A deep learning approach to identify the fetal head position using transperineal ultrasound during labor.

OBJECTIVES: To develop a deep learning (DL)-model using convolutional neural networks (CNN) to automatically identify the fetal head position at transperineal ultrasound in the second stage of labor. MATERIAL AND METHODS: Prospective, multicenter study including singleton, term, cephalic pregnancies in the second stage of labor. We assessed the fetal head position using transabdominal ultrasound and subsequently, obtained an image of the fetal head on the axial plane using transperineal ultrasound and labeled it according to the transabdominal ultrasound findings. The ultrasound images were randomly allocated into the three datasets containing a similar proportion of images of each subtype of fetal head position (occiput anterior, posterior, right and left transverse): the training dataset included 70 %, the validation dataset 15 %, and the testing dataset 15 % of the acquired images. The pre-trained ResNet18 model was employed as a foundational framework for feature extraction and classification. CNN1 was trained to differentiate between occiput anterior (OA) and non-OA positions, CNN2 classified fetal head malpositions into occiput posterior (OP) or occiput transverse (OT) position, and CNN3 classified the remaining images as right or left OT. The DL-model was constructed using three convolutional neural networks (CNN) working simultaneously for the classification of fetal head positions. The performance of the algorithm was evaluated in terms of accuracy, sensitivity, specificity, F1-score and Cohen's kappa. RESULTS: Between February 2018 and May 2023, 2154 transperineal images were included from eligible participants across 16 collaborating centers. The overall performance of the model for the classification of the fetal head position in the axial plane at transperineal ultrasound was excellent, with an of 94.5 % (95 % CI 92.0--97.0), a sensitivity of 95.6 % (95 % CI 96.8-100.0), a specificity of 91.2 % (95 % CI 87.3-95.1), a F1-score of 0.92 and a Cohen's kappa of 0.90. The best performance was achieved by the CNN1 - OA position vs fetal head malpositions - with an accuracy of 98.3 % (95 % CI 96.9-99.7), followed by CNN2 - OP vs OT positions - with an accuracy of 93.9 % (95 % CI 89.6-98.2), and finally, CNN3 - right vs left OT position - with an accuracy of 91.3 % (95 % CI 83.5-99.1). CONCLUSIONS: We have developed a DL-model capable of assessing fetal head position using transperineal ultrasound during the second stage of labor with an excellent overall accuracy. Future studies should validate our DL model using larger datasets and real-time patients before introducing it into routine clinical practice.

Relationship between hypertensive disorders of pregnancy (HDP) and cardiac remodeling during pregnancy: Systematic review and meta-analysis.

OBJECTIVES: Hypertensive disorders of pregnancy (HDP) are among the leading causes of maternal morbidity and mortality. The primary objective of this study was to ascertain whether maternal cardiac remodeling is more prevalent in HDP than normotensive pregnancy and if significant change in aortic root size is involved. The secondary objective was to determine the types of cardiac remodeling often associated with HDP. METHODS: A systematic search was conducted across four electronic databases, including Medline, PubMed, Cochrane and EMBASE. The reference lists of selected articles were also searched to ensure no relevant studies were missed. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines were followed in this systematic review. RESULTS: Out of 5,278 articles identified by the search terms, 9 were eligible for inclusion in the meta-analysis. The investigation unveiled a greater prevalence of maternal cardiac remodeling in HDP than normotensive pregnancies. The commonest type of maternal cardiac remodeling in both HDP and normotensive pregnancies was eccentric left ventricular hypertrophy, followed by concentric left ventricular remodeling which was more specific to HDP. Notably, left atrial diameter was significantly increased in HDP than normotensive pregnancies, suggesting higher prevalence of diastolic dysfunction. Additionally, the aortic root dimension was significantly increased in HDP than normotensive pregnancies. CONCLUSION: This study underscores the importance of monitoring cardiac health in pregnancy, particularly in those with hypertensive disorders, in order to mitigate potential complications and improve maternal outcomes. Finally, the risk of aortic dissection that may occur as a long-term effect of aortic root enlargement in women with history of HDP ought to be investigated in future studies.

Sonohysterography: time to step up its use in gynaecologic imaging in West Africa.

Sonohysterography is a simple, safe and convenient technique that is easily and rapidly performed in the ultrasound room; yet the technique seems to be underutilized in West Africa. We present two cases that were successfully carried out in our centre followed by detailed description, uses and challenges of the technique, with the hope of encouraging clinicians and sonographers in the sub-region to step up its use. Two women were referred for evaluation of their endometrial cavities on account of increasingly heavy menstrual bleeding. Sonohysterography revealed intracavity uterine masses with hyper-echoic focal thickening highly suggestive of endometrial polyps; histology confirmed the diagnosis of endometrial polyps. Sonohysterography is an affordable and feasible diagnostic modality for evaluating the endometrial cavity. Where equipment and skill permit, the technique should be used more often in the West African sub-region. Sonohysterography, Tansvaginal sonography, Gnaecologic imaging, West Africa.