RESUMO
Background: Fetal ductal constriction (DC) is associated with excessive polyphenol-rich food (PRF) consumption during pregnancy. However, the effect of this hemodynamic change on fetal cardiac function still needs to be elucidated. Therefore, this study aimed to evaluate the cardiac function of fetuses with PRF-related DC and to describe serial observations of cardiac function changes. Methods: We compared the traditional echocardiographic indices, including morphological, hemodynamic, and functional parameters, between study fetuses and controls. For global and segmental deformation analysis of the left and right ventricles, fetalHQ with the speckle-tracking technique was used to calculate sphericity index (SI), global longitudinal strain (GLS), fractional shortening (FS), fractional area change (FAC), etc. In addition, follow-up data were compared with the generalized linear model. Results: A total of 60 DC fetuses and 60 gestational-matched controls were enrolled in our study, with 20 DC fetuses undertaking a follow-up echocardiogram after 2-3 weeks. Compared with controls, there was a distinct decrease in right ventricular GLS (RVGLS) (-13.39 ± 3.77 vs. -21.59 ± 2.51, p < 0.001), RVFAC (22.20 ± 9.56 vs. 36.01 ± 4.84, p < 0.001), left ventricular GLS (LVGLS) (-19.52 ± 3.24 vs. -23.81 ± 2.01 p < 0.001), and LVFAC (39.64 ± 7.32 vs. 44.89 ± 4.91, p = 0.004). For 24-segment FS analysis, DC fetuses showed lower FS in left ventricular (LV) segments 18-24, with no difference in LV segments 1-17. Right ventricular (RV) FS in segments 4-23 was also reduced in the DC group. The 24-segment SI analysis indicated significantly lower SI in DC than those in controls for LV segments 1-14 and RV segments 19-24. We found that the pulsatility index (PI) of ductus arteriosus (DA) was an independent variable for RVGLS (ß = -0.29, p = 0.04). In 20 DC fetuses with follow-up echocardiograms, no obvious difference in myocardial deformation was found between the initial examination and follow-up data. Conclusion: Left and right ventricular performances were both impaired in DC fetuses, along with a series of morphological and hemodynamic changes. Although the state of DA constriction improved on second examinations, cardiac function was not completely restored.
RESUMO
The outbreak of COVID-19 around the world has caused great pressure to the health care system, and many efforts have been devoted to artificial intelligence (AI)-based analysis of CT and chest X-ray images to help alleviate the shortage of radiologists and improve the diagnosis efficiency. However, only a few works focus on AI-based lung ultrasound (LUS) analysis in spite of its significant role in COVID-19. In this work, we aim to propose a novel method for severity assessment of COVID-19 patients from LUS and clinical information. Great challenges exist regarding the heterogeneous data, multi-modality information, and highly nonlinear mapping. To overcome these challenges, we first propose a dual-level supervised multiple instance learning module (DSA-MIL) to effectively combine the zone-level representations into patient-level representations. Then a novel modality alignment contrastive learning module (MA-CLR) is presented to combine representations of the two modalities, LUS and clinical information, by matching the two spaces while keeping the discriminative features. To train the nonlinear mapping, a staged representation transfer (SRT) strategy is introduced to maximumly leverage the semantic and discriminative information from the training data. We trained the model with LUS data of 233 patients, and validated it with 80 patients. Our method can effectively combine the two modalities and achieve accuracy of 75.0% for 4-level patient severity assessment, and 87.5% for the binary severe/non-severe identification. Besides, our method also provides interpretation of the severity assessment by grading each of the lung zone (with accuracy of 85.28%) and identifying the pathological patterns of each lung zone. Our method has a great potential in real clinical practice for COVID-19 patients, especially for pregnant women and children, in aspects of progress monitoring, prognosis stratification, and patient management.