As technologic advances of ultrasound with high resolution, the importance and accuracy of identifying fetal structural abnormalities in first trimester has increased. We aimed to develop an artificial intelligence system called ViewAssist™ that automatically identifies and classifies the fetal structures in the first trimester and to evaluate its performance. Ultrasound images of over 8,000 first trimester fetuses were prospectively collected from Seoul St. Mary's Hospital, Eunpyeong St. Mary's Hospital, Uijeongbu St. Mary's Hospital, and Buchoen St. Mary's Hospital. The collected images were classified by anatomical areas including head, face, neck, chest, heart, abdomen, extremities, and spine, according to the International Society of Ultrasound in Obstetrics and Gynecology guideline. For effective classification of the anatomical areas, we used the Vision Transformer architecture and pre-processed the data by augmenting images while maintaining the aspect ratio. We randomly selected images from the original data, with 90% for the training set and 10% for the validation set. During the deep learning training stage, we used 100 epochs, with a batch size of 64 and a learning rate of 0.0005. We adjusted the hyperparameters at each epoch to minimise the loss function. The classification accuracy of the anatomical areas using ViewAssist™ was 96.75% overall, with the following category-specific accuracy: 100% for head, 98.9% for face, 93.8% for neck, 85.7% for chest, 100% for heart, 94.5% for abdomen, 97.5% for extremities, and 96.2% for spine. Through deep learning algorithms, ViewAssist™ was able to accurately classify the structures of first trimester fetuses. It is expected to be clinically useful in assisting with identifying fetal structures and diagnosing structural abnormalities in the first trimester.

A uniform endometrium was recorded in 572/1055 polyp cases (54.2%). In those with a non-uniform endometrium, 136/483 (28.2%) had regular, and 41/483 (8.5%) irregular cystic areas and 183 (37.9%) had a heterogeneous endometrial echogenicity. Cystic areas were present in 254/480 (52.9%) polyps of postmenopausal as opposed to 29/575 (5%) in premenopausal patients. Flow was detectable in 890 cases (84%): 527 (59.2%) had a single dominant vessel without branching and 78 (8.8%) with branching, 55 (6.2%) cases had multiple dominant vessels of unifocal and multifocal origin in 23/55 and 32/55 respectively, and 29 (3.3%) of polyps presented with scattered vessels. Conclusions: Endometrial polyps are common in women without abnormal bleeding undergoing an ultrasound scan for reasons unrelated with bleeding problems. The majority had visible vascularisation on colour Doppler imaging.

Background and PurposeAlthough studies have evaluated the relationship between intravitreal bevacizumab (IVB) injection and cerebral infarction (CI), the effects of IVB on CI are still not clear. The aim of this study was to investigate the effects of IVB injection on patients with CI with age‐related macular degeneration (AMD).MethodsWe retrospectively reviewed patients with AMD who received IVB injections for 1 year and determined the incidence of CI within 60 days after IVB injection to analyze the possible association between IVB and CI.ResultsA total of 263 patients were enrolled over a 12‐month period. Six patients (2.28%) were diagnosed with CI within 2 months after receiving an IVB injection. The incidence of CI in patients of 75–84 years of age was 6.38%. These results showed a higher incidence for patients with IVB injections than the results of previous epidemiological studies (0.13% for all age groups, 1.68% for patients of 75–84 years of age). All CIs occurred 21–53 days after the IVB injection (mean: 39.33 ± 14.65 days). Logistic regression analyses showed that age and CI history were factors associated with CI.ConclusionsTreatment with IVB might be an independent risk factor for CI. These results are useful for planning treatment strategies for patients with AMD and for prevention of CI.

Cervical length (CL) is a potential screening tool to predict preterm delivery for high risk women. Also it can be used for prediction of spontaneous labour or successful induction of labour. The objection of this presentation was to assess association between CL and previous vaginal delivery. Prospective observational cohort study was conducted from Jul. 2015 to Dec. 2015 at tertiary hospital. We measured CL at 18- 22 weeks, 22-26 weeks, 30-32 weeks and 36-37 weeks for all pregnant women who visited our hospital for antenatal care. Pregnant women with multifetal pregnancy, cerclage during pregnancy, fetal death in uterus and preterm delivery were excluded. Student t test was conducted between history of previous delivery and cervical length at each gestational week. We included 489 pregnant women and their records of CL. At 18-22 weeks of gestation, there was no significant association between previous vaginal delivery and CL. At 22-26 weeks of gestation, women with previous vaginal delivery (N = 316) had a shorter CL compared with women without previous vaginal delivery (N=159). (mean CL in women with previous vaginal delivery 34.7 ± 5.8 mm, women without previous vaginal delivery (N= 159), 36.1 ± 6.5 mm, P = 0.03). At 30-32 and 36-37 weeks of gestation, previous vaginal delivery was significantly associated with shorter CL than no history of vaginal delivery (P= 0.043 and 0.002, respectively). Maternal height, body mass index, birthweight, and gestational week at delivery were not associated with history of vaginal delivery. CL at 22-26 weeks and at 30 -32 weeks and 36-37 weeks are significantly associated with previous vaginal delivery. When we measure and use CL as a predictor for preterm or term labour, history of vaginal delivery should considered.

To evaluate whether the serial cervical length measured by transvaginal ultrasound between 26∼30 weeks and 35∼36 weeks of gestation is predictive of spontaneous early onset of labour in women with history of previous Caesarean section (CS). This study was designed as a retrospective observational study on 223 women with history of previous Caesarean section. The cervical length was measured ultrasonographically at 26–30 weeks and 35–36 weeks of gestation. Of the 223 pregnancies enrolled, 80 (35.9%) developed spontaneous onset of labour before 39 weeks of gestation. The cervical length at 35∼36weeks of gestations was significantly shorter in these women when compared with those delivering after 39 weeks of gestation (24 vs. 31 mm P<0.0001). Serial cervical length between 26∼30 weeks and 35∼36weeks of gestations was significantly larger in early spontaneous labour onset groups (0.89 vs. 0.35mm. p=0.004). Also, the birthweight was significantly lower in early spontaneous labour onset groups (3106 vs 3386g p <0.0001) Multivariate logistic regression analysis showed that cervical length (adjusted odds ratio(aOR) 5.85; 95% confidence interval (CI) 2.696-12.695; P≤0.0001) at 35∼36weeks and birthweight (aOR 1.003(95% CI 1.001-1.004, p<0.0001)were predictors for the onset of labour before 39 weeks of gestation. The area under the receiver-operating characteristics curve for the prediction of early onset of labour was 0.847 (95% CI 0.738-0.950) for cervical length and birthweight as test variable. Cervical length at 35-36 weeks of gestation and birthweights provides information about the likelihood of onset of labour before 39 weeks of gestations in women with history of previous CS and may be useful in individualising the gestational age for elective CS.

Uterine rupture during pregnancy is a life threatening condition. Spontaneous rupture in the second trimester is a very rare condition. Here we report a case of uterine rupture at 24-weeks pregnancy with a history of single-port laparoscopic myomectomy 3 year before. A 30 year old pregnant women was referred with acute abdominal pain and an amniotic fluid leaquage. The sonographic finding showed the oligohydramnios and 10 cm sized large anechoic cystic mass in posterior cul de sac, which is connected with gestational sac. The operative findings revealed a uterine rupture at the site of the previous myomectomy scar and a huge amniocele was expelled out from the ruptured myometirum. Classical incision was done in uterus and live baby was delivered. The incisised and ruptured sites were repaired in two layers. Laparoscopic myomectomy has advantage over laparotomy but the possibility of uterine rupture in following pregnancies should not be underestimated. This complication raises the problem of the quality of uterine repair following single-port laparoscopic myomectomy.

Fetal supraventricular tachycardia is the most common form of fetal tachycardia. When it causes signs of hemodynamic compromise, fetal distress, or hydrops fetalis, immediate medical therapy should be undertaken. Digoxin is often used as first-line therapy but can be ineffective and is poorly transferred to the fetus in the presence of fetal hydrops. In this case, an additional antiarrhythmic drug should be tried. A 27 year old women was transferred to our hospital for fetal supraventricular tachycardia at 25 weeks of gestation. Fetal cardiac sonography revealed supraventricular tachycardia with heart rate of 230–250 bpm and fetal hydrops. Despite digoxin, fetal tachycardia was persistent. So the combination therapy of transplacental sotalol and flecainide was done. Conversion to sinus rhythm was followed this treatment and the hydroptic sign gradually disappeared without any significant sequelae. For fetus with fetal tachycardia combined with hydrops, a combination therapy of sotalol and flecainide is effective and tolerable treatment.

Peritoneal trophoblastic implants have been known as a possible complication after treatment of tubal ectopic pregnancy. However, trophoblastic implant associated with dilatation and curettage is extremely rare. We present a case of trophoblastic implants at multiple peritoneal sites after dilatation and curettage, which was treated by surgical excision of the implants. A 39-year old woman was referred to our clinic presenting with amenorrhea for 4 months and elevated serum beta-hCG level after dilatation and curettage for missed abortion. The Ultrasound and MRI examinations showed hyper-vascularized nodule measuring 20 mm located within the myometrium of uterine fundus. Although HCG level was decreased to 23.7 mIU/ml, 3 weeks later, because the size of uterine mass was not decreased and the patient complained of a left abdominal discomfort, a diagnostic laparoscopy was performed. The operative finding showed that 2 cm sized of mass protruding from the fundal uterine wall and multiple small bluish mass of 5-10mm on the Left ovary, left pelvic wall and, vesicouterine peritoneal fold. The dissected masses showed necrotizing chorionic villi with normal trophoblastic lining. The postoperative course was uncomplicated, and 12 days after surgery, serum beta-hCG was normalized. This case underlines the importance of assessing serum beta-hCG level after dilatation and curettage. Persistent beta-hCG level after termination of pregnancy associated with a high vascularized lesion in the uterine wall may suggest the possibility of this disease entity.

This study was carried out to construct the reference equations and charts of fetal biometry in the Korean population and to identify ethnic differences by comparing them with those in other populations A prospective cross sectional study was performed with 986 fetuses from 15 to 40 weeks of pregnancy. All the fetuses were randomly allocated only once for the sake of this study in their own gestational ages, and the following fetal biometric variables were measured: biparietal diameter (BPD), head circumference (HC), abdominal circumference (AC), femur, tibia, fibular, humerus, ulnar and radio length. Maternal conditions affecting fetal growth and fetal malformations were excluded. For each measurement, regression models were fitted to estimate the mean and standard deviation at each gestational age. Our centiles were compared with results from other population using Z-scores. New charts and reference equations for Korean population were reported for all the fetal biometric variables. Most of the parameters in these charts were similar to those in charts for an Italian population. Also, in comparison with North American and UK populations, the BPD, HC, and AC in the first half of pregnancy were greater in Korean fetuses, but smaller in Korean fetuses later in pregnancy as the growth rate decrease with gestation. We developed reference equations and charts of fetal biometry for Korean using a recommended methodology. The size and growth in fetal biometry seem to be influenced by ethnicity.

Supporting information can be found in the online version of this abstract Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.

This study was performed to construct reference charts for fetal biometry in Korea, and to compare fetal long bone length of Korea with other countries in gestation This was a prospective observational study involving 296 single pregnant women at a gestational age of between 20 and 28 weeks gestation. All the gestation was confirmed according to last menstrual period and fetal crown-rump length measurement in the first trimester. No fetuses were excluded on the basis of abnormal biometry or birth weight. For the purposes of this study, each woman was scanned once only, and the following fetal biometric measurements were recorded: biparietal diameter, head circumference, abdominal circumference, and the lengths of long bones. For each measurement, regression models were fitted to estimate the mean and SD at each gestational age. We compared our reference equation with other populations at each gestation. Results were presented graphically across the different gestational ages to allow visual comparison. New charts and reference equations for Korean population were reported for fetal biparietal diameter, head circumference, abdominal circumference and long bone length. The notable differences in our fetal biometric measurements compared with those of the European populations were not found. We presented a new set of reference charts for fetal biometric measurements and equations for dating of pregnancy in a Korean population. This suggested the fetal biometry including long bone appeared to be similar to other European population.

To establish the relationship between three-dimensional cervical volume and the risk of spontaneous preterm birth, and to determine the possible role of measuring the cervical volume in predicting preterm birth. A prospective study was conducted involving 391 asymptomatic women with singleton pregnancies without a known risk for preterm birth. Two-dimensional cervical length measurement and three-dimensional cervical volume measurement were done at 20–24 weeks of gestation. We assessed the relationship between cervical factors and the risk for spontaneous preterm delivery before 36 weeks of gestation. At 20–24 weeks of gestation, the mean cervical length was 36.9 ± 7.9 mm and the mean cervical volume was 40.1 ± 13.5 cm3. Logistic regression analysis demonstrated that not only cervical length (odds ratio [OR], 0.94; 95% confidence interval [CI], 0.88–0.99, P = 0.002), but also cervical volume (OR, 0.26; 95% CI, 0.11–0.61, P = 0.045) was independent predictors of preterm birth. A combined approach in which a gravida was regarded as positive with a short cervical length (28 mm) or a small cervical volume (20 cubic cm) had a sensitivity of 57.1% for preterm birth before 36 weeks of gestation. Three-dimensional cervical volume at 20–24 weeks of gestation is an independent factor inversely proportional to the risk for preterm birth before 36 weeks of gestation in asymptomatic gravidas at low-risk for preterm labor. Screening combining cervical length and cervical volume may provide a better prediction of spontaneous preterm birth. Supporting information can be found in the online version of this abstract. Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.

Placenta increta is associated with maternal morbidity including gravid hysterectomy, massive transfusion, infection, and prolonged hospitalization. Diagnosis of placenta increta with antenatal high-resolution ultrasound facilitates to prepare the preoperative plans and to counsel with the patient. A 38-year-old woman, gravid 3, para 1 with a prior Cesarean delivery was referred at 32 weeks of gestation because of antepartum hemorrhage. The placenta was anterior, covering internal os totally. The placental-myometrial interface was disrupted over its entire surface. There were focal disruptions of hyperechoic bladder mucosa, diffuse lacunar flow by color Doppler and vessels crossing the interface-disruption sites. At 37 gestational weeks, the elective operation performed with transverse Cesarean incision over the edge of placental implantation, during which the placenta was bulging out from the uterine wall in the previous Cesarean scar. We operated the partial uterine excision of the placental implantation site soon after removal of placenta and primary repair. The total blood loss was 1200ml at the procedure and the diagnosis was confirmed histologically. The postnatal course was uneventful. To date a scheduled Cesarean hysterectomy is ideal to optimize maternal outcomes in suspected placenta increta. In recent years, numerous conservative managements have attempted using selective arterial embolization, adjuvant methotrexate, hypogastric artery ligation, and delayed definitive surgery for retained placenta which was left in situ after delivery. However, those procedures are associated with the complications including pelvic infection, methotrexate adverse effects, vascular thrombosis, and ischemic phenomenon. In this case, we could assess the location and the extent of the myometrial involvement on color Doppler and gray-scale ultrasound imaging. Therefore, we successfully managed placenta increta using the partial excision.