1.Self-Supervised Multi-Organ Segmentation in Pediatric Abdominal CT Based on Vision Foundation Models
Qinghua ZHANG ; Ming LI ; Zhedian ZHOU ; Jian ZHENG ; Huadan XUE ; Qiuxia WANG ; Yu DU ; Zhen LI
Medical Journal of Peking Union Medical College Hospital 2026;17(4):954-962
To address the scarcity of annotated data for pediatric abdominal CT imaging and the insufficient generalization capability of existing models, we constructed a self-supervised pretraining architecture tailored for pediatric CT domain adaptation based on the visual foundation model DINOv3, and validated its performance in the task of pediatric abdominal multi-organ segmentation. We built a general-purpose radiological visual representation using the large-scale adult CT dataset CT-3M, and introduced a Gram-anchoring mechanism that employs a frozen adult pretrained model as a structural teacher to guide domain alignment of local topological structures on unlabeled pediatric CT data. Combined with a multi-scale feature aggregation strategy and a lightweight Primus decoder, downstream segmentation tasks were evaluated on a public pediatric CT dataset. Based on case-wise paired results, we compared the mean Dice similarity coefficient (DSC) and mean intersection over union (IoU) between our model and the baseline nnU-Net using the Wilcoxon signed-rank test, and computed the relative performance improvements. A total of 867 abdominal CT imaging cases were collected, constituting a pretraining dataset comprising 367 588 two-dimensional CT slices. On the public Pediatric-CT-SEG dataset (359 cases), our model achieved a mean DSC of (71.38±1.08)% and a mean IoU of (63.73±1.01)%, representing improvements of 3.22% and 3.59% over the baseline nnU-Net, respectively, with statistically significant differences ( The self-supervised pretraining framework proposed in this study effectively alleviates the domain shift between adult and pediatric abdominal CT images, significantly enhances segmentation accuracy for pediatric abdominal multi-organs-particularly small organs and structures with complex boundaries-and provides a reliable technical solution for intelligent pediatric imaging analysis in scenarios with limited annotated data.
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.Comparison of three methods for induction of model mice with diminished ovarian reserve
Huadan LIN ; Xu WANG ; Chunhong CHEN ; Yuzhuo WEI ; Yanchun LUO ; Fanghui PANG ; Qiuyun QIN ; Ziyun RUAN
Chinese Journal of Comparative Medicine 2025;35(5):51-59
Objective To compare the effects of Tripterygium wilfordii polyglycosides,cyclophosphamide,and cisplatin on the establishment of a mouse model of diminished ovarian reserve(DOR).Methods Mice were randomly divided into the following treatment groups:control(Ctrl),Tripterygium wilfordii polyglycosides(TWP),cyclophosphamide(CTX),and cisplatin(DDP).Mice in the TWP group received a 50 mg/kg suspension of Tripterygium wilfordii polyglycosides by gavage for 14 days,mice in the CTX group received a 20 mg/kg cyclophosphamide suspension by intraperitoneal injection for 14 days,and mice in the DDP group received a 1.5 mg/kg cisplatin solution by intraperitoneal injection for 14 days.The body weight,uterine index,and ovarian index were recorded,the estrous cycle was monitored using the vaginal smear method,and the levels of anti-Mullerian hormone(AMH),estradiol(E2),follicle stimulating hormone(FSH),and luteinizing hormone(LH)were detected using ELISA.Hematoxylin and eosin staining was used to detect ovarian follicle development.The rates of oocyte maturation and fertility were analyzed.Results The three treatment groups of mice all showed the following:significantly decreased body weight and ovarian index(P<0.05);apparent disorder of the estrous cycle;significantly decreased levels of AMH and E2(P<0.05);decreased and increased rates of developing follicles and atretic follicles,respectively(P<0.05);and significantly decreased rates of oocyte maturation,pregnancy,and live birth(P<0.05).Conclusions DOR mouse models were successfully constructed using Tripterygium wilfordii polyglycosides,cyclophosphamide,or cisplatin,as evidenced by decreased body weight and ovarian index,disordered estrous cycle and hormones,and DOR function,resulting in reduced rates of oocyte maturation,pregnancy,and total number of live births.These DOR effects were most appropriate in the cyclophosphamide group.
4.Analysis of Self-assessed Health Changes and Influencing Factors among the Elderly People Based on CHARLS Database
Zhongjie WANG ; Yu XIA ; Hongrui ZHAO ; Xuelin XIANG ; Huadan WANG ; Min MA ; Liping HE
Journal of Kunming Medical University 2025;46(3):27-33
Objective To understand the changes in self-rated health among middle-aged and elderly individuals in China and the influencing factors,providing a reference for improving health and promoting healthy aging.Methods Using data from the China Health and Aged Care Tracking Survey(CHARLS)from 2011 to 2020,this study analyzed 3595 middle-aged and elderly individuals(≥45 years old)who participated in all five rounds of the survey from 2011 to 2020.Univariate analysis and multinomial logistic regression were employed to analyze the influencing factors of self-rated health changes.Results Among the 3 595 middle-aged and elderly individuals,26.54%reported an increase in self-rated health,28.40%reported a decrease,and 45.06%reported no change.The multinomial logistic regression results indicated that compared to those with unchanged self-rated health,individuals whose self-rated health declined were more likely to have an increased number of Activities of Daily Living(ADLs),a higher number of chronic diseases,not engaging in at least 10 minutes of light physical activity per week,and a decline in life satisfaction levels.The odds ratios for these factors were 1.415(OR=1.415,95%CI:1.181~1.694),1.479(OR=1.479,95%CI:1.225~1.785),1.454(OR=1.486,95%CI:1.172~1.804),and 1.263(OR=1.237,95%CI:1.043~1.530),respectively.In contrast,individuals whose self-rated health improved,compared to those with unchanged health,were more likely to report an increase in life satisfaction levels,while an increase in ADLs and chronic diseases negatively impacted self-rated health improvement.The odds ratios for these factors were 1.698(OR=1.698,95%CI:1.425~2.023),0.769(OR=0.769,95%CI:0.646~0.915),and 0.689(OR=0.689,95%CI:0.549~0.865),respectively.Conclusion From 2011 to 2020,the self-rated health of middle-aged and elderly individuals in China has slightly declined,with a focus on improving physical health status,increasing physical activity,and addressing mental health as key areas for enhancing self-rated health among the elderly in China.
5.Comparison of three methods for induction of model mice with diminished ovarian reserve
Huadan LIN ; Xu WANG ; Chunhong CHEN ; Yuzhuo WEI ; Yanchun LUO ; Fanghui PANG ; Qiuyun QIN ; Ziyun RUAN
Chinese Journal of Comparative Medicine 2025;35(5):51-59
Objective To compare the effects of Tripterygium wilfordii polyglycosides,cyclophosphamide,and cisplatin on the establishment of a mouse model of diminished ovarian reserve(DOR).Methods Mice were randomly divided into the following treatment groups:control(Ctrl),Tripterygium wilfordii polyglycosides(TWP),cyclophosphamide(CTX),and cisplatin(DDP).Mice in the TWP group received a 50 mg/kg suspension of Tripterygium wilfordii polyglycosides by gavage for 14 days,mice in the CTX group received a 20 mg/kg cyclophosphamide suspension by intraperitoneal injection for 14 days,and mice in the DDP group received a 1.5 mg/kg cisplatin solution by intraperitoneal injection for 14 days.The body weight,uterine index,and ovarian index were recorded,the estrous cycle was monitored using the vaginal smear method,and the levels of anti-Mullerian hormone(AMH),estradiol(E2),follicle stimulating hormone(FSH),and luteinizing hormone(LH)were detected using ELISA.Hematoxylin and eosin staining was used to detect ovarian follicle development.The rates of oocyte maturation and fertility were analyzed.Results The three treatment groups of mice all showed the following:significantly decreased body weight and ovarian index(P<0.05);apparent disorder of the estrous cycle;significantly decreased levels of AMH and E2(P<0.05);decreased and increased rates of developing follicles and atretic follicles,respectively(P<0.05);and significantly decreased rates of oocyte maturation,pregnancy,and live birth(P<0.05).Conclusions DOR mouse models were successfully constructed using Tripterygium wilfordii polyglycosides,cyclophosphamide,or cisplatin,as evidenced by decreased body weight and ovarian index,disordered estrous cycle and hormones,and DOR function,resulting in reduced rates of oocyte maturation,pregnancy,and total number of live births.These DOR effects were most appropriate in the cyclophosphamide group.
6.Analysis of Influencing Factors of Perceived Discrimination in HIV-infected Patients Treated with Antiviral Therapy
Hongrui ZHAO ; Xuelin XIANG ; Zhongjie WANG ; Yu XIA ; Huadan WANG ; Min MA ; Liping HE
Journal of Kunming Medical University 2024;45(12):88-93
Objective To investigate the status of perceived discrimination among HIV-infected people receiving antiviral treatment and analyze its influencing factors,so as to provide reference for reducing discrimination and improving the life quality of HIV-infected people.Methods The multi-stage stratified cluster sampling method was used to select HIV-infected individuals from designated hospitals in three cities and counties in Yunnan Province,as well as from designated township health centers,for face-to-face survey interviews.The questionnaire included socio-demographic characteristics,AIDS infection disease characteristics,Berger AIDS perceived discrimination Scale and Xiao Shui Yuan Social Support Rating Scale.The influencing factors of perceived discrimination were analyzed by multiple linear regression.Results There were 633 valid questionnaires.The perceived discrimination score of HIV-infected people was(111.11±19.43),which was at a medium high level,and the dimension with the highest average score was fear of publicity.Multiple regression showed that middle-aged people,those who do not participate in group activities and those who have less social support had higher perceived discrimination(P<0.05).Conclusion The perception discrimination of AIDS patients in Yunnan Province is high.In the prevention and control of AIDS,it is necessary to actively organize and participate in group activities,improve social support and pay attention to middle-aged AIDS patients.
7.Prevalence and associated factors of congenital heart disease among nursery, primary and middle school students in Zhaotong
FANG Jiayu, DUO Lin, FU Hongchen, YANG Qinghuan, MA Min, WANG Huadan, PANG Linhong, HE Liping
Chinese Journal of School Health 2022;43(11):1733-1736
Objective:
To investigate the prevalence and associated factors of congenital heart defects (CHD) among nursery, primary, and middle school students in Zhaotong, and to provide basis for CHD prevention strategies for children and adolescents.
Methods:
Using stratified random cluster sampling, a total of 11 343 nursery, primary and middle school students in 4 towns of Zhaotong were investigated with CHD screening and questionnaire during September to November in 2020.
Results:
The prevalence of CHD among nursery, primary and middle school students in Zhaotong was 11.99‰(95% CI =9.99‰-13.99‰), Yongshan County (14.90‰) > Yanjin County (10.22‰), rural (13.30‰) > urban (8.21‰)( χ 2=4.95, 4.77, P <0.05). Among 136 cases of CHD, the Ventricular Septal Defect (VSD) accounted the highest proportion (41.2%), followed by Atrial Septal Defect (ASD, 32.4% ), Patent Ductus Arteriosus (PDA, 14.0%), and Complex Congenital Heart Disease (CCHD, 5.9%) and the other CHD (others, 6.6%). The proportion of late diagnosed CHD was 50.74%, which was associated with living in rural areas of Yongshan County, low annual household income (10 000-<20 000 yuan), as well as isolated and uncomplicated CHD( OR =0.30, 0.13, 3.67 , 0.17, P <0.05).
Conclusion
Nursery, primary and middle schools students have the characteristics of high prevalence rate of CHD, large proportion of complex congenital heart disease, large number of late diagnosis and complex influencing factors in Zhaotong. It s in urgent need of strengthening learning prevention of CHD.
8.The application value of deep learning reconstruction algorithm in improving quality of low dose pancreatic CT images
Qiaoling WU ; Yun WANG ; Xiheng WANG ; Zhuangfei MA ; Huadan XUE ; Zhengyu JIN
Chinese Journal of Radiology 2022;56(4):437-442
Objective:To explore application value of improving quality of the low dose pancreatic CT images by using deep learning reconstruction (DLR).Methods:From August to December 2020, 68 patients who underwent contrast-enhanced pancreatic CT were prospectively collected in Peking Union Medical College Hospital. All patients were randomly divided into routine dose group (34 patients, with tube voltage of 120 kV) and low dose group (34 patients, with tube voltage of 100 kV). All patients underwent non-contrast, arterial phase, parenchymal phase and delay phase scans. The four-phase images of low dose group were reconstructed by using filtered back projection (FBP), hybrid iterative reconstruction (AIDR) and DLR which were marked with LD-FBP, LD-AIDR and LD-DLR, respectively. The four-phase images of routine dose group were reconstructed by using AIDR algorithm which were marked with RD-AIDR. The CT value, image noise (SD), signal to noise ratio (SNR) and contrast to noise ratio (CNR) of pancreas were measured. The ANOVA test was performed in comparison with objective parameters of different reconstruction algorithms, and LSD test was performed in pairwise comparison. The subjective image scores were obtained and were compared using Kruskal-Wallis test.Results:CT value, SD, SNR and CNR of non-contrast, arterial phase, parenchymal phase and delay phase had significant difference among different reconstruction images of routine dose group and low dose group (all P<0.05). The CT value of LD-FBP, LD-AIDR, and LD-DLR images were significantly higher than those of RD-AIDR images in parenchymal phase and delay phase (all P<0.05). There were statistically significant differences in each pairwise comparison of SD and SNR of four phase images (all P<0.05). There were statistically significant differences of CNR among LD-FBP, LD-DLR and RD-AIDR in four phase images (all P<0.05). The CNR of RD-AIDR was better than that of LD-FBP, and CNR of LD-DLR was better than that of RD-AIDR. DLR algorithm improved the SD, SNR and CNR of four phases of pancreatic images. The improvement of SNR was more significant after contrast enhancement, and the improvement of CNR was more significant in the non-contrast and delay phases. Subjective image scores of different reconstruction images were statistically different in four phase images (all P<0.001). Overall image scores of LD-DLR and RD-AIDR had no significant differences in four phase ( Z value of four phases were 1.00, 2.24, 0.45 and 1.34, respectively; P value of four phases were 0.317, 0.025, 0.655 and 0.180, respectively). Conclusion:The DLR technology can decrease radiation dose of pancreatic CT, improve image quality and satisfy diagnostic requirement. The DLR technology can also reduce image noise, improve the SNR and CNR in low dose contrast-enhanced pancreatic CT.
9.Amide proton transfer-weighted MRI of cervical squamous carcinoma: correlation with Ki-67 proliferation status
Yonglan HE ; Chengyu LIN ; Yafei QI ; Xiaoqi WANG ; Hailong ZHOU ; Yuan LI ; Bo CHEN ; Yang XIANG ; Huadan XUE ; Zhengyu JIN
Chinese Journal of Radiology 2021;55(5):517-521
Objective:To investigate the correlation between amide proton transfer-weighted (APTw) values and Ki-67 labeling index of cervical squamous cell carcinoma.Methods:From October 2017 to December 2018, 24 patients with cervical squamous cell carcinoma [International Federation of Gynecology and Obstetrics (FIGO) stage Ⅰ-Ⅲ] were prospectively enrolled in Peking Union Medical College Hospital and underwent pelvic morphological MRI on a 3.0 T MR scanner, including three-dimensional turbo-spin-echo APTw imaging and DWI. The maximum diameters of the lesions, APTw values and ADC values on the slice with the maximum diameter of the lesion were independently measured by two radiologists. The ICC was computed to evaluate the inter-observer consistency. Ki-67 immunohistochemical expression status was assessed by one pathologist. The Pearson correlation analysis was performed between the APTw values, maximum diameters, ADC values and Ki-67 labeling index.Results:The APTw values of cervical squamous cell carcinoma were (2.9±0.5)%. Inter-observer ICC was 0.972 (95%CI 0.937-0.988). The APTw values were positively moderately correlated with Ki-67 labeling index [(61.9±18.7)%, r=0.532, P=0.008]. The maximum diameters of the lesions were (28.7±10.6) mm. The mean ADC values were (0.998±0.217)×10 -3 mm 2/s. No correlations were found between maximum diameters, ADC values and Ki-67 labeling index ( r=0.038, P=0.859; r=0.238, P=0.263). Conclusion:APTw values can partially reveal the proliferation status of cervical squamous cell carcinoma.
10.The Chinese guidelines for the diagnosis and treatment of pancreatic neuroendocrine neoplasms (2020)
Wenming WU ; Jie CHEN ; Chunmei BAI ; Yihebali CHI ; Yiqi DU ; Shiting FENG ; Li HUO ; Yuxin JIANG ; Jingnan LI ; Wenhui LOU ; Jie LUO ; Chenghao SHAO ; Lin SHEN ; Feng WANG ; Liwei WANG ; Ou WANG ; Yu WANG ; Huanwen WU ; Xiaoping XING ; Jianming XU ; Huadan XUE ; Ling XUE ; Yang YANG ; Xianjun YU ; Chunhui YUAN ; Hong ZHAO ; Xiongzeng ZHU ; Yupei ZHAO
Chinese Journal of Digestive Surgery 2021;20(6):579-599
Pancreatic neuroendocrine neoplasms (pNENs) are highly heterogeneous, and the management of pNENs patients can be intractable. To address this challenge, an expert committee was established on behalf of the Chinese Pancreatic Surgery Association, Chinese Society of Surgery, Chinese Medical Association, which consisted of surgical oncologists, gastroenterologists, medical oncologists, endocrinologists, radiologists, pathologists, and nuclear medicine specialists. By reviewing the important issues regarding the diagnosis and treatment of pNENs, the committee concluded evidence-based statements and recommendations in this article, in order to further improve the management of pNENs patients in China.


Result Analysis
Print
Save
E-mail