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] In view of the crucial role of indole propionic acid in the treatment of tumor immune checkpoint blockade and further revealing its mechanism, our study intended to design and synthesize 1-[¹⁸F]-fluoroethyl-indole propionic acid (1-[¹⁸F]-IPA), and evaluate it as a tumor PET imaging agent. [Methods] The precursor 1-(2-p-toluenesulfonic acid oxygen ethyl)-methyl indole propionate underwent nucleophilic substitution reaction with ¹⁸F^-. The crude product was separated and purified by high-performance liquid chromatography and the intermediates were collected. Finally, 1-[¹⁸F]-IPA was obtained by hydrolysis. The clarity of the product was measured by visual inspection, the pH value was determined by precision test paper, and the radiochemical purity and stability were determined by high-performance liquid chromatography. In order to determine the biodistribution of 1-[¹⁸F]-IPA in normal mice, ICR mice were intravenously injected with 1-[¹⁸F]-IPA (0.2 mL, 7 MBq), and sacrificed at 5, 15, 25, 45, 75 and 120 min and dissected. Micro-PET imaging was performed and analyzed in BxPC-3 tumor-bearing nude mice. Student t test was used to compare the biodistribution of tissues and organs at different time points. [Results] The total preparation time of 1-[¹⁸F]-IPA was 35-40 min, the radiochemical yield was (45±5)%, and the radiochemical purity was more than 95%. The product solution was clear without particles, and the pH value was 6.5, which had good stability in vitro and in vivo. The results of biodistribution in healthy ICR mice showed that except for the brain, 1-[¹⁸F]-IPA had a certain uptake in all major organs, with the most obvious uptake in the liver, gallbladder and kidneys. The radioactivity in the gallbladder gradually increased with time and reached (39.86±6.56)%ID/g at 120 min, but bone uptake did not change significantly with time. Micro-PET/CT showed that there was radioactive uptake at the tumor 30 min after injection of 1-[¹⁸F]-IPA in Dutch BxPC-3 nude mice, but it was not obvious. At this time, SUVmax was about 55.18±14.62. Consistent with the results of biodistribution, the brain uptake was low at each time point. [Conclusion] In summary, 1-[¹⁸F]-IPA with short preparation time and high yield is expected to be a tool to probe tryptophan indole metabolism pathway and further reveal tumor immune resistance.

【Objective】 To compare the value of CT pulmonary angiography (CTPA) and echocardiography in predicting the degree pulmonary hypertension (PH). 【Methods】 Fifty-four patients in our hospital who underwent right heart catheterization, CTPA and echocardiography for suspected or confirmed PH from November 2013 to April 2021 were retrospectively recruited. Pulmonary artery systolic pressure (PASP) and mean pulmonary artery pressure (PAMP) were measured by right heart catheterization. According to PAMP, the patients were divided into non-PH group and mild, moderate, and severe PH groups. The three-dimensional model of the pulmonary artery was obtained by computer-aided segmentation, and the best fitting circle diameter (Dfit), inscribed circle diameter (Dmin), circumscribed circle diameter (Dmax), hydraulic diameter (Dh), cross-sectional area (Area), circumference (Scf), and the largest area and largest short diameter of the right ventricle were measured. Echocardiography was used to estimate PASP. The differences in the above parameters between different PH groups were compared, the correlations of the above parameters with PASP and PAMP were analyzed, and statistically significant indicators were included to establish three predictive models of PAMP (Model 1: CTPA pulmonary artery; Model 2: CTPA pulmonary artery+CTPA right ventricle; Model 3: CTPA pulmonary artery+CTPA right ventricle+echocardiography), and receiver operating characteristic (ROC) curves were used to compare the diagnostic performance of the three models. 【Results】 Some parameters of main pulmonary artery (Dfit, Dmin, Dmax, Dh, Area, Scf), right pulmonary artery (Dmax, Dh, Area, Scf), left pulmonary artery (Dfit), and right ventricular short diameter increased with the increase of PAMP (P<0.05). Dfit, Dmin, Dh, and area of main pulmonary artery, right pulmonary artery and left pulmonary artery were positively correlated with PASP and PAMP (P<0.05). Right ventricular short diameter and right ventricular maximum area were positively correlated with PASP (P<0.05), and right ventricular short diameter was positively correlated with PAMP (P<0.05). The estimated value of pulmonary artery systolic blood pressure in echocardiography was positively correlated with PASP and PAMP (P<0.05). Model 1, Model 2 and Model 3 could all be used to identify mild PH and moderate PH, among which Model 3 had the best performance in identifying non-PH and mild PH, moderate PH and severe PH. 【Conclusion】 CTPA and echocardiography are helpful in assessing the degree of PH, and the combination of the two has better accuracy in distinguishing non-PH from mild PH, moderate and severe PH.

Objective:To evaluate the diagnostic value of the 18F-prostate specific membrane antigen (PSMA)-1007 PET/CT in seminal vesicle invasion (SVI) of prostate cancer. Methods:Clinical and pathological materials of 88 patients (age: 51-84 years) who underwent radical prostatectomy (RP) between May 2019 and December 2021 in the First Affiliated Hospital of Xi′an Jiaotong University were analyzed retrospectively. All patients underwent 18F-PSMA-1007 PET/CT examination for primary staging before surgery. The diagnostic efficiency of 18F-PSMA-1007 PET/CT in SVI was obtained using postoperative pathological results as the " gold standard" and ROC curve was drawn. Furthermore, univariate and multivariate logistic regression analyses were used to screen the influencing factors for 18F-PSMA-1007 PET/CT prediction of SVI. Results:The accuracy, sensitivity, specificity, positive predictive value and negative predictive value of 18F-PSMA-1007 PET/CT in diagnosing SVI were 79.55%(70/88), 72.73%(16/22), 81.82%(54/66), 57.14%(16/28) and 90.00%(54/60), respectively. The ROC AUC was 0.77. Results of univariate logistic regression showed that total prostate specific antigen (tPSA), primary SUV max, Gleason score, International Society of Urological Pathology (ISUP) grade group were associated with 18F-PSMA-1007 PET/CT prediction of SVI. Results of multivariate logistic regression showed that Gleason score (odds ratio ( OR)=2.04, 95% CI: 1.19-3.50, P=0.009) was a predictor of SVI in prostate cancer. Conclusion:18F-PSMA-1007 PET/CT has certain diagnostic value in SVI of prostate cancer, and combining with Gleason score can improve the diagnostic efficiency.

【Objective】 To analyze the correlation of whole body tumor burden of ¹⁸F-prostate specific membrane antigen positron emission computed tomography （¹⁸F-PSMA PET/CT） with prostate specific antigen （PSA） and Gleason score so as to evaluate the value of ¹⁸F-PSMA PET/CT whole body tumor burden for predicting serum PSA progression in prostate cancer. 【Methods】 We retrospectively recruited 213 patients with prostate cancer who underwent ¹⁸F-PSMA PET/CT scanning from March 2019 to April 2021. The serum PSA and Gleason score were collected. Whole body tumor burden was measured by a semi-automatic method. The correlation of tumor burden with serum PSA and Gleason score was analyzed. After radical prostatectomy， the patients were divided into groups according to negative or positive ¹⁸F-PSMA PET/CT. PSA differences between groups were compared， and the receiver operating characteristic curve （ROC） of the subjects was drawn so as to obtain the threshold value of PSA to predict the positive rate of ¹⁸F-PSMA PET/CT. The patients were followed up for PSA after radical surgery， divided into groups according to the progress of PSA， and the differences in tumor burden between groups were compared. 【Results】 In Gleason score ≤7， =8， and ≥9 groups， whole body tumor burden was correlated with PSA in each group （P=0.001）， and tumor burden significantly differed between the groups （P<0.001）. In initial diagnosis and treatment group， biochemical recurrence group， and medication group， the correlation between tumor burden and PSA was statistically significant （P=0.001）. The Gleason score of primary prostate lesion was significantly correlated with systemic tumor burden （P<0.001）. The area under ROC curve of PSA predicting the positive rate of ¹⁸F-PSMA PET/CT after radical prostatectomy was 0.821； when PSA>0.577 ng/mL， the sensitivity and the specificity were 66.7% and 96.8%， respectively. The mean whole body tumor burden in ¹⁸F-PSMA PET/CT positive patients with PSA progression was higher than that in patients without PSA progression. 【Conclusion】 The whole body tumor burden of ¹⁸F-PSMA PET/CT is significantly correlated with PSA， which is helpful in predicting the serum PSA progression in prostate cancer. PSA can predict the positive rate of ¹⁸F-PSMA PET/CT to a certain extent. At the same time， PSA can also predict positive results of ¹⁸F-PSMA PET/CT to a certain extent， and guide clinical rational selection of this examination.

【Objective】 To explore the value of 18F-PSMA-1007 PET/CT in evaluating the primary tumor and infiltration range of prostate cancer. 【Methods】 We retrospectively collected 18F-PSMA-1007 PET/CT whole body imaging data of the patients who came to the Department of Urology， The First Affiliated Hospital of Xi’an Jiaotong University， from March 2019 to June 2021 due to suspected or diagnosed prostate cancer. No treatment was give before the examination. In addition， 51 patients underwent radical surgery after examination and obtained complete pathological results. We used a semi-automatic method to delineate the region of interest （ROI） of 40% SUVmax of prostate cancer foci， and obtained the metabolic parameters， namely， SUVmax， SUVmean， tumor metabolic volume （MTV） and total lesion metabolic （TLM）. We also observed for infiltration of bilateral seminal vesicle glands and bladder. Correlation analysis was used to analyze the correlation of metabolic parameters with Gleason score and tumor grade grouping； McNemar test was used to analyze the accuracy of PSMA in evaluating the extent of prostate invasion. 【Results】 The PET/CT parameters SUVmax， SUVmean， TLM and Gleason score were not significantly correlated， but SUVmean was positively correlated with tumor grade （r=0.306， P=0.041）. The pathological results showed a moderate correlation between the maximum diameter of the tumor and MTV （r=0.479， P=0.003）. The sensitivity evaluated by PSMA-PET/CT to primary prostate tumor， capsule invasion， seminal vesicle gland invasion， and bladder invasion was 72.00%， 64.71%， 83.33%， and 25.00%， respectively； the specificity was 88.46%， 33.33%， 84.61%， and 95.74%， respectively； the accuracy was 80.39%， 52.94%， 86.27%， and 90.19%， respectively. 【Conclusion】 ¹⁸F-PSMA-1007 PET/CT imaging has high accuracy in assessing primary tumor and the extent of invasion of prostate cancer， which indicates its value in clinical application.

【Objective】 To investigate the value of prostate cancer prevention trial risk calculator （PCPT-RC） combined with biopsy Gleason score for predicting the risk of metastasis in newly diagnosed prostate cancer patients. 【Methods】 We retrospectively collected the data of 74 patients with newly diagnosed prostate cancer confirmed by biopsy from April 2019 to August 2021， concurrent with ¹⁸F-PSMA-1007 PET/CT whole body imaging in the same period. Based on this， a binary logistic regression model was established to obtain the high risk probability of PCPT. We calculated the receiver operating characteristic curve （ROC） was drawn and the area under the curve， Yuden index， sensitivity， specificity， positive predictive value and negative predictive value. We compared the predictive value of the prostate cancer prevention trial risk calculator and Gleason score alone or in combination in predicting the risk of prostate cancer metastasis. 【Results】 Based on the PSMA PET/CT results， 74 patients were divided into non-metastatic group （46/74） and metastatic group （28/74）. PCPT high risk probability ［41.14% （16%-67%）］ vs. ［30.89% （5%-65%）］， Gleason score ［8.5（6-10） score］ vs. ［7.7（6-9） score］， tPSA ［26.24（5.70-42.32） ng/mL］ vs. ［19.58（2.47-49.35） ng/mL］， and fPSA ［3.94（0.82-12.00） ng/mL］ vs. ［2.33（0.35-10.20） ng/mL］ were significantly higher in metastatic group than in non-metastatic group. Binary Logistic regression analysis showed that Gleason score and PCPT low risk probability may be independent predictors of prostate cancer metastasis. PCPT low risk probability alone did not predict the risk of prostate cancer metastasis （P=0.172）. The predictive accuracy of Gleason score and high probability of PCPT in predicting prostate cancer metastasis were 0.715 and 0.679， respectively， and the accuracy of the combined prediction was 0.809. 【Conclusion】 PCPT-RC combined with Gleason score is valuable for predicting the metastasis risk of newly diagnosed prostate cancer patients， which has certain guiding significance for clinical individualized treatment.

Objective:To construct 2019 novel coronavirus (2019-nCoV) 614D and 614G pseudovirus by HIV lentivirus packaging system and explore their biological specificity.Methods:The recombinant expression plasmids pCDNA3.1-614D and pCDNA3.1-614G were transiently cotransfected with psPAX2 and pLenti CMV Puro LUC into 293T cells respectively. After 72 hours, the supernatant was collected and ultracentrifuged with 20% sucrose cushion. The titer, morphology, protein expression and neutralizing activity of pseudovirus were determined.Results:S protein specific fluorescence was detected by indirect immunofluorescence test, Western blot analysis showed S protein was expressed, and the spike of pseudovirus was observed under transmission electron microscope. The titers of pseudovirus 614D and 614G were 1.12×10 4 and 2.52×10 4 TCID 50/ml, respectively. The pseudovirus 614D and 614G could be neutralized by S rabbit polyclonal antibody, indicating that the pseudovirus has high specificity. Conclusions:In this study, 2019-nCoV 614D and 614G pseudovirus was successfully constructed, which laid the foundation for the establishment of in vitro neutralizing antibody detection platform based on pseudovirus.

OBJECTIVE: To analyze the indication, karyotyping result, ultrasound finding, pregnancy decision and follow-up of fetuses with sex chromosome aneuploidies (SCA) detected by non-invasive prenatal testing (NIPT) during early and midterm pregnancies. METHODS: The results of 225 singleton pregnancies with fetal SCA detected by NIPT were reviewed and analyzed. RESULTS: The 225 cases included 45,X (n=37), 47,XXY (n=74), 47,XXX (n=50), 47,XYY (n=56) and mosaicisms (n=8), among which 121 (53.8%) have opted to terminate the pregnancy, including 45,X (n=31), 47,XXY (n=61), 47,XXX (n=14), 47,XYY (n=12) and 3 mosaicisms. The remainder 104 (46.2%) have elected to continue with the pregnancy, among which three have opted to terminate due to abnormalities detected by ultrasonography, and two had spontaneous abortions. CONCLUSION NIPT as a first-tier screening method can effectively detect fetal trisomies 21, 13 and 18 as well as SCA. The types of fetal SCA and presence of ultrasound abnormalities are critical factors for the termination of pregnancy.
Aneuploidy ; Down Syndrome ; Female ; Fetus ; Humans ; Pregnancy ; Prenatal Diagnosis ; Sex Chromosome Aberrations ; Trisomy