Objective:To compare the efficacy of ustekinumab (UST) and vedolizumab (VDZ) in achieving transmural healing in active Crohn′s disease (CD).Methods:From March 1, 2020 to November 30, 2024, 112 patients with active CD treated with UST or VDZ at the Department of Gastroenterology, Tenth People′s Hospital of Tongji University were retrospectively enrolled. According to the medication regimen, the 112 patients were divided into UST group (61 cases) and VDZ group (51 cases). Collected the data at baseline, such as the disease phenotype, other medication history, and clinical indicators including C-creative protein (CRP), etc. Clinical disease activity and endoscopic disease activity were assessed by Harvey-Bradshaw index (HBI) and simplified endoscopic score for Crohn′s disease (SES-CD), respectively. Transmural healing was evaluated according to the intestinal wall thickness measured by intestinal imaging examination of the affected intestinal segment. Transmural healing was defined as bowel wall thickness <0.3 cm and 110 obvious signs of inflammation, clinical remission was defined as HBI≤4, and endoscopic remission was defined as a reduction in SES-CD ≥50% or a score of ≤2. The primary endpoint was transmural healing rate within one year after treatment. The secondary endpoints were endoscopic healing rate and clinical remission rate at 13 to 24th week and 30 to 52nd week after treatment. Chi-square test or Fisher′s exact test was used to compare the efficacy of the 2 medications.Results:There was no significant difference in transmural healing rate between UST group and VDZ group within 1 year after treatment (16.4% (10/61) vs. 23.5% (12/51), χ2=0.90, P=0.344). There were no significant differences in the healing rate between UST group and VDZ group in patients with specific baseline characteristics before treatment, including CD with stenosis, with perianal disease, no history of glucocorticoid use, secondary loss of response to anti-tumor necrosis factor (TNF)-α, SES-CD 7 to 15, decreased body mass index, and increased CRP (18.2%(6/33) vs. 19.4%(7/36), 17.9%(7/39) vs. 19.4%(6/31), 17.1%(6/35) vs. 24.2%(8/33), 20.0%(8/40) vs. 3/18, 14.3%(5/35) vs. 19.2%(5/26), 15.0%(3/20) vs. 3/10, 21.4%(6/28) vs. 5/16), all P>0.05). There was no significant difference in the clinical remission rate or endoscopic remission rate between the UST group and the VDZ group from 13 to 24th week (7/14 vs. 9/18, 3/14 vs. 7/18, RR=1.000 and 0.551, 95% confidence interval: 0.497to 2.011, 0.173to 1.755, χ2=<0.01, Fisher′s exact test, both P>0.05). There was no significant difference in clinical remission rate or endoscopic remission rate between UST group and VDZ group from week 30 to week 52 after treatment (68.5% (37/54) vs. 74.4% (32/43), 27.8% (15/54) vs. 32.6% (14/43), RR=0.921 and 0.853, 95% confidence interval: 0.716 to 1.184, 0.464 to 1.568, χ2=0.41 and 0.26, both P>0.05). In UST group, the proportion of patients with normal hemoglobin after transmural healing was higher than that of patients without transmural healing (9/10 vs. 45.1% (23/51), and the difference was statistically significant ( χ2=5.08, P=0.024). However, there were no significant differences in the proportion of patients with normal body mass index, CRP, platelet count, prealbumin, albumin, interleukin-6 or TNF-α levels after treatment between those who achieved transmural healing and those who did not in either UST group or VDZ group (all P>0.05). And in VDZ group there was no significant difference in the proportion of patients with normal hemoglobin between those who achieved transmural healing and who did not (all P>0.05). Conclusion:UST and VDZ exhibit similar efficacy in transmural healing within one year of treatment in patients with active CD.

Objective:To construct a thyroid nodule segmentation model using ultrasound dynamic images and explore its potential for assisting in the screening of thyroid nodules.Methods:A total of 126 patients with thyroid nodules（comprising 150 nodules）who were diagnosed and treated at Xuzhou Cancer Hospital from April 2024 to December 2024 were prospectively enrolled. Two-dimensional ultrasound was performed to capture short-axis and long-axis video images of thyroid nodules，forming a dynamic ultrasound image dataset. The dataset was divided into training，validation，and test sets in a ratio of 6∶1∶3. After the training loss curve converged，the model that performed well on the validation set was selected for testing. Three-fold cross-validation was employed for training and testing. All 300 ultrasound videos were divided into three subsets. In each experiment，two subsets were used as the training set，and one subset was used as the test set to evaluate the model's generalization ability. A collaborative spatiotemporal diffusion model was established based on the dynamic trends and tissue texture details of thyroid nodules. Six widely used segmentation metrics were employed to evaluate the model's application capabilities.Results:The study included 126 patients with 150 thyroid nodules，300 dynamic ultrasound images，and video lengths of 3-4 seconds per nodule，resulting in 12 312 segmented images. The size of the thyroid nodules was（10.7 ± 10.6）mm（transverse diameter）×（8.4 ± 6.3）mm（anteroposterior diameter）. Among the nodules，62（41.3%）had clear boundaries，while 88（58.7%）had indistinct boundaries；61（40.7%）exhibited regular shapes，while 89（59.3%）were irregular；66（44.0%）had a taller-than-wide aspect ratio；and 70（46.7%）showed microcalcifications. The collaborative diffusion model based on dynamic ultrasound image segmentation achieved the following scores：a Jaccard score of（69.22 ± 0.03）%，a Dice score of（79.16 ± 0.18）%，a Precision score of（86.70 ± 0.17）%，a Recall score of（77.82 ± 0.04）%，an Sα score of（85.26 ± 0.01）%，and an Eθmn score of（90.58 ± 0.17）%. Compared to other models，this model demonstrated significant improvements across all evaluation metrics，achieving the highest values in each metric with increments of over 8% and 1%，respectively. Conclusions:The collaborative diffusion model with a dynamic controller，constructed based on dynamic ultrasound images of thyroid nodules，demonstrates excellent performance in ultrasound image segmentation. It improves the accuracy of thyroid nodule screening，thereby providing a valuable auxiliary diagnostic tool for clinical practice.

Objective:To propose a deep learning（DL）-based ultrasound imaging auxiliary tool for automatic segmentation and recognition of the brachial plexus（BP），and to enhance the accuracy and safety of clinical procedures.Methods:It was a multicenter study that collected 773 healthy subjects from Peking University Third Hospital and its branch campuses，the Third Medical Center of the Chinese PLA General Hospital，and Shanghai Eighth People's Hospital between August 2024 and February 2025. Brachial plexus（BP）images in the interscalene groove were captured used high-frequency ultrasound by senior sonographers，a dataset comprising 1 289 standardized images were constructed and the improved model（CHA-TransUNet）was trained. The test set was input into 6 different models（CHA-TransUNet，R50-Unet，TransUnet，SegFormer，SwinUnet，MISSFormer）for segmentation. Segmentation accuracy was evaluated using metrics including the Dice similarity coefficient（DSC），95% Hausdorff distance（HD95）and mean intersection over union（mIoU），and was compared with the segmentation results of 3 ultrasound physicians with varying experience levels（junior physicians and senior physicians）to validate the model's segmentation efficacy.Results:The CHA-TransUNet model established based on a dataset of 1 289 standardized images achieved segmentation results for the BP with a DSC of 90.15%，mIoU of 91.02%，and HD95 of 8.08. Its accuracy was higher than other mainstream models（DSC：90.15% vs. 87.60%，87.77%，81.35%，84.78%，84.55%），significantly better than junior physicians（DSC：90.15% vs. 68.73%， Z=-127.76， P<0.001），and approached the level of senior physician（DSC：90.15% vs. 86.15%， Z=-31.33， P=0.549）. The model demonstrated superior boundary recognition in complex anatomical structures（e.g.，C6/C7 nerve roots）compared to ultrasound physicians（junior and senior）（HD95：8.08 vs. 26.34，17.44，56.80）. Conclusions:This study proposes an analysis model for BP ultrasound images，CHA-TransUNet. This model achieves segmentation and recognition of the BP with relatively complex pathways and structures. The model exhibits high accuracy and stability，outperforming current mainstream network models and junior physicians while approaching the performance level of senior physicians. It assists junior physicians or trainees in more accurately identifying and localizing the BP.

Objective:To compare the efficacy of ustekinumab (UST) and vedolizumab (VDZ) in achieving transmural healing in active Crohn′s disease (CD).Methods:From March 1, 2020 to November 30, 2024, 112 patients with active CD treated with UST or VDZ at the Department of Gastroenterology, Tenth People′s Hospital of Tongji University were retrospectively enrolled. According to the medication regimen, the 112 patients were divided into UST group (61 cases) and VDZ group (51 cases). Collected the data at baseline, such as the disease phenotype, other medication history, and clinical indicators including C-creative protein (CRP), etc. Clinical disease activity and endoscopic disease activity were assessed by Harvey-Bradshaw index (HBI) and simplified endoscopic score for Crohn′s disease (SES-CD), respectively. Transmural healing was evaluated according to the intestinal wall thickness measured by intestinal imaging examination of the affected intestinal segment. Transmural healing was defined as bowel wall thickness <0.3 cm and 110 obvious signs of inflammation, clinical remission was defined as HBI≤4, and endoscopic remission was defined as a reduction in SES-CD ≥50% or a score of ≤2. The primary endpoint was transmural healing rate within one year after treatment. The secondary endpoints were endoscopic healing rate and clinical remission rate at 13 to 24th week and 30 to 52nd week after treatment. Chi-square test or Fisher′s exact test was used to compare the efficacy of the 2 medications.Results:There was no significant difference in transmural healing rate between UST group and VDZ group within 1 year after treatment (16.4% (10/61) vs. 23.5% (12/51), χ2=0.90, P=0.344). There were no significant differences in the healing rate between UST group and VDZ group in patients with specific baseline characteristics before treatment, including CD with stenosis, with perianal disease, no history of glucocorticoid use, secondary loss of response to anti-tumor necrosis factor (TNF)-α, SES-CD 7 to 15, decreased body mass index, and increased CRP (18.2%(6/33) vs. 19.4%(7/36), 17.9%(7/39) vs. 19.4%(6/31), 17.1%(6/35) vs. 24.2%(8/33), 20.0%(8/40) vs. 3/18, 14.3%(5/35) vs. 19.2%(5/26), 15.0%(3/20) vs. 3/10, 21.4%(6/28) vs. 5/16), all P>0.05). There was no significant difference in the clinical remission rate or endoscopic remission rate between the UST group and the VDZ group from 13 to 24th week (7/14 vs. 9/18, 3/14 vs. 7/18, RR=1.000 and 0.551, 95% confidence interval: 0.497to 2.011, 0.173to 1.755, χ2=<0.01, Fisher′s exact test, both P>0.05). There was no significant difference in clinical remission rate or endoscopic remission rate between UST group and VDZ group from week 30 to week 52 after treatment (68.5% (37/54) vs. 74.4% (32/43), 27.8% (15/54) vs. 32.6% (14/43), RR=0.921 and 0.853, 95% confidence interval: 0.716 to 1.184, 0.464 to 1.568, χ2=0.41 and 0.26, both P>0.05). In UST group, the proportion of patients with normal hemoglobin after transmural healing was higher than that of patients without transmural healing (9/10 vs. 45.1% (23/51), and the difference was statistically significant ( χ2=5.08, P=0.024). However, there were no significant differences in the proportion of patients with normal body mass index, CRP, platelet count, prealbumin, albumin, interleukin-6 or TNF-α levels after treatment between those who achieved transmural healing and those who did not in either UST group or VDZ group (all P>0.05). And in VDZ group there was no significant difference in the proportion of patients with normal hemoglobin between those who achieved transmural healing and who did not (all P>0.05). Conclusion:UST and VDZ exhibit similar efficacy in transmural healing within one year of treatment in patients with active CD.

Objective:To construct a thyroid nodule segmentation model using ultrasound dynamic images and explore its potential for assisting in the screening of thyroid nodules.Methods:A total of 126 patients with thyroid nodules（comprising 150 nodules）who were diagnosed and treated at Xuzhou Cancer Hospital from April 2024 to December 2024 were prospectively enrolled. Two-dimensional ultrasound was performed to capture short-axis and long-axis video images of thyroid nodules，forming a dynamic ultrasound image dataset. The dataset was divided into training，validation，and test sets in a ratio of 6∶1∶3. After the training loss curve converged，the model that performed well on the validation set was selected for testing. Three-fold cross-validation was employed for training and testing. All 300 ultrasound videos were divided into three subsets. In each experiment，two subsets were used as the training set，and one subset was used as the test set to evaluate the model's generalization ability. A collaborative spatiotemporal diffusion model was established based on the dynamic trends and tissue texture details of thyroid nodules. Six widely used segmentation metrics were employed to evaluate the model's application capabilities.Results:The study included 126 patients with 150 thyroid nodules，300 dynamic ultrasound images，and video lengths of 3-4 seconds per nodule，resulting in 12 312 segmented images. The size of the thyroid nodules was（10.7 ± 10.6）mm（transverse diameter）×（8.4 ± 6.3）mm（anteroposterior diameter）. Among the nodules，62（41.3%）had clear boundaries，while 88（58.7%）had indistinct boundaries；61（40.7%）exhibited regular shapes，while 89（59.3%）were irregular；66（44.0%）had a taller-than-wide aspect ratio；and 70（46.7%）showed microcalcifications. The collaborative diffusion model based on dynamic ultrasound image segmentation achieved the following scores：a Jaccard score of（69.22 ± 0.03）%，a Dice score of（79.16 ± 0.18）%，a Precision score of（86.70 ± 0.17）%，a Recall score of（77.82 ± 0.04）%，an Sα score of（85.26 ± 0.01）%，and an Eθmn score of（90.58 ± 0.17）%. Compared to other models，this model demonstrated significant improvements across all evaluation metrics，achieving the highest values in each metric with increments of over 8% and 1%，respectively. Conclusions:The collaborative diffusion model with a dynamic controller，constructed based on dynamic ultrasound images of thyroid nodules，demonstrates excellent performance in ultrasound image segmentation. It improves the accuracy of thyroid nodule screening，thereby providing a valuable auxiliary diagnostic tool for clinical practice.

Objective:To propose a deep learning（DL）-based ultrasound imaging auxiliary tool for automatic segmentation and recognition of the brachial plexus（BP），and to enhance the accuracy and safety of clinical procedures.Methods:It was a multicenter study that collected 773 healthy subjects from Peking University Third Hospital and its branch campuses，the Third Medical Center of the Chinese PLA General Hospital，and Shanghai Eighth People's Hospital between August 2024 and February 2025. Brachial plexus（BP）images in the interscalene groove were captured used high-frequency ultrasound by senior sonographers，a dataset comprising 1 289 standardized images were constructed and the improved model（CHA-TransUNet）was trained. The test set was input into 6 different models（CHA-TransUNet，R50-Unet，TransUnet，SegFormer，SwinUnet，MISSFormer）for segmentation. Segmentation accuracy was evaluated using metrics including the Dice similarity coefficient（DSC），95% Hausdorff distance（HD95）and mean intersection over union（mIoU），and was compared with the segmentation results of 3 ultrasound physicians with varying experience levels（junior physicians and senior physicians）to validate the model's segmentation efficacy.Results:The CHA-TransUNet model established based on a dataset of 1 289 standardized images achieved segmentation results for the BP with a DSC of 90.15%，mIoU of 91.02%，and HD95 of 8.08. Its accuracy was higher than other mainstream models（DSC：90.15% vs. 87.60%，87.77%，81.35%，84.78%，84.55%），significantly better than junior physicians（DSC：90.15% vs. 68.73%， Z=-127.76， P<0.001），and approached the level of senior physician（DSC：90.15% vs. 86.15%， Z=-31.33， P=0.549）. The model demonstrated superior boundary recognition in complex anatomical structures（e.g.，C6/C7 nerve roots）compared to ultrasound physicians（junior and senior）（HD95：8.08 vs. 26.34，17.44，56.80）. Conclusions:This study proposes an analysis model for BP ultrasound images，CHA-TransUNet. This model achieves segmentation and recognition of the BP with relatively complex pathways and structures. The model exhibits high accuracy and stability，outperforming current mainstream network models and junior physicians while approaching the performance level of senior physicians. It assists junior physicians or trainees in more accurately identifying and localizing the BP.

Objective:To investigate the correlation of atrophy and intestinal metaplasia (IM) stage with gastric cancer and to optimize biopsy strategy.Methods:Data of patients who underwent endoscopy and five-point biopsy at Shandong Provincial Hospital between November 2020 and October 2022 were collected. The baseline characteristics of gastric cancer and non-gastric cancer patients, as well as the occurrence and severity of atrophy and IM in different areas were compared. Logistic regression analysis was used to evaluate the correlation of operative link for gastritis assessment (OLGA) and operative link for gastric intestinal metaplasia assessment (OLGIM) staging with gastric cancer. The Kendall tau correlation coefficient was used to compare the consistency of different biopsy strategies (two-point, three-point, and four-point) with the standard five-point biopsy in OLGA and OLGIM staging. Receiver operating characteristic (ROC) curve analysis was further performed to compare the diagnostic performance of different biopsy strategies in identifying the OLGA and OLGIM Ⅲ-Ⅳ stage.Results:A total of 122 patients were included in the analysis, with age of 61.0±10.0 years. Multivariate analysis showed that OLGA staging was not associated with gastric cancer ( P=0.788), while OLGIM Ⅲ-Ⅳ staging was significantly correlated with gastric cancer ( P=0.006, OR=3.39, 95% CI: 1.41-8.17). The occurrence of atrophy and IM were higher in lesser curvature of the antrum [56.6% (69/122) and 66.4% (81/122)] and incisura angularis [57.4% (70/122) and 52.5% (64/122)], with higher severity, while lower in greater curvature of the corpus [2.5% (3/122) and 5.7% (7/122)], with lower severity. The consistency of four-point and three-point biopsies with standard five-point biopsy in OLGA and OLGIM staging was high. The consistency of three-point biopsy in incisura angularis, lesser curvature of the antrum and corpus was exceptionally high among them, with correlation coefficients of 0.969 and 0.987, respectively. Conclusion:OLGIM Ⅲ-Ⅳ stages increase the risk of gastric cancer. Three-point biopsy in incisura angularis, lesser curvature of the antrum and corpus are recommended for the screening and monitoring of atrophy or IM.

Objective:To evaluate the efficacy and safety of adalimumab (ADA) in the treatment of Crohn′s disease (CD), and to analyze the predictive factors of ADA efficacy.Methods:From January 2020 to December 2020, 49 CD patients treated with ADA at the Department of Gastroenterology, Tenth People′s Hospital of Tongji University of Shanghai were enrolled. The clinical data before treatment were collected. During 12 weeks of ADA treatment, the patients were followed up every 2 weeks, the laboratory examinations were conducted every 4 weeks, and colonoscopy examination was rechecked at the 12th week. The improvement of the main symptoms of patients was assessed at 2nd, 4th, and 6th week during ADA treatment. At the 12th week after ADA treatment, the clinical response (Crohn′s disease activity index (CDAI) score decreased ≥70 points from baseline), clinical remission (CDAI score < 150 points), endoscopic response (simple endoscopic score for Crohn′s disease (SES-CD) decreased >50% from baseline) and endoscopic remission (SES-CD ≤2 points or Rutgeerts score ≤1 point), closure of anal fistula of CD patients complicated with anal fistula and occurrence of adverse reactions during treatment were recorded. The predictive factors of clinical remission of CD patients after ADA treatment for 12 weeks were analyzed. The Mann-Whitney U test and binary logistic regression analysis were used for statistical analysis. Results:The main symptom improved rates of 49 CD patients received ADA treatment at 2nd, 4th and 6th week were 75.5% (37/49), 95.9% (47/49) and 98.0% (48/49), respectively, and the main symptom improved time was 14.0 d (7.0 d, 17.0 d). After ADA treatment for 12 weeks, the clinical remission rate was 55.1% (27/49), the clinical response rate was 73.5% (36/49), the endoscopic remission rate was 43.3% (13/30), the endoscopic response rate was 55.6% (15/27), the anal fistula closure rate was 7/18, and the overall incidence of adverse reactions was 24.5% (12/49). The baseline of fecal calprotectin (FC) level of patients in the clinical remission group (27 cases) was lower than that of the patients in the active disease group (22 cases) (111.0 μg/g, 26.3 μg/g to 125.6 μg/g vs. 540.5 μg/g, 420.2 μg/g to 866.9 μg/g), and the difference was statistically significant ( Z=-4.44, P<0.001). The results of binary logistic regression analysis showed that baseline FC level was an independent predictive factor of clinical remission in CD patients treated with ADA for 12 weeks ( OR=1.08, 95%confidence interval 1.02 to 1.14, P=0.013). When the baseline FC cut-off value was 172.39 g/g, the sensitivity and specificity of it in predicting clinical remission in CD patients treated with ADA for 12 weeks were 81.48% and 90.91%, and the area under the receiver operator characteristic curve was 0.87 ( P<0.001). Conclusions:ADA is safe and effective in the treatment of CD. The baseline FC level is an independent predictive factor of clinical remission in CD patients treated with ADA for 12 weeks.

Objective To investigate the independent association of serum Fetuin-B with metabolic syndrome in obese Chinese adults.Methods Cross-sectional data on socio-demographic,lifestyle,clinical characteristics, and serum Fetuin-B were collected for 1 318 Chinese adults with central obesity.Associations of serum Fetuin-B with metabolic syndrome and insulin resistance were analyzed using multivariable Logistic regression analysis.Results A total of 820(62.2%)individuals were identified as metabolic syndrome.Subjects with metabolic syndrome showed significantly increased levels of serum Fetuin-B than those with non-metabolic syndrome[(4.18 ±1.39 vs 4.02 ± 1.35)μg/ml,P=0.043].Increased serum Fetuin-B were significantly associated with increased fasting plasma glucose and insulin levels, as well as prevalences of non-alcoholic fatty liver disease(NAFLD)and insulin resistance.After adjustment for potential confounders, serum Fetuin-B was significantly associated with increased risks of metabolic syndrome and insulin resistance(OR=1.19,95%CI 1.06-1.34,P=0.004;OR=1.15,95%CI 1.01-1.30,P=0.031 respectively).Conclusion Serum Fetuin-B level was significantly associated with NAFLD;and elevated serum Fetuin-B was significantly associated with increased risk of metabolic syndrome.

Objective To investigate the prophylactic effects of pancreatic duct stenting (PDS) combined with non-storied anti-inflammatory drug (NSAID) on post endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) in difficult bile duct cannulation .Methods One hundred and eight patients who experienced difficult bile duct cannulation during hospitalization from January 2012 to November 2016 in the Department of Gastroenterology of the hospital were enrolled for the study .The patients were ran-domly divided into 4 groups:i.e.Group A that underwent simple PDS , Group B that received NSAID , Group C that were treated with PDS combined with NSAID and Group D that had routine ERCP without preventive measures for PEP .The levels of serum amylase be-fore surgery, 4 and 24 hours after ERCP were observed closely .The scores of abdominal pain were evaluated by VAS method , and the levels of serum amylase , the rate of post ERCP and scores of abdominal pain after ERCP were compared between the 4 groups.Results Four hours after ERCP, serum amylase levels of group B and group C were all significantly lower that those of group D (P<0.05). Serum amylase levels of group A, B and C 24 hours after ERCP were all significantly lower that those of group D (P<0.05).The rate of PEP 24 hours after ERCP for group A and C was 0%, which was obviously lower than that of group D (7.4%)(P<0.05).The VAS scores of various groups 4 and 24 hours after ERCP were significantly higher than that before ERCP (P<0.05).The VAS scores of groups B and C 4 and 24 hours after ERCP were all significantly higher than that of group D (P<0.05), and the VAS scores of group B 4 and 24 hours after ERCP was obviously lower than that of group A (P<0.05).Only at hour 24 after ERCP, the VAS pain scores of group A were higher than that of group D (P<0.05).Conclusion After ERCP, pancreatic duct stenting combined with non-storied anti-inflammatory drug could reduce the rates of hyperamylasemia and PEP , as well as the scores of abdominal pain scores after ERCP, and also could effectively prevent the incidence of pancreatitis after PEP .