Search

This study presents an automatic method for estimating antenatal amniotic fluid (AF) volume from two-dimensional ultrasound (US) images, which is an important indicator of fetal well-being. This automatic estimation of AF volume (AFV) requires automated segmentation of the AF pocket, which is a challenging task due to its amorphous features and US artifacts, such as reverberation, shadowing, particle noise, and signal dropout. Recently, AF-net, a deep-learning method, has been shown to successfully perform AF pocket segmentation. However, we observed that AF-net is prone to misjudging AF pockets containing severe reverberation artifacts. The proposed method addresses this problem by developing a dual path network, which consists of AF-net as the primary path and an auxiliary network as the secondary path. The auxiliary network is designed to focus on the local area that is likely to be contaminated with the reverberation artifacts. It infers this local region and generates a feature map of the artifacts, incorporating it as prior information into a deep neural network, denoted as RVB-net, for segmenting the reverberation-artifact-contaminated AF region. Finally, the segmentation output from the auxiliary network complements the AF-net. Experimental results show that the proposed dual path network effectively reduces misjudgment of the AF pocket caused by severe reverberation artifacts. The proposed dual path network achieved an average Dice similarity coefficient (DSC) of 0.8599 ± 0.1074 (mean ± standard deviation) for AF pocket segmentation on the entire evaluation set.

Previous studies demonstrated an association between cervical strain and risk of spontaneous preterm delivery (sPTD). The present study aimed to assess the efficacy of elastography in predicting sPTD at &lt, 32 weeks of gestation in women with singleton pregnancies receiving progesterone for short cervix (≤2.5 cm) diagnosed between 16 and 28 weeks of gestation Among 115 participants eligible for analysis, nine had sPTD at &lt, 32 weeks. Preprogesterone (PP0) mean internal os strain (IOS), elasticity contrast index (ECI), hardness ratio (HR), one-week postprogesterone (PP1) IOS, mean external os strain (EOS), ECI, and HR were significantly different between groups. Higher PP0 IOS, PP1 IOS, and PP1 EOS were associated with a 2.92, 4.39 and 3.65-fold increase in the risk of sPTD at &lt, 32 weeks, respectively (adjusted for cervical length (CL) at diagnosis, p = 0.04, 0.012 and 0.026, respectively). A combination of CL at diagnosis, PP0 IOS and PP1 EOS showed a significantly higher area under the receiver operating characteristic curve (0.858) than that of CL alone (p = 0.041). In women with singleton pregnancies receiving progesterone for short cervix, cervical elastography performed before and one week after progesterone treatment may be useful in predicting sPTD at &lt, 32 weeks of gestation.

Given that systems based on artificial intelligence (AI) technologies now match or surpass human levels, more firms are adopting these technologies to gain a competitive advantage. However, the lit...

Purpose The purpose of this paper is to examine how clarity of corporate social responsibility (CSR) orientation of Japanese small and medium enterprises (SMEs) achieves constructive firm performance outcomes. Design/methodology/approach On the basis of the literature review, the authors present a research model that defines key constructs and provide propositions that explain the interrelationships with theoretical rationale and practical implications. Using careful selection criteria, the authors have further conducted the in-depth interviews of the executives of two prominent Japanese SMEs. Findings The results suggest that CEOs with strong CSR orientation are more likely to influence their firms to achieve effective firm performance. If CSR philosophy is strategically formulated, clearly communicated, and widely accepted, then such firm is more likely to attain desirable business performance outcomes for larger stakeholders. Furthermore, CSR implementation of SMEs is not necessarily too costly; in fact, the long-term rate of return on SMEs’ CSR investment, with proper priority and prudent focus, is quite competitive. Research limitations/implications In spite of the specificity of the two case studies, the research model and the study findings give valuable insight on the role of CEO’s philosophy on CSR implementation in the international market. The linkage mechanism between business operation and CSR by these SMEs is applicable to many innovative entrepreneurial firms that target beyond domestic markets. Originality/value The authors highlight how the clarity of CSR philosophy in terms of firm orientation and linkage mechanism aids SMEs in overcoming their resource constraints. Furthermore, well-implemented CSR activities may become instrumental in achieving long-term desirable performance in the form of customer loyalty, employee’s sense of pride, and corporate socio-economic reputation.

Preeclampsia is one of the leading causes of maternal and fetal morbidity and mortality. Due to the lack of effective preventive measures, its prediction is essential to its prompt management. This study aimed to develop models using machine learning to predict late-onset preeclampsia using hospital electronic medical record data. The performance of the machine learning based models and models using conventional statistical methods were also compared. A total of 11,006 pregnant women who received antenatal care at Yonsei University Hospital were included. Maternal data were retrieved from electronic medical records during the early second trimester to 34 weeks. The prediction outcome was late-onset preeclampsia occurrence after 34 weeks' gestation. Pattern recognition and cluster analysis were used to select the parameters included in the prediction models. Logistic regression, decision tree model, naive Bayes classification, support vector machine, random forest algorithm, and stochastic gradient boosting method were used to construct the prediction models. C-statistics was used to assess the performance of each model. The overall preeclampsia development rate was 4.7% (474 patients). Systolic blood pressure, serum blood urea nitrogen and creatinine levels, platelet counts, serum potassium level, white blood cell count, serum calcium level, and urinary protein were the most influential variables included in the prediction models. C-statistics for the decision tree model, naive Bayes classification, support vector machine, random forest algorithm, stochastic gradient boosting method, and logistic regression models were 0.857, 0.776, 0.573, 0.894, 0.924, and 0.806, respectively. The stochastic gradient boosting model had the best prediction performance with an accuracy and false positive rate of 0.973 and 0.009, respectively. The combined use of maternal factors and common antenatal laboratory data of the early second trimester through early third trimester could effectively predict late-onset preeclampsia using machine learning algorithms. Future prospective studies are needed to verify the clinical applicability algorithms.

The estimation of antenatal amniotic fluid (AF) volume (AFV) is important as it offers crucial information about fetal development, fetal well-being, and perinatal prognosis. However, AFV measurement is cumbersome and patient specific. Moreover, it is heavily sonographer-dependent, with measurement accuracy varying greatly depending on the sonographer's experience. Therefore, the development of accurate, robust, and adoptable methods to evaluate AFV is highly desirable. In this regard, automation is expected to reduce user-based variability and workload of sonographers. However, automating AFV measurement is very challenging, because accurate detection of AF pockets is difficult owing to various confusing factors, such as reverberation artifact, AF mimicking region and floating matter. Furthermore, AF pocket exhibits an unspecified variety of shapes and sizes, and ultrasound images often show missing or incomplete structural boundaries. To overcome the abovementioned difficulties, we develop a hierarchical deep-learning-based method, which consider clinicians' anatomical-knowledge-based approaches. The key step is the segmentation of the AF pocket using our proposed deep learning network, AF-net. AF-net is a variation of U-net combined with three complementary concepts - atrous convolution, multi-scale side-input layer, and side-output layer. The experimental results demonstrate that the proposed method provides a measurement of the amniotic fluid index (AFI) that is as robust and precise as the results from clinicians. The proposed method achieved a Dice similarity of 0.877±0.086 for AF segmentation and achieved a mean absolute error of 2.666±2.986 and mean relative error of 0.018±0.023 for AFI value. To the best of our knowledge, our method, for the first time, provides an automated measurement of AFI.

Objective: Staphylococcal scalded skin syndrome (SSSS) is a relatively rare superficial blistering skin disease caused by exfoliating toxins produced by Staphylococcus aureus. We experienced a 3-month outbreak of neonatal SSSS in a maternal unit. Methods: The medical records of newborns who were diagnosed with SSSS were retrospectively reviewed. Results: Eleven newborns with SSSS were transferred to our hospital between January and March 2019. The median age of the newborns was 18.0 (11.0-22.5) days. Of the 11 newborns, 2 (18%) showed the generalized type of SSSS, 4 (36%) the intermediate type, and 5 (45%) the abortive type. S. aureus was isolated in 10 of the newborns and found to be methicillin-resistant in 9 cases. All the newborns were treated with intravenous cefazolin, and two newborns with the generalized type were also treated with clindamycin. The median duration of antibiotic use is 8 (6-14) days. All the newborns responded well to antibiotics and were discharged without complications. Conclusion: We recently experienced an outbreak of neonatal SSSS. To manage problems associated with such an outbreak, periodic monitoring is required, along with guidelines for infection control, such as thorough infection education, isolation of infected newborns, and antiseptic handwashing.

Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD), are commonly used to evaluate the gestational age and diagnose fetal central nervous system (CNS) pathology. Since manual measurements are operator-dependent and time-consuming, there have been numerous researches on automated methods. However, existing automated methods still are not satisfactory in terms of accuracy and reliability, owing to difficulties in dealing with various artifacts in ultrasound images. This paper focuses on fetal head biometry and develops a deep-learning-based method for estimating HC and BPD with a high degree of accuracy and reliability. The proposed method effectively identifies the head boundary by differentiating tissue image patterns with respect to the ultrasound propagation direction. The proposed method was trained with 102 labeled data set and tested to 70 ultrasound images. We achieved a success rate of 92.31% for HC and BPD estimations, and an accuracy of 87.14 % for the plane acceptance check.

Objective In this study, we evaluated the prevalence of allergic disease in offsprings delivered via the delivery modes of vaginal delivery vs. planned Cesarean section vs. Cesarean section with labor. Methods This study included 175 mother-neonate pairs from Severance Hospital who were enrolled in the Cohort for Childhood Origin of Asthma and allergic diseases study. Information regarding prenatal environmental factors, delivery, and diagnosis of allergic diseases was obtained from a questionnaire and medical record review. Patients with at least 3 years of follow-up data were included in this study. Results were adjusted for sex, birth weight, gestational age at birth, season of birth, neonatal intensive care unit admission, parity, breastfeeding, and maternal factors. Results A total of 175 offsprings were eligible for analysis. Among the subjects, 52.0% were delivered by vaginal delivery, 34.3% by planned Cesarean section, and 16.6% by Cesarean section with labor. Fifty-nine offsprings (33.7%) were diagnosed with allergic disease at a median age of 1 year (range 0.5-3 years). The prevalence of allergic disease was not associated with delivery mode after adjusting for confounding variables. Time period from membrane rupture to delivery, duration of the active phase, and the beginning of the pelvic division prior to Cesarean section were not associated with allergic disease development in offsprings. Conclusion Cesarean section, irrespective of the occurrence of labor before surgery, did not increase the prevalence of allergic disease in infants up to 3 years of age.

Problem The lymphatic vasculature controls leukocytes trafficking and limits the adaptive immune response. In previous models of preeclampsia (PE), defective immune function caused by disruption of lymphangiogenesis was shown to be involved in the disease pathophysiology. Especially, the dysfunction of regulatory T cells (Treg) at the maternal-fetal interface may be one of the causes of severe PE. In particular, activation of Tregs to obtain immune tolerance requires adequate antigen presentation through the lymphatic system. We hypothesized that impaired lymphangiogenesis and imbalanced Tregs at the maternal-fetal interface are associated with the pathophysiology of severe PE. However, the current research addressing this hypothesis is limited. Therefore, to compare differences in lymphangiogenesis in severe PE and normal conditions, we aimed to examine the location of lymphatics at the maternal-fetal interface and to investigate the association between lymphangiogenesis and Tregs in severe PE. Method of study We obtained entire uterus from normal pregnant mice. Placental and fetal membranes, including decidua, were obtained from 10 pregnant women with severe PE and 10 gestational age-matched controls. Immunohistochemistry for LYVE1 was used to localize the distribution of lymphatic vessels and CD4, CD25, and FOXP3 for Treg. Results LYVE1-positive vessels were present in the uterine wall of mice. LYVE1-positive lymphatic vessels were localized on the human decidua. Tubular lymphatics were abundant in the control decidua, but significantly reduced in severe PE. Furthermore, lymphatic vessel density correlated with the number of decidual Tregs. Conclusion Abnormal decidual lymphangiogenesis is associated with reduced numbers of decidual Tregs in severe PE.

Background Multiple studies have been reported regarding preeclampsia as a possible risk factor of cerebrovascular disease (CVD). However, the correlation of preeclampsia and CVD, whether it is a cause-effect relationship or they are sharing common predisposing condition, is not well understood. Therefore, the aim of this study was to investigate the association between the preeclampsia during pregnancy and development of postpartum CVD. Methods A total of 1,384,550 Korean women who had a delivery between January 1, 2010 and December 31, 2012, were enrolled. Women with the risk of CVD within 1 year prior to pregnancy were excluded based on the Charlson comorbidity index. Primary endpoint was the event of CVD within a year from delivery. After exclusion, 1,075,061 women were analyzed. Results During the follow-up of 1 year postpartum, there were 25,577 preeclampsia out of 1,072,041 women without postpartum CVD (2.39%), and 121 of 3,020 women with postpartum CVD had preeclampsia before delivery (4.01%). In multivariate logistic regression analysis, women who had preeclampsia during pregnancy showed a higher risk for postpartum CVD (odds ratio, 1.64; 95% confidence interval, 1.37–1.98). Conclusion The incidence of CVD after delivery was higher in women who had preeclampsia during pregnancy., Graphical Abstract

Ultrasound diagnosis is routinely used in obstetrics and gynecology for fetal biometry, and owing to its time-consuming process, there has been a great demand for automatic estimation. However, the automated analysis of ultrasound images is complicated because they are patient specific, operator dependent, and machine specific. Among various types of fetal biometry, the accurate estimation of abdominal circumference (AC) is especially difficult to perform automatically because the abdomen has low contrast against surroundings, nonuniform contrast, and irregular shape compared to other parameters. We propose a method for the automatic estimation of the fetal AC from two-dimensional ultrasound data through a specially designed convolutional neural network (CNN), which takes account of doctors' decision process, anatomical structure, and the characteristics of the ultrasound image. The proposed method uses CNN to classify ultrasound images (stomach bubble, amniotic fluid, and umbilical vein) and Hough transformation for measuring AC. We test the proposed method using clinical ultrasound data acquired from 56 pregnant women. Experimental results show that, with relatively small training samples, the proposed CNN provides sufficient classification results for AC estimation through the Hough transformation. The proposed method automatically estimates AC from ultrasound images. The method is quantitatively evaluated and shows stable performance in most cases and even for ultrasound images deteriorated by shadowing artifacts. As a result of experiments for our acceptance check, the accuracies are 0.809 and 0.771 with expert 1 and expert 2, respectively, whereas the accuracy between the two experts is 0.905. However, for cases of oversized fetus, when the amniotic fluid is not observed or the abdominal area is distorted, it could not correctly estimate AC.

Objective: Obstetricians mainly use ultrasound imaging for fetal biometric measurements. However, such measurements are cumbersome. Hence, there is urgent need for automatic biometric estimation. Automated analysis of ultrasound images is complicated owing to the patient-specific, operator-dependent, and machine-specific characteristics of such images. Approach: This paper proposes a method for the automatic fetal biometry estimation from 2D ultrasound data through several processes consisting of a specially designed convolutional neural network (CNN) and U-Net for each process. These machine learning techniques take clinicians' decisions, anatomical structures, and the characteristics of ultrasound images into account. The proposed method is divided into three steps: initial abdominal circumference (AC) estimation, AC measurement, and plane acceptance checking. Main results: A CNN is used to classify ultrasound images (stomach bubble, amniotic fluid, and umbilical vein), and a Hough transform is used to obtain an initial estimate of the AC. These data are applied to other CNNs to estimate the spine position and bone regions. Then, the obtained information is used to determine the final AC. After determining the AC, a U-Net and a classification CNN are used to check whether the image is suitable for AC measurement. Finally, the efficacy of the proposed method is validated by clinical data. Significance: Our method achieved a Dice similarity metric of for AC measurement and an accuracy of 87.10% for our acceptance check of the fetal abdominal standard plane.

Neuroblastoma is the most common pediatric extracranial solid tumor derived from primitive neural crest cells of the sympathetic nervous system. Although one-fifths of all neuroblastomas occurs within the thorax, thoracic neuroblastomas detected in fetus have been rarely reported. We report a case of fetal thoracic neuroblastoma with massive pleural effusion detected with prenatal ultrasonography. A 34-year-old Korean second-gravida was referred to our hospital at 30 weeks of gestation for evaluation, after the right lung mass found in the fetus. Approximately 3 cm, well-defined, hyperechoic mass was found in the right thorax with right pleural effusion, with the initial suspicion of teratoma. However, as mass continued to grow with deteriorating pleural effusion and fetal hydrops, the mass was considered malignant after 3 weeks. After a cesarean delivery, an approximately 4 cm mass with peripheral calcification and hemothorax was found on neonatal ultrasonography. Neuroblastoma was diagnosed on excision biopsy.

Objective Nephrin is one of the slit membrane proteins of podocytes in the kidney. It is known that the nephrin is shed in the urine in nephropathy accompanying proteinuira. So the aim of this study was to evaluate the difference in the serum nephrin expression between normal and preeclamptic pregnancies. Methods A total of 20 pregnant women from May to September 2008 who received prenatal care and underwent delivery at our institute participated in the study. The preeclamptic group includes 13 women diagnosed as preeclampsia and a normal group of 7. Their serum were collected before delivery and analyzed by Western blotting for comparing serum nephrin expression. Results There was no difference in age, body weight of pregnant women, blood urea nitrogen, serum creatinine, urine creatinine level and gestational age between two groups. However, preeclampsia group had significantly higher systolic and diastolic blood pressure ( P