Objective:To explore the clinical application value of artificial intelligence（AI）-assisted training in enhancing the accuracy of nuchal translucency（NT）identification，standardization of measurement，and diagnostic efficacy for abnormalities among ultrasound residents.Methods:A retrospective collection of 300 standard fetal NT ultrasound images was conducted at the Center for Medical Ultrasound，Suzhou Hospital Affiliated of Nanjing Medical University from January 2018 to June 2024. The AI model performed NT measurements and diagnoses once. Four sonographers of different seniority levels（including two resident physicians）independently conducted NT measurements and diagnoses twice. Prior to the experiment，the middle-age and resident sonographers had uniformly completed traditional theory training. Following the first independent measurements，the two resident sonographers received additional AI-assisted training，after which all 4 sonographers performed the second independent measurements. A fetal medicine expert evaluated blindly all the results and compared the differences in NT recognition accuracy，measurement standard rate and diagnosis accuracy between the middle-age sonographer（traditional training only）and two resident sonographers（traditional + AI-assisted training）.Results:For the middle-aged sonographer who only received traditional lecture-based training，the accuracy of NT recognition，standardization rate of measurement，or diagnostic accuracy were not significantly improved befroe and after the training，and the diffrence was not statistically significant（ χ2=0.189，1.887，0.326；all P>0.05）. In contrast，the second-year resident（Resident 2）and first-year resident（Resident 1），who received both traditional lecture-based training and AI training，demonstrated some improvements in the accuracy of NT measurement site recognition，though the differences were not statistically significant（ χ2=1.301，2.418；all P>0.05）. However，both residents did significant improvements in the standardization rate of NT measurement（ χ2=25.768，17.035；all P<0.05）. In terms of diagnostic accuracy，Resident 1 did significant improvement（ χ2=10.180， P<0.05），while Resident 2 also did some improvement，though the difference was not statistically significant（ χ2=2.573， P>0.05）. Conclusions:The AI-assisted training system enhances the ability of ultrasound resident sonographers to recognize，measure，and diagnose NT，providing a novel and efficient training model for standardized residency training in ultrasound specialties.

Objective:To investigate the diagnostic value of fetal cardiac ultrasound view visualization in the first trimester for congenital heart disease（CHD）.Methods:A retrospective analysis was performed on 13 323 singleton fetuses who underwent first-trimester（11-13 +6 weeks）ultrasound screening at the Ultrasound Medicine Center，the Affiliated Suzhou Hospital of Nanjing Medical University from January 2018 to June 2024. Cardiac views including the four-chamber view（4CV），left ventricular outflow tract view（LVOT），and Results:The study group showed significantly higher rates of "poorly visualized" 4CV，LVOT，and 3VT than the control group（2.70% vs. 0.14%， P=0.005；36.49% vs. 4.76%， P<0.001；36.49% vs.2.46%， P<0.001）. The efficacies of combination 1（any view abnormal）and combination 2（any view "poorly visualized" or "abnormal"）were comparable，with AUCs of 0.86 and 0.85（ P=0.424）. The AUCs of combination 3（3VT "poorly visualized" or any view "abnormal"）and combination 4（4CV "poorly visualized" or any view "abnormal"）were 0.88 and 0.86（ P=0.424），all significantly higher than combination 5（LVOT "poorly visualized" or any view "abnormal"，AUC=0.84，all P<0.05）. Conclusions:"Poorly visualized" cardiac views in the first trimester demonstrate good diagnostic efficacy for CHD，particularly when 3VT or 4CV are affected，warranting heightened clinical vigilance for fetal cardiac anomalies.

Objective:To explore the clinical application value of artificial intelligence（AI）-assisted training in enhancing the accuracy of nuchal translucency（NT）identification，standardization of measurement，and diagnostic efficacy for abnormalities among ultrasound residents.Methods:A retrospective collection of 300 standard fetal NT ultrasound images was conducted at the Center for Medical Ultrasound，Suzhou Hospital Affiliated of Nanjing Medical University from January 2018 to June 2024. The AI model performed NT measurements and diagnoses once. Four sonographers of different seniority levels（including two resident physicians）independently conducted NT measurements and diagnoses twice. Prior to the experiment，the middle-age and resident sonographers had uniformly completed traditional theory training. Following the first independent measurements，the two resident sonographers received additional AI-assisted training，after which all 4 sonographers performed the second independent measurements. A fetal medicine expert evaluated blindly all the results and compared the differences in NT recognition accuracy，measurement standard rate and diagnosis accuracy between the middle-age sonographer（traditional training only）and two resident sonographers（traditional + AI-assisted training）.Results:For the middle-aged sonographer who only received traditional lecture-based training，the accuracy of NT recognition，standardization rate of measurement，or diagnostic accuracy were not significantly improved befroe and after the training，and the diffrence was not statistically significant（ χ2=0.189，1.887，0.326；all P>0.05）. In contrast，the second-year resident（Resident 2）and first-year resident（Resident 1），who received both traditional lecture-based training and AI training，demonstrated some improvements in the accuracy of NT measurement site recognition，though the differences were not statistically significant（ χ2=1.301，2.418；all P>0.05）. However，both residents did significant improvements in the standardization rate of NT measurement（ χ2=25.768，17.035；all P<0.05）. In terms of diagnostic accuracy，Resident 1 did significant improvement（ χ2=10.180， P<0.05），while Resident 2 also did some improvement，though the difference was not statistically significant（ χ2=2.573， P>0.05）. Conclusions:The AI-assisted training system enhances the ability of ultrasound resident sonographers to recognize，measure，and diagnose NT，providing a novel and efficient training model for standardized residency training in ultrasound specialties.

Objective:To investigate the diagnostic value of fetal cardiac ultrasound view visualization in the first trimester for congenital heart disease（CHD）.Methods:A retrospective analysis was performed on 13 323 singleton fetuses who underwent first-trimester（11-13 +6 weeks）ultrasound screening at the Ultrasound Medicine Center，the Affiliated Suzhou Hospital of Nanjing Medical University from January 2018 to June 2024. Cardiac views including the four-chamber view（4CV），left ventricular outflow tract view（LVOT），and Results:The study group showed significantly higher rates of "poorly visualized" 4CV，LVOT，and 3VT than the control group（2.70% vs. 0.14%， P=0.005；36.49% vs. 4.76%， P<0.001；36.49% vs.2.46%， P<0.001）. The efficacies of combination 1（any view abnormal）and combination 2（any view "poorly visualized" or "abnormal"）were comparable，with AUCs of 0.86 and 0.85（ P=0.424）. The AUCs of combination 3（3VT "poorly visualized" or any view "abnormal"）and combination 4（4CV "poorly visualized" or any view "abnormal"）were 0.88 and 0.86（ P=0.424），all significantly higher than combination 5（LVOT "poorly visualized" or any view "abnormal"，AUC=0.84，all P<0.05）. Conclusions:"Poorly visualized" cardiac views in the first trimester demonstrate good diagnostic efficacy for CHD，particularly when 3VT or 4CV are affected，warranting heightened clinical vigilance for fetal cardiac anomalies.

Objective:To explore the diagnostic value of first-trimester and mid-trimester ultrasound in screening fetal pentalogy of Cantrell, and to analyze missed and misdiagnosed cases.Methods:The fetal ultrasound image characteristics of pentalogy of Cantrell diagnosed in the Affiliated Suzhou Hospital of Nanjing Medical University from March 2018 to November 2022 were retrospectively analyzed. The necessary sections and key features of ultrasound images for diagnosing the disease in first-trimester and mid-trimester were summarized. The diagnostic value of ultrasound screenings in first-trimester and mid-trimester was analyzed, and the progression of the disease during pregnancy was understood, the missed diagnosis rate and misdiagnosis rate were calculated, and the reasons for missing diagnosis were analyzed. All fetuses were followed up to birth or induction of labor.Pentalogy of Cantrell was divided into types Ⅰ, Ⅱ, and Ⅲ according to Toyama′s research.Results:Among the 120 190 fetuses, 13 cases of pentalogy of Cantrell were diagnosed by ultrasound in first-trimester and mid-trimester. Ultrasound predominantly showed the fetal heart being malpositioned outside the chest and the fetal abdominal contents bulging outside the abdominal cavity, and the sternumal echo was partially or completely missed in some cases. All 13 cases were confirmed by follow-up, including 1 case of type Ⅱ, and 12 cases of type Ⅲ. In addition, 1 missed case of type Ⅱ pentalogy of Cantrell was followed up after birth. The correct diagnostic rates of fetal pentalogy of Cantrell using standard ultrasound sections during the first-trimester and mid-trimester were 99.9% and 100%, the sensitivity were 88.9% and 100%, the specificity were both 100%, the positive predictive values were both 100%, and the negative predictive values were 99.9% and 100%, respectively.Conclusions:First-trimester and mid-trimester ultrasound screenings have high diagnostic accuracy for pentalogy of Cantrell, and early detection and early diagnosis are of great clinical significance for the guidance of pregnancy outcomes.