1.Real-Time Typical Urodynamic Signal Recognition System Using Deep Learning
Xin LIU ; Ping ZHONG ; Di CHEN ; Limin LIAO
International Neurourology Journal 2025;29(1):40-47
Purpose:
Gold-standard urodynamic examination is widely used in the diagnosis and treatment of lower urinary tract dysfunction. The purpose of urodynamic quality control is to standardize urodynamic examination and ensure its clinical reference value. In our study, we attempted to use a deep learning (DL) algorithm model, mainly for the recognition of typical urodynamic signal, to help physicians complete high-quality urodynamic examinations.
Methods:
Urodynamic image data from 2 cohorts of adult patients with neurogenic bladder were used: (1) 300 patients with neurogenic bladder in our center from 2012 to 2018 (1,960 images used to train and validate the DL model); and (2) 100 patients with neurogenic bladder from 2020 to 2021 (695 images used to test the performance of the DL model). This resulted in a total of 2,655 images to train, validate and test the DL algorithm to predict the urdynamic signals.
Results:
Yolov5l had the best detection performance and the highest comprehensive index score (F1, 0.81; mean average precision, 0.83). Our study is a retrospective single-center study, and the generalization ability of the model has not been verified.
Conclusions
DL algorithms can help operators identify typical urodynamic signals in real time, improve the interpretation and quality of urodynamic examination, and benefit patients.
2.Design, synthesis and anti-Alzheimer's disease activity evaluation of cinnamyl triazole compounds
Wen-ju LEI ; Zhong-di CAI ; Lin-jie TAN ; Mi-min LIU ; Li ZENG ; Ting SUN ; Hong YI ; Rui LIU ; Zhuo-rong LI
Acta Pharmaceutica Sinica 2025;60(1):150-163
19 cinnamamide/ester-triazole compounds were designed, synthesized and evaluated for their anti-Alzheimer's disease (AD) activity. Among them, compound
3.Real-Time Typical Urodynamic Signal Recognition System Using Deep Learning
Xin LIU ; Ping ZHONG ; Di CHEN ; Limin LIAO
International Neurourology Journal 2025;29(1):40-47
Purpose:
Gold-standard urodynamic examination is widely used in the diagnosis and treatment of lower urinary tract dysfunction. The purpose of urodynamic quality control is to standardize urodynamic examination and ensure its clinical reference value. In our study, we attempted to use a deep learning (DL) algorithm model, mainly for the recognition of typical urodynamic signal, to help physicians complete high-quality urodynamic examinations.
Methods:
Urodynamic image data from 2 cohorts of adult patients with neurogenic bladder were used: (1) 300 patients with neurogenic bladder in our center from 2012 to 2018 (1,960 images used to train and validate the DL model); and (2) 100 patients with neurogenic bladder from 2020 to 2021 (695 images used to test the performance of the DL model). This resulted in a total of 2,655 images to train, validate and test the DL algorithm to predict the urdynamic signals.
Results:
Yolov5l had the best detection performance and the highest comprehensive index score (F1, 0.81; mean average precision, 0.83). Our study is a retrospective single-center study, and the generalization ability of the model has not been verified.
Conclusions
DL algorithms can help operators identify typical urodynamic signals in real time, improve the interpretation and quality of urodynamic examination, and benefit patients.
4.Real-Time Typical Urodynamic Signal Recognition System Using Deep Learning
Xin LIU ; Ping ZHONG ; Di CHEN ; Limin LIAO
International Neurourology Journal 2025;29(1):40-47
Purpose:
Gold-standard urodynamic examination is widely used in the diagnosis and treatment of lower urinary tract dysfunction. The purpose of urodynamic quality control is to standardize urodynamic examination and ensure its clinical reference value. In our study, we attempted to use a deep learning (DL) algorithm model, mainly for the recognition of typical urodynamic signal, to help physicians complete high-quality urodynamic examinations.
Methods:
Urodynamic image data from 2 cohorts of adult patients with neurogenic bladder were used: (1) 300 patients with neurogenic bladder in our center from 2012 to 2018 (1,960 images used to train and validate the DL model); and (2) 100 patients with neurogenic bladder from 2020 to 2021 (695 images used to test the performance of the DL model). This resulted in a total of 2,655 images to train, validate and test the DL algorithm to predict the urdynamic signals.
Results:
Yolov5l had the best detection performance and the highest comprehensive index score (F1, 0.81; mean average precision, 0.83). Our study is a retrospective single-center study, and the generalization ability of the model has not been verified.
Conclusions
DL algorithms can help operators identify typical urodynamic signals in real time, improve the interpretation and quality of urodynamic examination, and benefit patients.
5.Cloning and gene functional analysis study of dynamin-related protein GeDRP1E gene in Gastrodia elata
Xin FAN ; Jian-hao ZHAO ; Yu-chao CHEN ; Zhong-yi HUA ; Tian-rui LIU ; Yu-yang ZHAO ; Yuan YUAN
Acta Pharmaceutica Sinica 2024;59(2):482-488
The gene
6.Multimodal ultrasound and ultrasound-guided fine-needle aspiration biopsy for distinguishing benign and malignant thyroid nodules of C-TIRADS grade 4
Di ZHONG ; Di TANG ; Xiaoqiang GAO ; Haixia LI ; Hongbo WANG ; Ying LIU
Chinese Journal of Medical Imaging Technology 2024;40(2):182-185
Objective To compare the value of multimodal ultrasound and ultrasound-guided fine-needle aspiration biopsy(US-FNAB)for distinguishing benign and malignant thyroid nodules of Chinese thyroid imaging reporting and data system(C-TIRADS)grade 4.Methods Data of 247 thyroid nodules in 201 patients were retrospectively analyzed,including 193 malignant and 54 benign noes.Taken postoperative pathology as the gold standards,the value of multimodal ultrasound,i.e.the combination of conventional ultrasound,shear wave elastography(SWE)and contrast-enhanced ultrasound(CEUS)and US-FNAB for distinguishing benign and malignant thyroid nodules were compared.Results The sensitivity,specificity,accuracy,misdiagnosis rate and rate of missed diagnosis of conventional ultrasound for diagnosing malignant thyroid nodules was 86.53%,59.26%,80.57%,40.74%and 13.47%,respectively,of SWE was 78.76%,74.07%,77.73%,25.93%and 21.24%,respectively,of CEUS was 90.16%,77.78%,87.45%,22.22%and 9.84%,respectively,while of multimodal ultrasound was 97.93%,88.89%,95.95%,11.11%and 2.07%,respectively,and of US-FNAB was 89.64%,96.30%,91.09%,3.70%and 10.36%,respectively.The sensitivity,specificity and accuracy of multimodal ultrasound for distinguishing benign and malignant thyroid nodules were higher,while the misdiagnosis rate and missed diagnosis rate were lower than those of conventional ultrasound,SWE and CEUS alone.The sensitivity,accuracy and misdiagnosis rate of multimodal ultrasound were higher,while its specificity and missed diagnosis rate were both lower than those of US-FNAB(all P<0.05).Conclusion For distinguishing benign and malignant thyroid nodules of C-TIRADS grade 4,multimodal ultrasound had higher sensitivity and accuracy but higher misdiagnosis rate,while US-FNAB had higher specificity but also higher missed diagnosis rate.
7.Efficacy-driving Mechanism of Danhong Injection for Stable Angina Pectoris Based on Composition-activity Relationship of Target Modules
Siwei TIAN ; Wenjing ZONG ; Jun LIU ; Wei YANG ; Qikai NIU ; Siqi ZHANG ; Jing'ai WANG ; Huamin ZHANG ; Zhong WANG ; Bing LI
Chinese Journal of Experimental Traditional Medical Formulae 2024;30(23):121-128
ObjectiveTo explore the efficacy-driving mechanism of Danhong injection (DHI) in the treatment of stable angina pectoris (SAP) based on the composition-activity relationship of target modules and clarify the pharmacological effects of DHI. MethodAccording to the angina frequency (AF) in the Seattle Angina Questionnaire (SAQ) that was obtained in the previous clinical trial, the patients before and after DHI treatment were grouped based on efficacy. The transcriptomic data of the patients before treatment and in the best efficacy group 30 days post-treatment were selected as the data source, and then weighted gene co-expression network analysis (WGCNA) was employed to construct the co-expression network. Relevant modules in the network were identified and associated with clinical features. In addition, the On-modules (Z value below 0) were identified by Zsummary. The topological indicators such as density, centrality, and clustering coefficient were adopted to explore the dynamics of DHI efficacy at the network level and module level, respectively. In addition, the driver genes were screened by the personalized network control (PNC) algorithm. Finally, rat H9C2 cells were used to establish the model of hypoxia/reoxygenation (H/R), which was used to confirm the potential therapeutic target of DHI for SAP and provide a scientific basis for revealing the therapeutic mechanism of DHI. ResultWe identified 19 modules in the best efficacy group of DHI for SAP, and the comparison between day 0 and day 30 revealed 12 On-modules. The changes of network topological indicators at the network and module levels confirmed the correlation between the best efficacy of DHI treatment and topological dynamics. Finally, the driver genes, Klotho and fibroblast growth factor 22 (FGF22), in DHI treatment of SAP were verified by the H9C2 cell model of H/R. ConclusionBased on clinical transcriptome data, this study determined the composition-activity relationship of target modules of DHI for SAP, which provided a scientific basis for deciphering the efficacy-driven mechanism of DHI for SAP.
8.Application of 18F-AlF-P16-093 PET combined with multiparametric MRI in the diagnosis of primary prostate cancer lesions: a head-to-head comparative study based on needle biopsy pathology
Miao KE ; Jinhui LIU ; Shaonan ZHONG ; Jing ZHANG ; Mingzhao LI ; Di GU ; Ruiyue ZHAO ; Xinlu WANG
Chinese Journal of Nuclear Medicine and Molecular Imaging 2024;44(9):533-538
Objective:To evaluate the diagnostic efficacy of the novel prostate specific membrane antigen (PSMA)-targeted PET imaging agent 18F-AlF-P16-093 in combination with multiparametric MRI (mpMRI) for prostate cancer (PCa), and to explore its application in guiding transperineal puncture biopsy. Methods:A retrospective analysis was conducted on the clinical and pathological data of 36 patients diagnosed as PCa (age: 68-76 years) who underwent 18F-AlF-P16-093 PET/CT and mpMRI examinations at the First Affiliated Hospital of Guangzhou Medical University from August 2023 to March 2024. The entire prostate was divided into 12 regions based on biopsy localization. Imaging evaluations were performed using PET/CT and mpMRI at the lesion level, with biopsy pathology as the gold standard. The correlations between mpMRI scores, PET/CT scores and pathological diagnosis results were evaluated by Phi coefficient analysis. Diagnostic efficacy was assessed by ROC curve analysis. Logistic regression was used to determine the impact of bleeding on image interpretation. Results:18F-AlF-P16-093 PET/CT showed a moderate positive correlation with pathological diagnosis result ( Phi=0.415, P<0.001), which was superior to mpMRI ( Phi=0.338, P<0.001). The diagnostic efficacy of PET single-modality model was superior to mpMRI in all indicators. The combination of 18F-AlF-P16-093 PET/CT with mpMRI significantly improved diagnostic specificity and positive predictive value, with the diagnostic specificity of the PET+ T 2 weighted imaging (WI)+ diffusion WI (DWI) and PET+ T 2WI+ DWI+ apparent diffusion coefficient (ADC) combinations exceeding 90%, and the positive predictive value exceeding 80%. Bleeding did not significantly affect the diagnosis of PCa by mpMRI and PET/CT (odds ratio ( OR): 0.463-0.785, all P>0.05). Conclusion:18F-AlF-P16-093 PET/CT is superior to mpMRI in the detection and diagnostic efficacy of PCa lesions, and the combination of 18F-AlF-P16-093 PET with mpMRI can further improve diagnostic specificity and positive predictive value, which is of guiding significance for targeted prostate biopsy.
9.Clinical effects of Yiqi Shengjin Prescription on patients with primary Sj?gren's syndrome due to Dual Deficiency of Qi and Yin
Zhong-Fu TANG ; Chuan-Bing HUANG ; Li-Li CHENG ; Jun-Jie CHEN ; Shuang-Shuang SHANG ; Si-Di LIU ; Ming LI
Chinese Traditional Patent Medicine 2024;46(6):1857-1861
AIM To investigate the clinical effects of Yiqi Shengjin Prescription on patients with primary Sj?gren's syndrome due to Dual Deficiency of Qi and Yin.METHODS Ninety-two patients were randomly assigned into control group(46 cases)for 8-week intervention of conventional treatment,and observation group(46 cases)for 8-week intervention of both Yiqi Shengjin Prescription and conventional treatment.The changes in clinical effects,TCM syndrome scores,ESSDAI score,ESSPRI score,salivary flow rate,immunoinflammatory indices(ESR,hs-CRP,IgG,C3,C4),SAS score,SDS score,T lymphocytes(CD4+,CD8+,Treg,Th17)and safety indices were detected.RESULTS The observation group demonstrated higher total effective rate than the control group(P<0.05).After the treatment,the observation group exhibited decreased TCM syndrome scores(P<0.05),which was lower than those in the control group(P<0.05);the two groups displayed decreased ESSDAI score,ESSPRI score,ESR,hs-CRP,IgG,SAS score,SDS score,CD8+,Th17(P<0.05),and increased salivary flow rate,C3,C4,Treg(P<0.05),especially for the observation group(except for CD4+)(P<0.05).No obvious adverse reactions were observable in the two groups.CONCLUSION For the patients with primary Sjogren's syndrome due to Deficiency of Qi and Yin,Yiqi Shengjin Prescription can safely and effectively improve dry mouth and eye symptoms,and reduce inflammatory indices,whose mechanism may contribute to the regulation of T lymphocyte balance in vivo.
10.Research hotspots and trend analysis of puberty development among children and adolescents from 2013 to 2022
Chinese Journal of School Health 2023;44(6):900-905
Objective:
To analyze the hotspots, frontiers, and future research trends related to puberty development among children and adolescents from 2013 to 2022, and to provide a reference for subsequent research related to puberty development.
Methods:
Data related to puberty development from 2013 to 2022 were retrieved from the Web of Science core collection with the search formula "puberty timing (title) OR puberty development (title) OR pubertal timing (title) OR pubertal development (title) OR puberty timing (abstract) OR puberty development (abstract) OR pubertal timing (abstract) OR pubertal development (abstract)". The CiteSpace was used for visual analysis.
Results:
A total of 6 684 publications were obtained and an upward trend could be seen in the number of publications in the field of puberty development in the last 10 years. Researchers with a high number of publications were Juul Anders, Brix Nis, and Ernst Andreas, in addition, the United States had the highest number of publications ( 2 125 ) and the highest betweenness centrality (0.23) in this field. In the last decade, research hotspots had focused on the timing of pubertal initiation, biological mechanisms of pubertal development, and sex differences in pubertal development. Research on environmental endocrine disruptors and the mechanisms of pubertal development were at the forefront of research and future research trends.
Conclusion
Scholars can refer to the research hotspots and research trends in this field and focus on the issues related to environmental endocrine disruptors and pubertal development mechanisms.


Result Analysis
Print
Save
E-mail