Objective:To establish a risk scoring system for moderate to severe spermatogenic dysfunction based on scrotal ultrasound parameters and machine learning, and to explore its value.Methods:A retrospective cohort analysis was conducted on 112 patients diagnosed with azoospermia, moderate to severe oligospermia, and asthenospermia in the Department of Reproductive Medicine at Binzhou Medical University Affiliated Hospital from June 2021 to December 2022. Scrotal ultrasound parameters of these patients were compared with those of 116 normal male patients who visited the same hospital during the same period for reproductive assistance. Models were constructed using Random Forest, Support Vector Machine, logistic Regression, K-nearest neighbor algorithm, and XGBoost. A risk scoring system was established based on the average SHapley Additive exPlanation values of each model. The predictive performance of the model was evaluated using the receiver operating characteristic curve, and the clinical application value of the model was evaluated using the decision curve analysis.Results:The scoring system included bilateral testicular total volume, whether the testicular echo was uniform, the inner diameter of the right spermatic vein, and the reflux time of varicocele. The area under the curve (AUC) of the risk scoring system for the training set was 0.757, and the AUC for the test set was 0.718. The decision curve showed that this scoring system had a high clinical value.Conclusion:A risk scoring system based on scrotal ultrasound parameters and machine learning can effectively predict moderate to severe spermatogenic dysfunction, which is of positive significance for early detection of such patients.

Objective:To establish a risk scoring system for moderate to severe spermatogenic dysfunction based on scrotal ultrasound parameters and machine learning, and to explore its value.Methods:A retrospective cohort analysis was conducted on 112 patients diagnosed with azoospermia, moderate to severe oligospermia, and asthenospermia in the Department of Reproductive Medicine at Binzhou Medical University Affiliated Hospital from June 2021 to December 2022. Scrotal ultrasound parameters of these patients were compared with those of 116 normal male patients who visited the same hospital during the same period for reproductive assistance. Models were constructed using Random Forest, Support Vector Machine, logistic Regression, K-nearest neighbor algorithm, and XGBoost. A risk scoring system was established based on the average SHapley Additive exPlanation values of each model. The predictive performance of the model was evaluated using the receiver operating characteristic curve, and the clinical application value of the model was evaluated using the decision curve analysis.Results:The scoring system included bilateral testicular total volume, whether the testicular echo was uniform, the inner diameter of the right spermatic vein, and the reflux time of varicocele. The area under the curve (AUC) of the risk scoring system for the training set was 0.757, and the AUC for the test set was 0.718. The decision curve showed that this scoring system had a high clinical value.Conclusion:A risk scoring system based on scrotal ultrasound parameters and machine learning can effectively predict moderate to severe spermatogenic dysfunction, which is of positive significance for early detection of such patients.

Objective:To explore the value of the elasticity contrast index (ECI) in differential diagnosis of thyroid nodules, and contrast the effect of 4 different methods on measuring ECI.Methods:A total of 122 patients with 131 thyroid nodules in Binzhou Medical University Hospital from May 2018 to May 2019 were enrolled, and elastography was performed in 4 different ways such as in axial plane for internal (AI), axial plane for periintranodular (AP), longitudinal plane for internal (LI) and longitudinal plane for periintranodular (LP). The cut-off values for predicting malignant nodules in 4 different ways were determined separately using receiver operating characteristic (ROC) curve analysis.Results:There were 54 benign and 77 malignant ones in 131 nodules. The ECI in AI, AP, LI and LP in benign thyroid nodules was significantly lower than that in malignant ones: 2.10 (1.48, 2.34) vs. 3.07 (2.73, 3.87), 1.91 (1.64, 2.18) vs. 2.62 (2.24, 3.07), 2.19 (1.59, 2.39) vs. 3.00 (2.72, 3.63) and 1.89 (1.71, 2.16) vs. 2.66 (2.21, 3.10), and there was statistical difference ( P<0.05). Among the 4 different ways, the largest area under curve was achieved in AI with 0.925, and the corresponding optimal diagnostic threshold was 2.43 (with 90.9% sensitivity, 87.0% specificity, 88.5% accuracy, 89.7% positive predictive value and 86.8% negative predictive value). Conclusions:ECI is helpful for conventional ultrasound to diagnose thyroid nodules as malignant or benign. The best value is obtained in AI.

Objective To investigate the clinical application value of the real-time shear wave elastography (SWE)technology in the curative evaluation on Hashimoto′s thyroiditis(HT)patients treated with prednisone. Methods Applying SWE technology to determine the Young′s modulus value of thyroid tissue of 45 HT cases with subclinical hypothyroidism before and one month after treatment. Results 1 month after prednisone treat-ment,the Young′s modulus value and serum thyroid stimulating hormone(TSH),thyroid-peroxidase antibody (TPOAb)and thyroglobulin antibody(TGAb)were observed significantly changed before and one month after treatment(P < 0.05,respectively). The various modulus value was found reduced with different degrees,but the serum TSH was shown back to normal after the treatment with prednisone. Conclusions By quantitative determi-nation of Young′s modulus value,the hardness of organization information was obtained objectively,which could provide more meaningful reference basis to evaluate the treatment of prednisone for HT.

Objective To dynamically observe and evaluate the position and movement of anterior pelvic floor organs in vaginal delivery and selective caesarean section primipara with translabial two-dimensional 2D ultrasound and discuss the short-term effect of delivery mode on the anterior compartment of pelvic floor Methods Translabial 2D ultrasound was performed on selective caesarean section and vaginal delivery primipara in 6-8 weeks The position of bladder the existence of bladder neck funneling were observed and the mobility of bladder neck and the urethral rotation angle were measured during maximum Valsalva maneuver Results The mobility of bladder neck was larger in vaginal delivery group than selective caesarean section group during maximum Valsalva maneuver The rates of bladder neck funneling cystocele and stress urinary incontinence were higher in vaginal delivery group Conclusions Translabial 2D ultrasound could dynamically observe and evaluate the position and movement of anterior pelvic floor organ which could be used to assess the effect of delivery mode on anterior compartment of pelvic floor The short-term effect of vaginal delivery on anterior compartment of pelvic floor is greater than that of selective cesarean delivery.

Objective To investigate the pelvic floor in cystocele patients using translabial ultrasound,and discuss the ultrasound appearance.Methods Translabial 2D ultrasound was performed on 136 patients who were diagnosed or suspected as anterior vaginal wall prolapse or cystocele using pelvic organ prolapse quantitation system,the position of bladder,the retrovesical angle and urethral rotation were measured during maximum Valsalva maneuver.Cystocele subtypes were diagnosed according to the ultrasound findings.Results Translabial 2D ultrasound diagnosed 88 cases cystocele based on the position of bladder,retrovesical angle and urethral rotation,including ten cases cystocele type Ⅰ,32 cases type Ⅱ and the remaining 46 classified as type Ⅲ.Conclusions Translabial 2D ultrasound successfully acquired the ultrasonic characteristics of cystocele subtypes,which could provide imaging evidence for clinic diagnosis of this disease.