Brain Vascular Dysfunction in Mothers and Their Children Exposed to Preeclampsia

Diffusion-Weighted MRI of the Fetal Brain in Fetal Growth Restriction With Maternal Preeclampsia or Gestational Hypertension

BACKGROUND

The fetal neurodevelopmental microstructural alterations of intrauterine exposure to preeclampsia (PE) or gestational hypertension (GH) remain unknown.

PURPOSE

To evaluate the differences in diffusion-weighted imaging (DWI) of the fetal brain between normotensive pregnancies and PE/GH pregnancies, with a focus on PE/GH pregnancies with fetal growth restriction (FGR).

STUDY TYPE

Retrospective matched case-control study.

POPULATION

40 singleton pregnancies with PE/GH complicated by FGR, and 3 paired control groups (PE/GH without FGR, normotensive FGR, normotensive pregnancies) (28-38 gestational weeks).

FIELD STRENGTH/SEQUENCE

DWI with single-shot echo-planar imaging at 1.5 Tesla.

ASSESSMENT

The apparent diffusion coefficient (ADC) values were calculated in the centrum semi-ovale (CSO), parietal white matter (PWM), frontal white matter (FWM), occipital white matter (OWM), temporal white matter (TWM), basal ganglia, thalamus (THAL), pons, and cerebellar hemisphere.

STATISTICAL TESTS

Student t test or Wilcoxon matched test was used to reveal the difference of ADC values among the investigated brain regions. A correlation between gestational age (GA) and ADC values was determined by linear regression analysis.

RESULTS

Compared with fetuses in PE/GH without FGR and those with normotensive pregnancies, fetuses in the PE/GH with FGR group had significantly lower average ADC measurements of supratentorial regions (1.65 ± 0.09 vs. 1.71 ± 0.10 10-3  mm2 /sec; vs. 1.73 ± 0.11 10-3  mm2 /sec, respectively). Regions of significantly decreased ADC values in the fetal brain included CSO, FWM, PWM, OWM, TWM and THAL in cases of PE/GH with FGR. ADC values from supratentorial regions in PE/GH pregnancies were not significantly correlated with GA (P = 0.12, 0.26); however, this trend was statistically significant in the normotensive groups.

DATA CONCLUSION

ADC values may indicate fetal brain developmental alterations in PE/GH with FGR fetuses but more microscopic and morphological studies are necessary to provide additional evidence to offer a different interpretation of this trend in fetal brain.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 3.

Prediction of preeclampsia from retinal fundus images via deep learning in singleton pregnancies: a prospective cohort study

INTRODUCTION

Early prediction of preeclampsia (PE) is of universal importance in controlling the disease process. Our study aimed to assess the feasibility of using retinal fundus images to predict preeclampsia via deep learning in singleton pregnancies.

METHODS

This prospective cohort study was conducted at Shanghai First Maternity and Infant Hospital, Tongji University School of Medicine. Eligible participants included singleton pregnancies who presented for prenatal visits before 14 weeks of gestation from September 1, 2020, to February 1, 2022. Retinal fundus images were obtained using a nonmydriatic digital retinal camera during their initial prenatal visit upon admission before 20 weeks of gestation. In addition, we generated fundus scores, which indicated the predictive value of hypertension, using a hypertension detection model. To evaluate the predictive value of the retinal fundus image-based deep learning algorithm for preeclampsia, we conducted stratified analyses and measured the area under the curve (AUC), sensitivity, and specificity. We then conducted sensitivity analyses for validation.

RESULTS

Our study analyzed a total of 1138 women, 92 pregnancies developed into hypertension disorders of pregnancy (HDP), including 26 cases of gestational hypertension and 66 cases of preeclampsia. The adjusted odds ratio (aOR) of the fundus scores was 2.582 (95% CI, 1.883-3.616; P  < 0.001). Otherwise, in the categories of prepregnancy BMI less than 28.0 and at least 28.0, the aORs were 3.073 (95%CI, 2.265-4.244; P  < 0.001) and 5.866 (95% CI, 3.292-11.531; P  < 0.001). In the categories of maternal age less than 35.0 and at least 35.0, the aORs were 2.845 (95% CI, 1.854-4.463; P  < 0.001) and 2.884 (95% CI, 1.794-4.942; P  < 0.001). The AUC of the fundus score combined with risk factors was 0.883 (sensitivity, 0.722; specificity, 0.934; 95% CI, 0.834-0.932) for predicting preeclampsia.

CONCLUSION

Our study demonstrates that the use of deep learning algorithm-based retinal fundus images offers promising predictive value for the early detection of preeclampsia.