppression effects caused by EID3 knocking down inhibition. These findings were confirmed in glioma cells generated patient-derived xenograft models. AMPKα1 protein levels were affected by MG132 treatment in glioma, which suggested EID3 might down regulate AMPKα1 through protein degradation. Conclusion : Collectively, our study demonstrated that EID3 promoted glioma cell proliferation and survival by inhibiting AMPKα1 expression. Targeting EID3 might represent a promising strategy for treating glioma.

Objective:To compare the detection rate of genital Chlamydia trachomatis (CT) DNA between urine and urethral/cervical swab samples. Methods:From December 2018 to December 2019, a total of 1 475 outpatients were collected from sexually transmitted disease clinics in 7 medical institutions, such as Department of Venereology, Guangzhou Institute of Dermatology, including 1 118 males and 357 females. One urethral/cervical swab sample and one urine sample were collected successively from each patient. Real-time fluorescence-based PCR was performed to detect CT DNA in urine and urethral/cervical swab samples, and paired chi-square test was used to compare the positive rate of CT DNA between the 2 kinds of samples. Random- or fixed-effect meta-analysis was conducted for the test of heterogeneity and merging of positive rates of CT DNA in the urine and urethral/cervical swabs among 7 medical institutions.Results:The positive rate of CT DNA in the urine samples was significantly higher than that in the swab samples from 4 medical institutions (all P < 0.05) , while there was no significant difference in the positive rate of CT DNA between the 2 kinds of samples from 3 medical institutions (all P > 0.05) . The heterogeneity ( I2) estimates of the CT-DNA positive rate in urine and swab samples among different medical institutions were 78.6% (95% CI: 55.9% - 89.6%) and 73.7% (95% CI: 43.7% - 87.7%) , respectively; meta-analysis showed that the total merged positive rate of CT DNA in the urine samples was 10.8% (95% CI: 7.2% - 15.9%) , which was significantly higher than that in the swab samples (7.8%, 95% CI: 4.9% - 12.1%; χ2 = 39.2, P < 0.05) . Compared with the swab sample-based CT-DNA detection method, the sensitivity, specificity, positive predictive value, negative predictive value and consistency rate of the urine sample-based CT-DNA detection method were 97.0% (128/132) , 96.3% (1 293/1 343) , 71.9% (128/178) , 99.7% (1 293/1 297) , and 96.3% (1 421/1 475) , respectively. The positive rate of CT DNA in the urine samples from 1 118 male patients was 11.0% (95% CI: 7.2% - 16.5%) , which was significantly higher than that in the swab samples (7.6%, 95% CI: 4.9% - 11.8%; χ2 = 34.3, P < 0.05) . There was no significant difference in the positive rate of CT DNA between the urine (11.9%, 95% CI: 7.7% - 17.9%) and cervical swab samples from 357 female patients (10.4%, 95% CI: 7.6% - 14.0%; χ2 = 3.2, P > 0.05) . Conclusions:The positive rate of CT DNA in urine samples is higher than or similar to that in urethral/cervical swab samples. The urine sample-based CT-DNA detection method has characteristics of convenience, non-invasiveness, painlessness and low cost, and is worthy of clinical promotion.

Objective:To investigate the effects of dexmedetomidine on perioperative coagulation function and inflammatory factors in patients with malignant ovarian tumors.Methods:A total of 60 patients undergoing cytoreductive surgery for malignant ovarian tumors from September 2019 to May 2020 in the Second Hospital of Shanxi Medical University were selected and divided into the dexmedetomidine group and the control group according to the random number table method, 30 cases in each group. Patients in the dexmedetomidine group were pumped with dexmedetomidine 0.5 μg/kg 10 min before induction of anesthesia, and then the intravenous pump was maintained at a rate of 0.2-0.6 μg·kg -1·h -1 until 30 min before the completion of the operation pump injection. The control group was pumped with 0.9% NaCl solution of the same volume at the same time. Before induction of anesthesia (T 0), 2 h after administration (T 1), and 3 h after operation (T 2), the patients' venous blood was collected to detect platelet count (Plt), prothrombin time (PT), activated partial thrombin time (APTT), plasma fibrinogen (FIB), D-dimer; and levels of serum inflammatory factors interleukin 6 (IL-6) and tumor necrosis factor α (TNF-α) were also detected. The operation time, intraoperative fluid infusion, amount of anesthetics, and total intraoperative blood loss were compared between the two groups. Results:Plt at T 1 and T 2 time were (154±28)×10 9/L, (138±27)×10 9/L of the dexmedetomidine group and (133±44)×10 9/L, (114±50)×10 9/L of the control group, which were lower than those of both groups at T 0 time [(182±46)×10 9/L, (184±55)×10 9/L], and the differences were statistically significant ( F values were 11.975, 16.058, all P < 0.05); and Plt at T 1 and T 2 time of the control group were lower than those of the dexmedetomidine group (all P < 0.05). FIB level at T 1 and T 2 time [(3.2±0.9) g/L, (3.3±0.9) g/L of the dexmedetomidine group; (3.7±0.6) g/L, (4.6±0.9) g/L of the control group] and D-dimer level at T 1 and T 2 time [(0.77±0.25) mg/L, (0.81±0.51) mg/L of the dexmedetomidine group; (0.96±0.31) mg/L, (1.15±0.56) mg/L of the control group] were higher than those of both groups at T 0 time [FIB: (3.0met) g/L, (2.8 met) g/L; D-dimer: (0.65rt T) mg/L, (0.63 rt T) mg/L], and the differences were statistically significant (F values were 5.234, 46.121, 4.358, 11.091, all P < 0.05); FIB and D-dimer levels at T 1 and T 2 time of the control group were higher than those of the dexmedetomidine group (all P < 0.05). PT and APTT at T 2 time of the dexmedetomidine group were (12.7±0.5) s and (33.8±3.7) s, respectively, and the control group were (12.3±0.8) s, (31.8±2.4)s, respectively, which were shorter than those of both groups at T 0 time [PT: (13.0±0.3) s, (13.0±0.3) s; APTT: (35.7±2.0) s, (35.7±2.6) s], and the differences were statistically significant (all P < 0.05), and PT and APTT levels at T 2 time of the control group were shorter than those of the dexmedetomidine group (all P < 0.05). IL-6 level at T 1 and T 2 time [(73.3±2.8) pg/L, (84.7±3.8) pg/L of the dexmedetomidine group; (81.5±3.6) pg/L, (89.8±3.2) pg/L of the control group] and TNF-α level at T 1 and T 2 time [(27.4±4.4) ng/L, (32.9±3.7) ng/L of the dexmedetomidine group; (32.7±2.5) ng/L, (39.8±4.0) ng/L of the control group] were higher than those of both groups at T 0 time [IL-6: (65.9±2.9) pg/L, (65.0±1.8) pg/L; TNF-α: (15.4±3.1) ng/L, (16.6±2.6) ng/L)], and the differences were statistically significant ( F values were 264.650, 553.019, 162.447, and 438.225, respectively, all P < 0.05), and IL-6 and TNF-α levels at T 1 and T 2 time of the control group were higher than those of the dexmedetomidine group (all P < 0.05). There were no statistically significant differences in operation time, intraoperative fluid infusion, and intraoperative total blood loss between the two groups (all P > 0.05), but the intraoperative use of propofol and remifentanil of the control group was more than that of the dexmedetomidine group (all P < 0.05). Conclusion:Dexmedetomidine under general anesthesia for malignant ovarian patients undergoing surgery can effectively improve the perioperative coagulation function and reduce the level of inflammatory factors, thereby reducing the risk of postoperative thrombotic events.