Objective:To investigate the value of the five-sectional screening method of the central nervous system（CNS）in early detection of fetal CNS abnormalities during the first trimester.Methods:The data of pregnant women who underwent nuchal translucency（NT）screening at the Affiliated Suzhou Hospital of Nanjing Medical University from September 2018 to September 2023 were retrospectively analyzed. And a five-sectional screening method of CNS was performed in all fetuses at the meantime. The five-sectional screening protocol in the first trimester consists of the mid-sagittal plane of the fetal head，trans-ventricular plane，trans-thalamus plane，axial plane of the fetal head at the posterior fossa level，and the sagittal plane of the fetal spine. All fetuses underwent ultrasound screening during the second trimester and the third trimester sequentially after NT screening. All the ultrasound findings were tracked，and all fetuses were followed up until delivery or after induction. Fetuses with CNS abnormalities found or suspected in the first trimester were reviewed by at least one senior physician，and follow-up examinations were routinely performed after 2 weeks to further confirm the diagnosis or find other abnormalities that may be present.Results:A total of 13 679 fetuses were screened，included 11 415 singleton pregnancies and 1 132 twin pregnancies. Among them，there were 289 cases of missed follow-up and unexplained fetal death，included 263 singleton pregnancies and 13 twin pregnancies. A total of 13 390 fetuses were finally included，among which，35 cases developed CNS abnormalities with 34 cases detected by prenatal ultrasound and 1 case of closed spina bifida missed in prenatal diagnosis，and the detection rate of CNS malformation by prenatal ultrasound was 97.14%（34/35）. Of the 35 fetuses with CNS abnormalities，24 were detected by the CNS five-sectional screening method in the first trimester，with a sensitivity of 68.57%，a specificity of 100%，a positive predictive value of 100%，and a negative predictive value of 99.92%. Among them，there were 2 cases of anencephaly，3 cases of exencephaly and 6 cases of encephalocele were all detected in the first trimester. In addition，6 cases of holoprosencephaly，3 cases of severe ventriculomegaly，2 cases of open spina bifida，and 2 cases of Dandy-Walker malformation were detected in the first trimester. In this study，1 case of agenesis of corpus callosum（ACC），1 case of arachnoid cyst，1 case of lissencephaly，1 case of schizencephaly，and 1 case of mega cisterna magna were not detected in early pregnancy.Conclusions:The fetal five-sectional screening method of CNS in the first trimester has high specificity，positive predictive value and negative predictive value for the detection of fetal CNS abnormalities，but the sensitivity is moderate. The five-sectional screening method for CNS in early pregnancy may be an effective method for early detection of fetal CNS abnormalities.

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 investigate the value of the five-sectional screening method of the central nervous system（CNS）in early detection of fetal CNS abnormalities during the first trimester.Methods:The data of pregnant women who underwent nuchal translucency（NT）screening at the Affiliated Suzhou Hospital of Nanjing Medical University from September 2018 to September 2023 were retrospectively analyzed. And a five-sectional screening method of CNS was performed in all fetuses at the meantime. The five-sectional screening protocol in the first trimester consists of the mid-sagittal plane of the fetal head，trans-ventricular plane，trans-thalamus plane，axial plane of the fetal head at the posterior fossa level，and the sagittal plane of the fetal spine. All fetuses underwent ultrasound screening during the second trimester and the third trimester sequentially after NT screening. All the ultrasound findings were tracked，and all fetuses were followed up until delivery or after induction. Fetuses with CNS abnormalities found or suspected in the first trimester were reviewed by at least one senior physician，and follow-up examinations were routinely performed after 2 weeks to further confirm the diagnosis or find other abnormalities that may be present.Results:A total of 13 679 fetuses were screened，included 11 415 singleton pregnancies and 1 132 twin pregnancies. Among them，there were 289 cases of missed follow-up and unexplained fetal death，included 263 singleton pregnancies and 13 twin pregnancies. A total of 13 390 fetuses were finally included，among which，35 cases developed CNS abnormalities with 34 cases detected by prenatal ultrasound and 1 case of closed spina bifida missed in prenatal diagnosis，and the detection rate of CNS malformation by prenatal ultrasound was 97.14%（34/35）. Of the 35 fetuses with CNS abnormalities，24 were detected by the CNS five-sectional screening method in the first trimester，with a sensitivity of 68.57%，a specificity of 100%，a positive predictive value of 100%，and a negative predictive value of 99.92%. Among them，there were 2 cases of anencephaly，3 cases of exencephaly and 6 cases of encephalocele were all detected in the first trimester. In addition，6 cases of holoprosencephaly，3 cases of severe ventriculomegaly，2 cases of open spina bifida，and 2 cases of Dandy-Walker malformation were detected in the first trimester. In this study，1 case of agenesis of corpus callosum（ACC），1 case of arachnoid cyst，1 case of lissencephaly，1 case of schizencephaly，and 1 case of mega cisterna magna were not detected in early pregnancy.Conclusions:The fetal five-sectional screening method of CNS in the first trimester has high specificity，positive predictive value and negative predictive value for the detection of fetal CNS abnormalities，but the sensitivity is moderate. The five-sectional screening method for CNS in early pregnancy may be an effective method for early detection of fetal CNS abnormalities.

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.

Objective:To establish reference ranges of central nervous system-related fetal intracranial markers during the first trimester in a local population of Suzhou.Methods:Ultrasound images of fetuses with normal birth outcomes in singleton pregnancies who underwent nuchal translucency(NT) screening during the first trimester (11-13 + 6 gestational weeks) from January 2021 to July 2022 at the Affiliated Suzhou Hospital of Nanjing Medical University were retrospectively selected. The images including 3 planes: the midsagittal plane of the fetal head, also known as the plane for NT measurement, the trans-ventricular plane of the fetal head, and the axial plane of the fetal head at the posterior fossa level. The brainstem (BS) thickness, brainstem to occipital bone distance (BSOB), the ratio of BS to BSOB (BS/BSOB), intracranial translucency (IT) thickness, cisterna magna (CM) width, and the midbrain (MB) to falx (F) ratio MB/F were measured in the mid-sagittal plane of the fetal head. Choroid plexus length (CPL) to occipital frontal diameter (OFD) ratio CPL/OFD, and choroid plexus area (CPA) to head area (HA) ratio CPA/HA were measured in the trans-ventricular plane of the fetal head. Anteroposterior diameter of the fourth ventricle (4V) and CM were measured in the axial plane of the fetal head at the posterior fossa level.Statistical analysis was performed to obtain the corresponding normal reference range.Intra-class correlation coefficient (ICC) was used to analyze intra-observer and inter-observer consistency. Pearson correlation analysis and linear correlation analysis were used to study the correlations between crown-lump length (CRL) and intracranial markers, and the regression equation was derived. Results:A total of 2 331 fetuses were enrolled, providing 1 023 images of the midsagittal plane, 817 images of the trans-ventricular plane, and 567 images of the axial plane of the fetal head at the posterior fossa level. The intra-observer and inter-observer ICCs of intracranial markers BS, BSOB, BS/BSOB, IT thickness, CM width, MB/F in the mid-sagittal plane, the intracranial markers CPL/OFD, CPA/HA on the trans-ventricular plane, and the intracranial markers 4V and CM width in the axial plane at the posterior fossa level were all >0.75. Fetal intracranial markers were linearly correlated with CRL. The midsagittal plane: BS, BSOB, BS/BSOB, IT thickness, CM width, MB/F were linearly correlated with CRL ( r=0.508, 0.626, -0.234, 0.105, 0.508, -0.493; all P<0.05); the trans-ventricular plane: CPL/OFD, CPA/HA were linearly correlated with CRL( r=-0.324, -0.268; all P<0.001); the axial plane of the fetal head at the posterior fossa level: 4V, CM width were linearly correlated with CRL ( r=0.246, 0.467; all P<0.001). Conclusions:Quantitative analysis of fetal intracranial markers in the first trimester is feasible. This study constructed a normal reference range of multiple intracranial markers related to central nervous system in the first trimester with a local population of Suzhou. And the construction of this normal range can provide an objective basis for the detection of fetal central nervous system malformations in the first trimester.

Objective:To explore the relationship between soft markers found in the first trimester (11-13 + 6 gestational weeks) ultrasound screening and fetal adverse pregnancy outcomes. Methods:Single pregnancy fetuses were selected from the Multicenter Clinical Study of First Trimester Screening in China during August 2017 to August 2020. The types and detection rate of soft markers during the first trimester were compared. The correlation between positive soft markers and adverse pregnancy outcomes was analyzed by binary Logistics regression.Results:A total of 16 625 fetuses with complete follow-up outcomes were included in the group. Six hundred and seven ultrasonic soft markers were detected in 556 fetuses with positive soft markers during the first trimester, and the first four most frequently occurred were increased nuchal translucency (NT) (2.08%, 345/16 625), echogenic intracardiac focus (EIF) (0.94%, 156/16 625), hypoplasia of fetal nasal bone (0.20%, 34/16 625), single umbilical artery (SUA) (0.19%, 31/16 625). Among 556 fetuses, the incidence of adverse pregnancy outcome in fetuses with two or more positive soft markers was 32.50% (13/40), which was significantly higher than fetuses with single positive soft marker (11.05%, 57/516), and the difference was statistically significant (χ 2=5.055, P<0.001). The incidence of adverse pregnancy outcome in positive soft markers fetus associated with structural abnormalities was 80.77% (21/26), which was significantly higher than fetuses with isolated positive soft marker (12.08%, 64/530), and the difference was statistically significant (χ 2=90.310, P<0.001). Binary logistic regression analysis showed choroid plexus cyst (CPC), SUA, echogenic bowel (EB), absent/reversed a-wave of ductus venosus, hypoplasia of fetal nasal bone, increased NT, and EIF were closely related to the adverse pregnancy outcomes (all P<0.05). However, there were no significant correlations between tricuspid regurgitation (TR), pyelectasis (PYE) and fetal adverse pregnancy outcomes (all P>0.05). Conclusions:The ultrasonic soft markers during the first trimester are of great significance in predicting fetal adverse pregnancy outcomes. For multiple positive soft markers or positive soft markers combined with structural abnormalities, more attention should be paid to them and comprehensive evaluation is required to be carried out.

Objective:To explore the clinical value of prenatal ultrasound in diagnosis of fetal cleft lip and palate during first-trimester (11-13 + 6 gestational weeks). Methods:Ultrasonographic images were retrospectively selected from those fetuses who underwent first trimester scanning during July 2017 to June 2020 in the Affiliated Suzhou Hospital of Nanjing Medical University. Fetal facial mid-sagittal section and the retronasal triangle (RNT) section were combined together to evaluate whether the fetuses had cleft lip and palate (CLP) or not. All fetuses were followed up to birth or induced abortion.Results:A total of 5 520 fetuses were enrolled, with crown-rump length (CRL) between 45-84 mm. Seven cases of different types of CLP were detected by the 2 combined sections, including 4 cases with unilateral CLP, 1 case with median CLP, and 2 cases with bilateral CLP, which were confirmed by follow-up. In addition, 2 cases of isolated cleft lip (CL) were missed.Conclusions:Combination of fetal facial mid-sagittal section and RNT section is useful for the early diagnosis of fetal cleft lip and palate during first-trimester scanning.