Multimodal Early Birth Weight Prediction Using Multiple Kernel Learning.

In this work, a novel multimodal learning approach for early prediction of birth weight is presented. Fetal weight is one of the most relevant indicators in the assessment of fetal health status. The aim is to predict early birth weight using multimodal maternal-fetal variables from the first trimester of gestation (Anthropometric data, as well as metrics obtained from Fetal Biometry, Doppler and Maternal Ultrasound). The proposed methodology starts with the optimal selection of a subset of multimodal features using an ensemble-based approach of feature selectors. Subsequently, the selected variables feed the nonparametric Multiple Kernel Learning regression algorithm. At this stage, a set of kernels is selected and weighted to maximize performance in birth weight prediction. The proposed methodology is validated and compared with other computational learning algorithms reported in the state of the art. The obtained results (absolute error of 234 g) suggest that the proposed methodology can be useful as a tool for the early evaluation and monitoring of fetal health status through indicators such as birth weight.

Characterization of systolic and diastolic pressure time series in pregnant women with preeclampsia through symbolic dynamics.

Preeclampsia (PE) is one of the leading causes of maternal mortality worldwide. Although clinical strategies to prevent the early onset of PE have been proposed, the ultimate solution is to end the pregnancy. Therefore, patients' identification with major PE risk is important towards the prevention and better management of a severe manifestation of the illness. This study aims to analyze the systolic blood pressure (SBP) and diastolic blood pressure (DBP) time series through a nonlinear perspective using symbolic dynamics and to incorporate a multi-scale assessment in the first trimester of pregnancy, previous to the clinical manifestation of PE. The study group of normotensive women who developed and were diagnosed with PE included 14 pregnant women, a normotensive throughout pregnancy control group (N) consisting of 14 participants, and a group of 14 normotensive women during pregnancy without comorbidities (S) were matched with PE by age, body mass index, gestational age and comorbidities. The preliminary results of this study showed a decreased complexity of SBP, assessed by multiscale symbolic entropy in the first trimester in PE patients, in comparison with normotensive pregnant women.Clinical relevance- This work shows how nonlinear analysis of systolic and diastolic blood pressure time series are useful to detect preeclampsia in the first trimester of pregnancy.

The sFlt-1/PlGF ratio as a triage tool to identify superimposed preeclampsia in women with chronic hypertension in emergency rooms.

OBJECTIVES: Assess the usefulness of the sFlt-1/PlGF ratio for the differential diagnosis of uncontrolled chronic hypertension vs. superimposed preeclampsia. STUDY DESIGN: We performed a cross-sectional study from 2015 to 2017 and 42 women with initial diagnosis of superimposed preeclampsia were enrolled in the emergency room. After a 12 week follow up patients were grouped as superimposed preeclampsia (Group A) and uncontrolled chronic hypertension (Group B) according to the American College of Obstetricians and Gynecologist criteria. A group of 33 healthy women paired by gestational age were included as controls (Group C). Maternal serum levels of sFlt-1 and PlGF were measured at enrollment, and the ratios of the groups were compared. MAIN OUTCOME MEASURES: Superimposed preeclampsia vs. uncontrolled chronic hypertension. RESULTS: After follow-up, group distribution was 30 women in Group A, 12 women in Group B, and 25 women in Group C. The sFlt-1/PlGF ratio was higher in women with superimposed preeclampsia than in women with uncontrolled chronic hypertension (215.5 vs. 9.65, p < 0.001). The control group displayed lower ratio values (3.66, p < 0.001). The sFlt-1 concentration was higher in Group A than in Group B (7564 vs. 1281 pg/mL, p < 0.001) and the PlGF level was lower in Group A (34.39 vs. 169 pg/mL, p < 0.001). CONCLUSIONS: The sFlt-1/PlGF ratio exhibits good performance for the differential diagnosis of superimposed preeclampsia vs. uncontrolled chronic hypertension.

Placental Microarray Profiling Reveals Common mRNA and lncRNA Expression Patterns in Preeclampsia and Intrauterine Growth Restriction.

Preeclampsia (PE) and Intrauterine Growth Restriction (IUGR) are major contributors to perinatal morbidity and mortality. These pregnancy disorders are associated with placental dysfunction and share similar pathophysiological features. The aim of this study was to compare the placental gene expression profiles including mRNA and lncRNAs from pregnant women from four study groups: PE, IUGR, PE-IUGR, and normal pregnancy (NP). Gene expression microarray analysis was performed on placental tissue obtained at delivery and results were validated using RTq-PCR. Differential gene expression analysis revealed that the largest transcript variation was observed in the IUGR samples compared to NP (n = 461; 314 mRNAs: 252 up-regulated and 62 down-regulated; 133 lncRNAs: 36 up-regulated and 98 down-regulated). We also detected a group of differentially expressed transcripts shared between the PE and IUGR samples compared to NP (n = 39), including 9 lncRNAs with a high correlation degree (p < 0.05). Functional enrichment of these shared transcripts showed that cytokine signaling pathways, protein modification, and regulation of JAK-STAT cascade are over-represented in both placental ischemic diseases. These findings contribute to the molecular characterization of placental ischemia showing common epigenetic regulation implicated in the pathophysiology of PE and IUGR.

Left ventricle segmentation in fetal echocardiography using a multi-texture active appearance model based on the steered Hermite transform.

OBJECTIVE: Fetal echocardiographic analysis is essential for detecting cardiac defects at early gestational ages. Fetal cardiac function can be assessed by performing some measurements regarding the dimension and shape of the heart cavities. In this work we propose an automatic segmentation method applied to the analysis of the left ventricle in fetal echocardiography. METHODS: For segmentation of the left ventricle, we designed a novel multi-texture active appearance model (AAM) based on the Hermite transform (HT). Local orientation analysis is addressed by steering the coefficients obtained with the HT. The method basically consists of an AAM-based scheme which uses the steered HT to efficiently code texture patterns of the input image. A wider and detailed description of the image features can be obtained with this method. Compared with classic AAM methods, the segmentation performance is substantially improved with the proposed scheme. Since AAM-based approaches process local information, an automatic method is also proposed to initialize the multi-texture AAM. For this purpose, a database of pre-segmented images was built. Then, techniques such as thresholding, mathematical morphology and correlation are combined to identify the position and orientation of the left ventricle. Typical issues found in fetal cardiac ultrasound images such as different orientations and shape variations of the heart cavities can be easily handled with the designed method. RESULTS: Several images of fetal echocardiography were used to evaluate the proposed segmentation method. The algorithm performance was validated using different metrics. We used a database of 143 real images of fetal hearts acquired for different phases of the cardiac cycle. We obtained an average Dice coefficient of 0.8631 and a point-to-curve distance of 2.027 pixels. The proposed algorithm was also validated by comparing it with other segmentation methods. CONCLUSIONS: We have designed an automatic algorithm for left ventricle segmentation in fetal echocardiography. The reported results demonstrate that the proposed approach can achieve an efficient segmentation of the left ventricular cavity. Typical problems found in images of fetal echocardiography are satisfactorily handled with the proposed multi-texture AAM scheme.

Amniotic band sequence: prenatal diagnosis, phenotype descriptions, and a proposal of a new classification based on morphologic findings.

OBJECTIVE: The aim of this study is to describe the phenotype of fetuses affected by amniotic band sequence (ABS) that were diagnosed at the Instituto Nacional de Perinatología Isidro Espinosa de los Reyes and to propose a new classification based on morphologic findings. MATERIAL AND METHODS: Cases with a final diagnosis of amniotic band sequence, diagnosed between January 1993 and July 2010 in the Department of Maternal Fetal Medicine, were reviewed. Demographic, clinical, and periconceptional data were collected, and the defects were described and classified. The association frequencies of the defects were also determined. RESULTS: We included 50 cases with prenatal diagnosis of amniotic band sequence. The mean maternal age was 25.7 ± 6.9 years. Of these patients, 54% (27/50) were primiparous compared to 22% (11/50) who had three or more previous pregnancies. Craniofacial defects were seen in 78% (39/50) of the cases, followed by defects of the extremities 70% (35/50), abdominal wall, spine, and/or thorax 52% (26/50). The most frequent defects were the following: a) Encephalocele and facial clefts in the craniofacial group. b) Shortening at any level in the limb defects group, and c) Alterations of the spinal column curvature in the group of "other" defects. CONCLUSIONS: The amniotic band sequence shows a tendency to affect women who are in their earlier years of reproduction. We observed an inverse relationship between the number of pregnancies and the frequency of presentation of this pathology. The majority of affected fetuses showed a phenotype that fit into one of many groups. Therefore, we propose classifying the amniotic band sequence phenotypes into the following groups: I. Craniofacial defect + limb defect. II. Craniofacial defect + limb defect + abdominal wall, spinal column, and/or thoracic defects. III. Limb defect + abdominal wall, spinal column, and/or thoracic defects; and IV. Isolated defect (craniofacial, limb, or thoraco-abdominal wall). This classification system will be helpful in diagnosing amniotic band sequence. Based on future research studies, we hope that we can use this classification system as a prognosis fetal factor to establish a more accurate fetal prognosis and recurrence probability. Finally, we created a flowchart describing all of the steps that were followed by our Department from the moment an amniotic band was found by ultrasound until the definitive diagnosis was made and the follow up according to the fetal findings.

Association between selected structural defects and chromosomal abnormalities.

OBJECTIVE: To determine the association between some major structural abnormalities detected prenatally by ultrasound and chromosomal abnormalities. MATERIAL AND METHODS: The present study was a retrolective, transversal study. We analyzed case records of patients during the fetal follow-up at the Department of Maternal Fetal Medicine from January 1994 to May 2010 to identify fetal patients with a diagnosis of holoprosencephaly, diaphragmatic hernia, omphalocele, cystic hygroma, hydrops and cardiac defects. We analyzed patients who had a prenatal invasive diagnosis procedure to obtain the odds ratio (OR) for some major isolated anomalies and their different combinations with respect to chromosomal abnormalities. RESULTS: We examined 280 patients with ultrasonographic markers for chromosomal alteration, 197 met inclusion criteria, from which 88 had chromosomal abnormalities. The most frequent diagnosis was trisomy 18 (31.8%), which was followed by trisomy 21 (21.6%), trisomy 13 (21.6%), Turner syndrome (monosomy X) (14.8%) and other chromosomal abnormalities (10.2%). Among the fetuses with nonisolated holoprosencephaly, we obtained an OR of 4.9 95% CI (0.99-24.2) for aneuploidy. Associated omphalocele had an OR of 7.63 95% CI (2.07-46.75), p < 0.01. Interestingly, 62% of aneuploidy cases had associated cardiac defects [OR = 7.7 95% CI (1.4-41.7)]. In addition, associated cystic hygroma had an OR of 2.5 95% CI (0.59-10.91). Heart defects were the most common defects in fetuses with trisomy 18 (57.1%), when they were associated with facial cleft, we had an OR of 11.08 95% CI (2.99-41.11), p < 0.0001. Statistical potency was calculated for each analyzed defect and it was over 80% for all of them but diaphragmatic hernia. CONCLUSIONS: The association of 2 or more structural defects increased the probability of a fetus to be a carrier of a chromosomal disorder; however this was not statistically significative except for associated omphalocele. Heart defects showed the greatest association with all chromosomal abnormalities. The most important association was among heart defect, facial cleft and trisomy 13.

Automatic segmentation of the fetal cerebellum on ultrasound volumes, using a 3D statistical shape model.

Previous work has shown that the segmentation of anatomical structures on 3D ultrasound data sets provides an important tool for the assessment of the fetal health. In this work, we present an algorithm based on a 3D statistical shape model to segment the fetal cerebellum on 3D ultrasound volumes. This model is adjusted using an ad hoc objective function which is in turn optimized using the Nelder-Mead simplex algorithm. Our algorithm was tested on ultrasound volumes of the fetal brain taken from 20 pregnant women, between 18 and 24 gestational weeks. An intraclass correlation coefficient of 0.8528 and a mean Dice coefficient of 0.8 between cerebellar volumes measured using manual techniques and the volumes calculated using our algorithm were obtained. As far as we know, this is the first effort to automatically segment fetal intracranial structures on 3D ultrasound data.

Prenatal prevalence of skeletal dysplasias and a proposal ultrasonographic diagnosis approach.

OBJECTIVE: To determine the prevalence of fetal bone dysplasias diagnosed at the Department of Maternal Fetal Medicine (UNIMEF) of the Instituto Nacional de Perinatologia (INPer); and to describe the most frequent skeletal dysplasias and to propose a diagnostic flow chart. MATERIALS AND METHODS: This is a case series study including skeletal dysplasias cases from January 1995 until December 2009 at the UNIMEF Statistical analysis was performed using SPSS 12 statistical software. RESULTS: A total of 81,892 births were registered at the institution during the study period. The prevalence of bone dysplasia was 8.1 per 10,000 births. We used a diagnostic flow chart that was developed at our institution to diagnose skeletal dysplasias. Micromelia (n = 40, 59.7%) and both rhizomelia and mesomelia (n = 17, 25.3%) were highly prevalent. We found other structural anomalies in 40 cases (61.1%), which were associated with different skeletal dysplasias; these other anomalies were mainly congenital heart diseases (12 cases) with a predominance of ventricular septal defects. There was polyhydramnios in 43.2% of cases. The mean of the gestational age at diagnosis was 24.5 weeks (SD 5.66). The karyotype was obtained in 11.9% (8/67) of cases. A total of 7 stillbirths and 11 neonatal deaths were registered, of which only 10 cases received a necropsy. Births occurred in the third trimester for 88% of cases, of which 85% were born via Cesarean section, whereas in the second trimester, the vaginal approach was chosen in 100% of cases. CONCLUSIONS: The prenatal diagnosis of bone dysplasias is challenging due to the late development of the diagnostic features. Nevertheless, using ultrasonography in a systematic approach, in conjunction with a multidisciplinary approach, is a key factor in the diagnosis of this disease during the fetal period.

Major craniofacial defects: case series and prenatal diagnosis at the Instituto Nacional de Perinatología, Mexico.

OBJECTIVE: To describe the prenatal diagnosis, characteristics, development, perinatal outcome, and final diagnosis of pregnancies complicated by fetuses with major craniofacial defects, at the Instituto Nacional de Perinatologia, México, 1997-2008. MATERIAL AND METHODS: A retrospective, descriptive study from January of 1997 to January 2008, analyzed 152 pregnancies complicated by fetuses with major craniofacial defects, diagnosed at the Department of Fetal Medicine of the National Institute of Perinatology. Data were obtained from patients clinical records. RESULTS: . The mean age was 28 +/- 8 years, with the largest number of cases between 20 and 24. The mean gestational age at diagnosis was 27.5 +/- 6.4 gestational weeks. The average termination of pregnancy was at 35 +/- 5 gestational weeks. In 43.4% of cases there were no major structural defects associated with the facial defect. The most commonly associated structural alterations were cerebral, cardiac, and limb abnormalities. Karyotyping was performed in only 57 cases, and was abnormal in 25. CONCLUSIONS: Structural ultrasound should be performed on all pregnant women between weeks 18 and 24 for detection of major craniofacial defects. Where defects are found, a thorough review of other structures should be carried out to determine whether the defects are syndromic. A systematic and multidisciplinary approach is essential to providing the best care and appropriate advice to parents.

Accuracy of different equations for estimating fetal weight.

OBJECTIVE: To evaluate the accuracy of ten equations based on ultrasound parameters for estimating fetal weight (FW). STUDY DESIGN: A cross-sectional study was performed in 250 healthy women with normal singleton pregnancies between 34 and 41 weeks of gestation. FW estimations calculated according to ten different equations were compared against birth weight (BW) which was determined within 72 h after FW estimation. Estimated error rate, intraclass correlation coefficient, and agreement between BW and FW calculated by each formula were analyzed. RESULTS: Most of the formulas were inaccurate in predicting BW, only 2 formulas showed less than 10% of the measurements lying within the 10% of estimated error. Four formulas tended to overestimate, while six tended to underestimate FW. CONCLUSIONS: Appropriate equations for estimating FW in all populations should be developed. However, where there are no local growth curves, the accuracy of the available fetal growth equations should be tested.

Iniencefalia: un raro defecto del Sistema Nervioso Central / Iniencephaly: a central nervus system abnormalities

De un total de 10 261 valoraciones obstétricas realizadas por ultrasonido, en el período comprendido entre enero 1993-diciembre 1995, se diagnosticaron en etapa prenatal tres casos de iniencefalia, con seguimiento perinatal, calculándose una frecuencia para esta infrecuente y letal malformación del tubo neural del 1/3 420. La edad promedio fue de 24 años y el común denominador fue la baja paridad, el 100 por ciento de los productos afectos cursaron con polihidramnios y eran de sexo femenino, con cariotipo normal. Se presentó un 66 por ciento de anomalías estructurales asociadas, destacándose un caso de agenesia suprarrenal

Descarte prenatal de la distrofia muscular de Duchenne / Prenatal discard of the Duchenne muscular dystrophy

El diagnóstico prenatal de la distrofia muscular de Duchenne, es factible mediante biopsia muscular a partir del segundo trimestre del embarazo, analizando las fibras musculares por medio de microscopía de luz, electrónica, pruebas histoenzimáticas y sondas del DNA. Esta entidad constituye la más común y severa de las miopatías de la infancia, afectando 1 varón de cada 3 500 nacidos, de herencia recesiva y ligada al sexo, caracterizada por ausencia de la distrofina, proteína que se localiza en el sarcolema del músculo esquelético. Describimos a continuación un caso en el cual se hizo descarte prenatal de la patología descrita y se hacen planteamientos sobre el manejo perinatal.

Displasia tanatofórica: diagnóstico y manejo perinatal / Thanatophoric dysplasia: diagnostic and perinatal management

Las displasias esqueléticas se ubican como prioridad en el área del diagnóstico prenatal. El presente estudio muestra dos casos de displasia tanatofórica diagnosticados en la Unidad de Perinatología del Hospital Universitario de Caracas. Se evalúan hallazgos ecográficos y se hacen consideraciones referentes a su etiología y manejo perinatal.

Manejo perinatal del higroma quístico / Perinatal management of cystic higroma

El higroma quístico constituye una malformación congénita del sistema linfático. La incidencia global es de 1,7x10.000 nacimientos. Se presentan dos casos diagnosticados entre enero y agosto de 1993. Se resalta la importancia de la determinación del cariotipo, evaluación ecográfica seriada y vigilancia del desarrollo o no de hidrops fetalis.