1.Clinical Value of A Arterial and Portal CT-Based Deep Learning Model for the Differential Diagnosis of Benign and Malignant Pancreatic Cystic Lesions
Boyu CHEN ; Wenyi DENG ; Fuze CONG ; Huadan XUE
Medical Journal of Peking Union Medical College Hospital 2026;17(4):963-975
To develop a deep learning model based on arteriovenous dual-phase CT imaging features and evaluate its diagnostic value in differentiating benign from malignant pancreatic cystic lesions(PCLs). Preoperative contrast-enhanced CT images of patients with histopathologically confirmed PCLs at Peking Union Medical College Hospital from June 1, 2014 to May 31, 2023 were retrospectively collected. The data were randomly partitioned at the lesion level into training, validation, and test sets in a 3∶1∶1 ratio. CT images were preprocessed and regions of interest were delineated. Using postoperative pathological results as the reference standard, five deep learning models(ResNet50, DenseNet121, ResNeXt50, EfficientNet-b5, and MobileNetV2) were constructed to extract arteriovenous dual-phase CT imaging features for binary classification of PCLs. The optimal model was selected based on the area under the curve(AUC), accuracy, sensitivity, and specificity. Further comparative analyses were conducted against single-phase CT-based deep learning models, conventional radiomics models, and radiologist interpretations to comprehensively evaluate the performance of the arteriovenous dual-phase CT-based deep learning model in the differential diagnosis of PCLs. A total of 480 patients with 485 lesions(206 malignant and 279 benign) were ultimately enrolled. The training, validation, and test sets comprised 291, 97, and 97 lesions, corresponding to 288, 96, and 96 patients, respectively. In the validation set, the ResNeXt50 model based on arteriovenous dual-phase CT features achieved an AUC of 0.837(95% CI: 0.748-0.915), an accuracy of 77.32%(95% CI: 67.70%-85.21%), a sensitivity of 80.49%(95% CI: 65.13%-91.18%), and a specificity of 75.00%(95% CI: 61.63%-85.61%). In the test set, the corresponding values were 0.822(95% CI: 0.737-0.904), 73.20%(95% CI: 63.24%-81.68%), 82.93%(95% CI: 67.94%-92.85%), and 66.07%(95% CI: 52.19%-78.19%), demonstrating overall superior performance. Calibration curves indicated that the predicted probabilities of the model were generally consistent with observed outcomes, albeit with certain shortcomings in probability calibration. Decision curve analysis demonstrated that, overall, the use of this model for clinical decision-making conferred a net benefit to patients. Compared with single-phase CT-based models and conventional radiomics models, the ResNeXt50 model incorporating arteriovenous dual-phase CT features exhibited superior overall performance, and its diagnostic performance was comparable to that of radiologists, with good consistency. The deep learning model based on arteriovenous dual-phase CT imaging features demonstrates diagnostic value in differentiating benign from malignant PCLs and may serve as an adjunctive reference for preoperative clinical assessment. However, its stability and generalizability warrant further validation in larger cohorts and with external datasets.
2.Prediction of Mismatch Repair Deficiency Status in Endometrial Cancer Using Multiparametric MRI Radiomics and Deep Learning: A Multimodal Model with Preliminary Validation
Liru WANG ; Shangying YANG ; Boyu CHEN ; Fuze CONG ; Xinran LI ; Xinyu LIU ; Huadan XUE ; Zhengyu JIN ; Yang XIANG ; Yonglan HE ; Yuan LI
Medical Journal of Peking Union Medical College Hospital 2026;17(4):976-984
To explore the clinical value of a multimodal predictive model based on multiparametric magnetic resonance imaging(MRI) radiomics combined with deep learning(DL) features for the preoperative noninvasive assessment of mismatch repair-deficient(MMRd) status in endometrial cancer(EC). Patients diagnosed with EC at Peking Union Medical College Hospital from January 2015 to December 2021 were retrospectively enrolled and randomly divided into a training set and a validation set at a ratio of 8∶2. Relevant clinical data were collected, and radiomics features and DL features were extracted from preoperative contrast-enhanced T1-weighted imaging(CE-T1WI), fat-suppressed T2-weighted imaging(fs-T2WI), and diffusion-weighted imaging(DWI) sequences. High-dimensional feature selection and dimensionality reduction were performed sequentially using the recursive feature elimination(RFE) algorithm to generate a radiomics score(Rad-score) and a deep learning score(DL-score), respectively. Multivariate logistic regression was utilized to construct a clinical model, a pure radiomics model, a clinical-radiomics model, and an integrated multimodal model incorporating clinical indicators, Rad-score, and DL-score. Model performance was assessed and compared using area under receiver operating characteristic curve(AUC) and DeLong test. A total of 509 patients were enrolled in this study, comprising 413 in the training cohort and 96 in the validation cohort. Independent predictors: Multivariate analysis indicated that preoperative fasting blood glucose level, histological grade, lymph node metastasis status, Rad-score, and DL-score were all independent significant predictors of MMRd status in EC patients. The integrated multimodal model demonstrated optimal predictive performance with an AUC of 0.699(95% CI: 0.635-0.763) in the training set, which was superior to the clinical model(AUC=0.629, 95% CI: 0.561-0.697) and the pure radiomics model(AUC=0.641, 95% CI: 0.575-0.706). In the validation set, the integrated model maintained good generalizability, achieving an AUC of 0.655(95% CI: 0.535-0.775), and its diagnostic efficacy was higher than that of the clinical model(AUC=0.578, 95% CI: 0.450-0.705) and the pure radiomics model(AUC=0.611, 95% CI: 0.488-0.734). According to the DeLong test, the incorporation of DL features resulted in the clinicalradiomicsdeep learning model performing better than both the clinicalonly model( The initially developed clinical-radiomics-deep learning model exhibits a certain predictive potential for the MMRd status in patients with EC. The inclusion of DL features may help complement the limitations of traditional evaluations, offering a preliminary radiological reference for preoperative non-invasive screening. However, given the current diagnostic performance, its overall accuracy and clinical generalizability warrant further validation in multi-center, large-sample external cohort studies.
3.Analysis of the efficacy of mepolizumab for maintenance therapy following endoscopic sinus surgery in patients with eosinophilic chronic rhinosinusitis with nasal polyps
Rui DING ; Li CHEN ; Boyu CAI ; Yan LIANG
China Pharmacy 2026;37(16):2150-2155
OBJECTIVE To investigate the clinical efficacy of mepolizumab as postoperative maintenance therapy after endoscopic sinus surgery (ESS) in patients with eosinophilic chronic rhinosinusitis with nasal polyps (EosCRSwNP).METHODS A retrospective cohort study was conducted to collect clinical data from patients with EosCRSwNP who underwent ESS at the Dept. of Otolaryngology in Xuzhou First People’s Hospital, from January 1 to May 31, 2025. Patients were divided into a control group (56 cases, treated with intranasal corticosteroids postoperatively) and an observation group (51 cases, treated with mepolizumab postoperatively) based on their postoperative maintenance therapy regimens. The nasal function parameters [nasal cavity volume (NCV), distance from the minimum cross-sectional area to the anterior nostril (DCAN), nasal minimum cross-sectional area (NMCA), saccharin clearance time, nasal mucociliary clearance rate, mucociliary clearance velocity], and the indicators related to nasal mucosal remodeling [peripheral blood eosinophil (EOS) percentage, serum levels of transforming growth factor-β 1 (TGF-β 1 ) and vascular endothelial growth factor (VEGF)] were compared between the two groups at 2 weeks and 3, 6 months after surgery. The assessment indicators of the inflammation status of nasal mucositis [modified Lund-Kennedy Endoscopic Scoring System (MLK) score], the degree of nasal polyp recurrence[nasal polyp score (NPS)], and the quality of life [Sino-nasal Outcome Test-20 (SNOT-20) score] were compared at 2 weeks and 6 months after surgery. Adverse events were also recorded and compared between the two groups.RESULTS At 2 weeks after surgery, there were no statistically significant differences in the aforementioned indicators/scores between the two groups ( P >0.05). Compared with the same group at 2 weeks postoperatively, both groups showed significant increases in NCV, NMCA, nasal mucociliary clearance rate, and mucociliary clearance velocity at 3 and 6 months postoperatively; significant decreases or reductions were observed in DCAN, saccharin clearance time, EOS percentage, TGF-β 1 and VEGF levels at 3 and 6 months postoperatively, while in MLK score, NPS, SNOT-20 score were all significantly reduced or shortened ( P <0.05). Furthermore, the improvements in these indicators in the observation group were significantly greater than those in the control group during the same time periods ( P <0.05). The overall incidence of adverse reactions was comparable between the two groups ( P >0.05), but the incidence of injection-site reactions was significantly higher in the observation group than in the control group ( P <0.05).CONCLUSIONS The use of mepolizumab for postoperative maintenance therapy following ESS in patients with EosCRSwNP promotes the recovery of nasal function, improves indicators of nasal mucosal remodeling, reduces inflammation, lowers polyp score, and enhances quality of life. Its efficacy is superior to that of intranasal corticosteroids; however, clinicians should be mindful of the risk of injection-site reactions of mepolizumab.
4.Correlation analysis of genetic and environmental factors with clinical characteristics of pediatric upper urinary tract calculi
Youquan ZHAO ; Xiaochuan WANG ; Boyu YANG ; Chen NING ; Houyu ZHOU ; Huimin ZHAO ; Xiaochen WANG ; Ruiyu YUE ; Shao ZHANG ; Manjiang SUN ; Jun LI
Chinese Journal of Urology 2025;46(10):728-733
Objective:To investigate the influence of genetic and environmental factors on the clinical characteristics of upper urinary tract calculi in pediatric patients.Methods:This study was a retrospective case series. The clinical data of 179 children under the age of 14 with upper urinary tract calculi treated at Beijing Friendship Hospital,Capital Medical University,from August 2014 to February 2023 were analyzed. There were 121 males(67.60%)and 58 females(32.40%),with a median age at onset of 2.10(1.14,5.17)years. Thirty-three cases(18.44%)had a family history of urinary stone disease. Stone characteristics was defined by CT,with a median stone burden(sum of the diameters of all stones)of 1.3(1.00,1.60)cm. Fifty-four(30.17%)children had staghorn calculi. Multiple stones were present in 92 cases(51.40%),and bilateral stones in 52 cases(29.05%),with hydronephrosis was present in 119 children(66.48%). The median follow-up time was 67 months,and 36 children(20.11%)experienced stone recurrence. Dietary habits and related information were collected by electronic questionnaire,including a total of 115 children(64.25%)with an unbalanced diet,101(56.42%)with insufficient water intake,and 32 children(17.88%)with a preference for a high-protein diet. Tap water was used as the source of drinking water by 128 patients(71.51%),and 107(59.78%)took dietary supplements. Whole-exome sequencing revealed that 55 children(30.73%)carried pathogenic mutations in stone-related genes. Binary logistic regression was used for univariate analysis of above risk factors. Variables with P < 0.1 in univariate analysis and without multicollinearity were included in multivariate logistic regression to further screen for independent risk factors. Results:Multivariate analysis confirmed that carrying stone-related pathogenic gene mutations( OR = 3.06,95% CI 1.25?7.45, P = 0.014)and insufficient water intake( OR = 3.28,95% CI 1.14?9.47, P = 0.028)were independent risk factors for higher stone burden. A high-protein diet( OR = 2.40,95% CI 1.03?5.63, P = 0.044),carrying stone-related pathogenic gene mutations( OR = 4.57,95% CI 2.21?9.46, P<0.01),and a family history of stones( OR = 3.18,95% CI 1.28 ~ 7.91, P = 0.013)were independent risk factors for staghorn calculi. Multiple stones were closely associated with a family history of stones( OR = 2.66,95% CI 1.15-6.17, P = 0.022)and carrying stone-related pathogenic gene mutations( OR = 3.22,95% CI 1.60-6.48, P = 0.001). Moreover,carrying stone-related pathogenic gene mutations( OR = 5.19,95% CI 2.52?13.82, P < 0.01)were an independent risk factor for stone recurrence,whereas dietary supplement intake was a protective factor( OR = 0.26,95% CI 0.11?0.62, P = 0.002). Conclusions:Genetic and environmental factors play significant roles in the occurrence and development of pediatric upper urinary tract stones. A high-protein diet as well as a positive family history of stones are independent risk factors for staghorn calculi,and insufficient water intake is a critical environmental factor for stone formation,while appropriate use of dietary supplements may help reduce the risk of stone recurrence. Genetic testing indicates that approximately 30% of children carry stone-related pathogenic gene mutations,and these patients prone to severe stone and an increased risk of recurrence.
5.Natural product virtual-interact-phenotypic target characterization:A novel approach demonstrated with Salvia miltiorrhiza extract
Rui XU ; Hengyuan YU ; Yichen WANG ; Boyu LI ; Yong CHEN ; Xuesong LIU ; Tengfei XU
Journal of Pharmaceutical Analysis 2025;15(2):425-441
Natural products(NPs)have historically been a fundamental source for drug discovery.Yet the complex nature of NPs presents substantial challenges in pinpointing bioactive constituents,and corresponding targets.In the present study,an innovative natural product virtual screening-interaction-phenotype(NP-VIP)strategy that integrates virtual screening,chemical proteomics,and metabolomics to identify and validate the bioactive targets of NPs.This approach reduces false positive results and enhances the ef-ficiency of target identification.Salvia miltiorrhiza(SM),a herb with recognized therapeutic potential against ischemic stroke(IS),was used to illustrate the workflow.Utilizing virtual screening,chemical proteomics,and metabolomics,potential therapeutic targets for SM in the IS treatment were identified,totaling 29,100,and 78,respectively.Further analysis via the NP-VIP strategy highlighted five high-confidence targets,including poly[ADP-ribose]polymerase 1(PARP1),signal transducer and activator of transcription 3(STAT3),amyloid precursor protein(APP),glutamate-ammonia ligase(GLUL),and glutamate decarboxylase 67(GAD67).These targets were subsequently validated and found to play critical roles in the neuroprotective effects of SM.The study not only underscores the importance of SM in treating IS but also sets a precedent for NP research,proposing a comprehensive approach that could be adapted for broader pharmacological explorations.
6.Natural product virtual-interact-phenotypic target characterization: A novel approach demonstrated with Salvia miltiorrhiza extract.
Rui XU ; Hengyuan YU ; Yichen WANG ; Boyu LI ; Yong CHEN ; Xuesong LIU ; Tengfei XU
Journal of Pharmaceutical Analysis 2025;15(2):101101-101101
Natural products (NPs) have historically been a fundamental source for drug discovery. Yet the complex nature of NPs presents substantial challenges in pinpointing bioactive constituents, and corresponding targets. In the present study, an innovative natural product virtual screening-interaction-phenotype (NP-VIP) strategy that integrates virtual screening, chemical proteomics, and metabolomics to identify and validate the bioactive targets of NPs. This approach reduces false positive results and enhances the efficiency of target identification. Salvia miltiorrhiza (SM), a herb with recognized therapeutic potential against ischemic stroke (IS), was used to illustrate the workflow. Utilizing virtual screening, chemical proteomics, and metabolomics, potential therapeutic targets for SM in the IS treatment were identified, totaling 29, 100, and 78, respectively. Further analysis via the NP-VIP strategy highlighted five high-confidence targets, including poly [ADP-ribose] polymerase 1 (PARP1), signal transducer and activator of transcription 3 (STAT3), amyloid precursor protein (APP), glutamate-ammonia ligase (GLUL), and glutamate decarboxylase 67 (GAD67). These targets were subsequently validated and found to play critical roles in the neuroprotective effects of SM. The study not only underscores the importance of SM in treating IS but also sets a precedent for NP research, proposing a comprehensive approach that could be adapted for broader pharmacological explorations.
7.Correlation analysis of genetic and environmental factors with clinical characteristics of pediatric upper urinary tract calculi
Youquan ZHAO ; Xiaochuan WANG ; Boyu YANG ; Chen NING ; Houyu ZHOU ; Huimin ZHAO ; Xiaochen WANG ; Ruiyu YUE ; Shao ZHANG ; Manjiang SUN ; Jun LI
Chinese Journal of Urology 2025;46(10):728-733
Objective:To investigate the influence of genetic and environmental factors on the clinical characteristics of upper urinary tract calculi in pediatric patients.Methods:This study was a retrospective case series. The clinical data of 179 children under the age of 14 with upper urinary tract calculi treated at Beijing Friendship Hospital,Capital Medical University,from August 2014 to February 2023 were analyzed. There were 121 males(67.60%)and 58 females(32.40%),with a median age at onset of 2.10(1.14,5.17)years. Thirty-three cases(18.44%)had a family history of urinary stone disease. Stone characteristics was defined by CT,with a median stone burden(sum of the diameters of all stones)of 1.3(1.00,1.60)cm. Fifty-four(30.17%)children had staghorn calculi. Multiple stones were present in 92 cases(51.40%),and bilateral stones in 52 cases(29.05%),with hydronephrosis was present in 119 children(66.48%). The median follow-up time was 67 months,and 36 children(20.11%)experienced stone recurrence. Dietary habits and related information were collected by electronic questionnaire,including a total of 115 children(64.25%)with an unbalanced diet,101(56.42%)with insufficient water intake,and 32 children(17.88%)with a preference for a high-protein diet. Tap water was used as the source of drinking water by 128 patients(71.51%),and 107(59.78%)took dietary supplements. Whole-exome sequencing revealed that 55 children(30.73%)carried pathogenic mutations in stone-related genes. Binary logistic regression was used for univariate analysis of above risk factors. Variables with P < 0.1 in univariate analysis and without multicollinearity were included in multivariate logistic regression to further screen for independent risk factors. Results:Multivariate analysis confirmed that carrying stone-related pathogenic gene mutations( OR = 3.06,95% CI 1.25?7.45, P = 0.014)and insufficient water intake( OR = 3.28,95% CI 1.14?9.47, P = 0.028)were independent risk factors for higher stone burden. A high-protein diet( OR = 2.40,95% CI 1.03?5.63, P = 0.044),carrying stone-related pathogenic gene mutations( OR = 4.57,95% CI 2.21?9.46, P<0.01),and a family history of stones( OR = 3.18,95% CI 1.28 ~ 7.91, P = 0.013)were independent risk factors for staghorn calculi. Multiple stones were closely associated with a family history of stones( OR = 2.66,95% CI 1.15-6.17, P = 0.022)and carrying stone-related pathogenic gene mutations( OR = 3.22,95% CI 1.60-6.48, P = 0.001). Moreover,carrying stone-related pathogenic gene mutations( OR = 5.19,95% CI 2.52?13.82, P < 0.01)were an independent risk factor for stone recurrence,whereas dietary supplement intake was a protective factor( OR = 0.26,95% CI 0.11?0.62, P = 0.002). Conclusions:Genetic and environmental factors play significant roles in the occurrence and development of pediatric upper urinary tract stones. A high-protein diet as well as a positive family history of stones are independent risk factors for staghorn calculi,and insufficient water intake is a critical environmental factor for stone formation,while appropriate use of dietary supplements may help reduce the risk of stone recurrence. Genetic testing indicates that approximately 30% of children carry stone-related pathogenic gene mutations,and these patients prone to severe stone and an increased risk of recurrence.
8.Genetic analysis of a child with Primary hypertrophic osteoarthropathy
Chen WANG ; Xueping QIU ; Yating CHENG ; Boyu LI ; Yuanzhen ZHANG ; Jianhong MA ; Fang ZHENG
Chinese Journal of Medical Genetics 2024;41(9):1100-1104
Objective:To explore the genetic etiology of a child with primary hypertrophic osteoarthropathy(PHO).Methods:A child who was admitted to Zhongnan Hospital of Wuhan University on July 27, 2021 was selected as the study subject. Genomic DNA was extracted from peripheral blood samples of the child and his parents and subjected to whole exome sequencing. Suspected splicing variant was verified by Sanger sequencing of family members. In vitro function was validated through a minigene assay, whilst the suspected exonic deletion was validated by long-fragment PCR. This study was approved by the Children′s Hospital Affiliated to Zhengzhou University (Ethics No. 2023-K-011). Results:Whole exome sequencing revealed that the child has harbored compound heterozygous variants of HPGD gene, including a heterozygous deletion (Exon 3 del) derived from his father and a splicing variant (c.421+ 1G>T) derived from his mother. Long-fragment PCR verified that the child and his father had both harbored a 7 565 bp heterozygous deletion (c.218-1304_324+ 6156del), whilst the minigene assay proved that the splicing variant has resulted in skipping of exon 4. Conclusion:The heterozygous c. 218-1304_324+ 6156del deletion and the c. 421+ 1G>T splicing variant of the HPGD gene probably underlay the pathogenesis in this child. Above finding has enriched the mutational spectrum of the HPGD gene and provided a basis for genetic counseling and prenatal diagnosis for this family.
9.The relationship between intestinal microecological imbalance and heart failure based on the theory of"spleen as the guardian"
Changxing LIU ; Xinyi GUO ; Boyu WANG ; Na SHI ; Qiuhan CHEN ; Yabin ZHOU ; He WANG
Chinese Journal of Arteriosclerosis 2024;32(3):263-270
Heart failure is a fatal stage of end-stage cardiovascular disease,which brings a huge medical burden to the society because of its high mortality and re-hospitalisation rates.Intestinal microecology is the largest and most com-plex microecosystem of human body.It is inhabited by tens of thousands of microorganisms in human gastrointestinal tract.In recent years,with the deepening of the study of intestinal flora,more and more studies have found that the im-balance of intestinal microecology can cause changes of metabolites in heart failure patients,which is one of the key triggers for the development of heart failure,therefore,using the intestinal microbial homeostasis as a new entry point for the treat-ment of heart failure will be a hotspot in medical research.However,the theory of Chinese medicine,"the spleen is the guardian",covers the physiological functions of the spleen,such as the spleen's main function of transporting,spleen's main function of ascending and clearing,and its main function of hiding camping,etc.,and the functions of intestinal flora and the"spleen is the guardian"are similar to a certain extent.Therefore,this paper starts from a holistic viewpoint and takes the theory of"spleen as the guardian"in Chinese medicine as an entry point to elaborate on the pathogenesis of intes-tinal microecological imbalance and heart failure,so as to provide a reference for Chinese medicine treatment or drug re-search.
10.The application value of artificial intelligence in evaluating brain atrophy in patients with spinocerebellar ataxia type 3
Sidan CHEN ; Jiaojiao WU ; Boyu CAO ; Kuanghui XU ; Yugang LI ; Zhouyao HU ; Rui HUA ; Feng SHI ; Xiaochuan WANG ; Le QI
Journal of Practical Radiology 2024;40(7):1037-1042
Objective To evaluate the degree of brain atrophy in spinocerebellar ataxia type 3(SCA3)patients based on artificial intelligence(AI)technology,and to explore the correlation between the degree of brain atrophy and the severity of the disease.Methods The clinical and imaging data of 23 SCA3 patients(SCA3 group)and 24 healthy controls(HC)(HC group)were collected.The International Cooperative Ataxia Rating Scale(ICARS)was used to evaluate the severity of ataxia in patients with SCA3.AI technology was used to process the 3D-T1 WI MR image data of the SCA3 and HC groups to segment and measure the volume and volume percentage of brain,followed by correlation analyses between brain structural alterations and the severity of ataxia in SCA3 patients.Results There were no significant differences in gender and age between the two groups(P>0.05).The SCA3 group had a significant reduction in the volume and volume percentage of various brain regions,such as the frontal,temporal,parietal,occipital,limbic,right cerebral white mat-ter,subcortical gray matter,cerebellum and brainstem,compared to the HC group(multiple hypothesis testing adjusted P<0.01).In the SCA3 group,the ICARS showed positive correlation with patient age(r=0.571,P=0.004)and negative correlation with the vol-ume of the left cerebellar white matter,vermis,medulla oblongata,and the volume percentages of bilateral cerebellar white matter,vermis,pons,medulla oblongata(P<0.05).Conclusion The significant atrophy of the supratentorial and subtentorial regions of the brain in SCA3 patients.The globus pallidus exhibits the most substantial atrophy,suggesting its potential as an imaging diagnostic marker of SC A3.

Result Analysis
Print
Save
E-mail