Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

Objective To investigate the risk factors for anastomotic leakage (AL) after laparoscopic intersphincteric resection (Lap-ISR) for patients with low-lying rectal cancer.Methods This retrospective study was conducted in the Characteristic Medical Center of PLA Rocket Force from Jun 2011 to Nov 2018.151 patients undergoing Lap-ISR were enrolled for this study.Results All patients in this series had a defunctioning ileostomy.The overall leakage rate was 17.2％ (26/151),including peri-operative AL (n =20) and delayed AL (n =6).In accordance with the grading system of the International Study Group of Rectal Cancer,there were 24 patients (15.9％) with AL Grade B (requiring active therapeutic intervention) and two patients (1.3％) with AL Grade C (requiring re-laparotomy).Univariate analysis showed that BMI (≥ 25 kg/m2),tumor annularity (≥ 3/4) and operation time (≥ 240 min) were associated with AL (P ＜ 0.05).Multivariate analysis showed that operation time (≥ 240 min,OR =7.390,95％ CI:2.483-21.988,P =0.000),tumor annularity (≥ 3/4,OR =6.233,95％ CI:1.932-20.107,P=0.002) and higher BMI (≥ 25 kg/m2,OR=3.523,95％ CI:1.275-9.738,P=0.015)were independently predictive of AL Conclusion Tumor annularity,operation time and higher BMI are independently associated with symptomatic AL after Lap-ISR.

OBJECTIVETo evaluate the long-term efficacy of stapled transanal rectal resection (STARR) in treating obstructed defecation syndrome(ODS).

METHODSClinical data of 95 female patients with ODS undergoing STARR at Department of Colorectal Surgery, Rocket Army General Hospital from February 2010 to August 2012 were analyzed retrospectively. The Cleveland constipation scoring system (CSS), Longo ODS scoring system and severe symptoms score(SSS) were used to evaluate the degree and intensity of clinical symptoms. Patient satisfaction was assessed by visual analogue scale (VAS). Clinical symptoms at postoperative 12-month were defined as short-term efficacy, and at the end of follow up (≥48 months) were defined as long-term efficacy.

RESULTSThe mean age was 54.5 (29 to 79) years and the median follow-up was 65 (48 to 78) months. Eighty (84.2%) and 44 (46.3%) patients completed the short-term and long-term efficacy evaluation respectively. At the end of follow up, compared with the baseline levels before operation, the CSS score (14.69 vs. 6.02), ODS score (16.51 vs. 5.73) and SSS score (14.64 vs. 5.14) were significantly decreased (all P<0.01), but the VAS score (3.96 vs. 7.20, P<0.01) was significantly increased. A total of 10 patients (22.7%) developed symptomatic recurrence. The self-reported definitive satisfaction was excellent in 10 (22.7%) patients, fairly good in 17(38.6%), good in 9(20.5%), and poor in 8(18.2%). The total effective rate was 81.8%(36/44).

CONCLUSIONLong-term efficacy of STARR in the treatment of ODS is good, but the rate of symptomatic recurrence is relatively high.