This paper proposes a novel approach for segmenting fetal ultrasound images. This problem presents a variety of challenges including high noise, low contrast, and other US imaging properties such as similarity between texture and gray levels of two organs/ tissues. In this paper, we have proposed a Conditional Random Field (CRF) based framework to handle challenges in segmenting fetal ultrasound images. Clinically, it is known that fetus is surrounded by specific maternal tissues, amniotic fluid and placenta. We exploit this context information using CRFs for segmenting the fetal images accurately. The proposed CRF framework uses wavelet based texture features for representing the ultrasound image and Support Vector Machines (SVM) for initial label prediction. Initial results on a limited dataset of real world ultrasound images of fetus are promising. Results show that proposed method could handle the noise and similarity between fetus and its surroundings in ultrasound images.
Clinical decision support systems augment the quality of medical care by aiding healthcare workers in the evaluation and management of complicated cases. Clinical decision support systems are especially instrumental in quickly assessing the criticality of pregnancy as it involves interpreting multiple maternal and fetal parameters. We propose a machine learning approach for early determination of the risk category of pregnancy based on patterns gleaned from profiles of known clinical parameters. In particular, we demonstrate the usefulness of classification and regression trees in solving multivariate problems in obstetric care since the decision making process and the importance of specific parameters are clearly illustrated in the tree. As proof of concept, an application use case has been presented.
Objectives: The purpose of this study is to assess the feasibility of foetal nasal bone (NB) measurement during the first trimester of pregnancy, and to examine the contribution of this measurement to the prenatal screening for Down syndrome following the definition of NB threshold using ROC curves in an unselected population. Methods: This prospective study was carried out at our centre SIHCUS-CMCO (reference centre) from January 2002 to December 2004 on a total of 2,044 pregnant outpatients at gestational weeks 11–14. Only 1260 singleton foetuses were used for statistical analysis. In the 784 other patients, we were unable to obtain a correct image allowing a reproducible measurement. NB was measured during the same session as nuchal translucency (NT) measurement. Ten trained sonographers took part in the study. Correlation index was evaluated to shed light on a link between interest variables and NB. Screening values of NB measurement in T 21 were also calculated with NB measurement according to crown-rump length, and expressed as the best threshold of multiple of the median determined by ROC curve. Screening values of genetic ultrasound were then evaluated by adding NB measurement to maternal age and NT measurement. Results: Two thousand and forty-four patients were included. We indexed 30 cases of T 21, 14 cases of Trisomy 18, 10 cases of Trisomy 13 and 25 cases of other karyotype abnormalities. Feasibility of measurement was 62% of all cases. We observed a significant relation between NB and NT (p = 0.001 ), as well as between NB and crown-rump-length (p < 0.0001 ). However, size of NB was not correlated to maternal ethnic group (p = 0.314). At 0.6 multiple of the median thresholds, screening values of NB measurement in T 21 were: sensibility 32%, false positive rate 10%, positive predictive value 13.6%, and negative predictive value 96.9%. The likelihood ratio for T 21 in case of NB ≤ 0.6 multiple of the median was 4.4 (2.0–9.4). Screening values for maternal age and NT measurement were: sensitivity 88%, false positive rate 23%,positive predictive value 9.7%, and negative predictive value 99.6%. Inclusion of NB measurement increased sensitivity to 100%, positive predictive value to 13.6%, and negative predictive value to 100%, and decreased false positive rate to 5%. Conclusion: NB measurement seemed to be a great sonographic marker for T 21. However, its low feasibility made it inadequate for routine settings in first trimester T 21 screening in an unselected population. Statistical independence with NT thickness needed to be further evaluated.
Background: Advances in prenatal diagnosis make it possible to detect many fetal pathologies for which a termination of pregnancy (TOP) is possible in France. In pregnancies which go beyond 3 months, the use of prostaglandins combined with mifepristone has simplified this procedure. Since mifepristone must be taken 48 h before using prostaglandins, we have used only misoprostol intravaginally. Methods: Our report deals with a continuous series of terminated pregnancies in the second and third trimesters. The time period in question is January 1, 1996 through July 31, 2001. When this treatment was used within the first 30 weeks of gestation, four tablets (800 µg) of misoprostol were administered intravaginally. When there were no contractions, two additional tablets (400 µg) of misoprostol were given orally every 3 h, not exceeding 3 times. Beyond 30 weeks of amenorrhoea, because of the risk of uterine rupture, the initial dose was lower: 1/4 tablet (50 µg) of misoprostol intravaginally was increased to 100 µg (1/2 tablet) every 3 h until expulsion. Results: In the second and third trimesters, 55 pregnancies were terminated medically; only 1 case was not successful. In the other 54 cases, the average time interval between administering misoprostol intravaginally and expulsion was 12.7 ± 8 h. Side effects included nausea or vomiting for 12 patients (22%) and hyperthermia for 11 patients (20%). Thirty-three patients (60%) had no side effects at all. In 10 cases (18%), the fetus and the placenta were removed in one movement. In 11 cases (20%), the placenta had to be removed by artificial means. In 7 cases (13%), a curettage with a curette foam was done. In the long run perspective, only 1 patient needed a curettage to remove placental residue. Conclusion: Treatment by misoprostol without mifepristone during the second and third trimesters makes it possible to terminate a pregnancy easily and quickly without significant complications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.