Fetal face as important indicator of fetal brain function

Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology

Artificial intelligence (AI) has gained prominence in medical imaging, particularly in obstetrics and gynecology (OB/GYN), where ultrasound (US) is the preferred method. It is considered cost effective and easily accessible but is time consuming and hindered by the need for specialized training. To overcome these limitations, AI models have been proposed for automated plane acquisition, anatomical measurements, and pathology detection. This study aims to overview recent literature on AI applications in OB/GYN US imaging, highlighting their benefits and limitations. For the methodology, a systematic literature search was performed in the PubMed and Cochrane Library databases. Matching abstracts were screened based on the PICOS (Participants, Intervention or Exposure, Comparison, Outcome, Study type) scheme. Articles with full text copies were distributed to the sections of OB/GYN and their research topics. As a result, this review includes 189 articles published from 1994 to 2023. Among these, 148 focus on obstetrics and 41 on gynecology. AI-assisted US applications span fetal biometry, echocardiography, or neurosonography, as well as the identification of adnexal and breast masses, and assessment of the endometrium and pelvic floor. To conclude, the applications for AI-assisted US in OB/GYN are abundant, especially in the subspecialty of obstetrics. However, while most studies focus on common application fields such as fetal biometry, this review outlines emerging and still experimental fields to promote further research.

Fetal brain activity and the free energy principle

OBJECTIVES

To study whether the free energy principle can explain fetal brain activity and the existence of fetal consciousness via a chaotic dimension derived using artificial intelligence.

METHODS

In this observational study, we used a four-dimensional ultrasound technique obtained to collect images of fetal faces from pregnancies at 27-37 weeks of gestation, between February and December 2021. We developed an artificial intelligence classifier that recognizes fetal facial expressions, which are thought to relate to fetal brain activity. We then applied the classifier to video files of facial images to generate each expression category's probabilities. We calculated the chaotic dimensions from the probability lists, and we created and investigated the free energy principle's mathematical model that was assumed to be linked to the chaotic dimension. We used a Mann-Whitney test, linear regression test, and one-way analysis of variance for statistical analysis.

RESULTS

The chaotic dimension revealed that the fetus had dense and sparse states of brain activity, which fluctuated at a statistically significant level. The chaotic dimension and free energy were larger in the sparse state than in the dense state.

CONCLUSIONS

The fluctuating free energy suggests consciousness seemed to exist in the fetus after 27 weeks.

Trypanosoma cruzi dysregulates expression profile of piRNAs in primary human cardiac fibroblasts during early infection phase

Trypanosoma cruzi, the etiological agent of Chagas Disease, causes severe morbidity, mortality, and economic burden worldwide. Though originally endemic to Central and South America, globalization has led to increased parasite presence in most industrialized countries. About 40% of infected individuals will develop cardiovascular, neurological, and/or gastrointestinal pathologies. Accumulating evidence suggests that the parasite induces alterations in host gene expression profiles in order to facilitate infection and pathogenesis. The role of regulatory gene expression machinery during T. cruzi infection, particularly small noncoding RNAs, has yet to be elucidated. In this study, we aim to evaluate dysregulation of a class of sncRNAs called piRNAs during early phase of T. cruzi infection in primary human cardiac fibroblasts by RNA-Seq. We subsequently performed in silico analysis to predict piRNA-mRNA interactions. We validated the expression of these selected piRNAs and their targets during early parasite infection phase by stem loop qPCR and qPCR, respectively. We found about 26,496,863 clean reads (92.72%) which mapped to the human reference genome. During parasite challenge, 441 unique piRNAs were differentially expressed. Of these differentially expressed piRNAs, 29 were known and 412 were novel. In silico analysis showed several of these piRNAs were computationally predicted to target and potentially regulate expression of genes including SMAD2, EGR1, ICAM1, CX3CL1, and CXCR2, which have been implicated in parasite infection, pathogenesis, and various cardiomyopathies. Further evaluation of the function of these individual piRNAs in gene regulation and expression will enhance our understanding of early molecular mechanisms contributing to infection and pathogenesis. Our findings here suggest that piRNAs play important roles in infectious disease pathogenesis and can serve as potential biomarkers and therapeutic targets.

Artificial intelligence to understand fluctuation of fetal brain activity by recognizing facial expressions

OBJECTIVE

To examine whether artificial intelligence can achieve discoveries regarding fetal brain activity.

METHODS

In this observational study, the authors collected images of fetal faces using a four-dimensional ultrasound technique obtained from singleton pregnancies of outpatients in routine practice at 27 to 37 weeks of gestation between February 1 and December 31, 2021. The authors developed an artificial intelligence classifier to recognize seven facial expressions of fetuses, then applied it to video files of fetal facial images to generate the probabilities, as confidence scores, of each expression category. Discrete Fourier transform and chaotic analysis were used to investigate the scores. Mann-Whitney test, t test, variance test, and one-way analysis of variance were used for statistical analysis.

RESULTS

Facial expression changes were observed in cycles averaging 66 to 73 s. The power spectrum showed that mouthing and neutral expressions were the most prevalent. There was a difference between categories for the spectrum (p = 0.004). Two different states--dense and sparse--of confidence scores were discovered. The correlation dimension was 1.19 ± 0.22 and 1.33 ± 0.27 for dense and sparse, respectively (p = 0.047).

CONCLUSION

This method objectively and quantitatively demonstrated fetal brain activity and may provide insight into how the fetus spends its time in utero.

Fetal Pain in the First Trimester

Fetal pain perception has important implications for fetal surgery, as well as for abortion. Current neuroscientific evidence indicates the possibility of fetal pain perception during the first trimester (<14 weeks gestation). Evidence for this conclusion is based on the following findings: (1) the neural pathways for pain perception via the cortical subplate are present as early as 12 weeks gestation, and via the thalamus as early as 7–8 weeks gestation; (2) the cortex is not necessary for pain to be experienced; (3) consciousness is mediated by subcortical structures, such as the thalamus and brainstem, which begin to develop during the first trimester; (4) the neurochemicals in utero do not cause fetal unconsciousness; and (5) the use of fetal analgesia suppresses the hormonal, physiologic, and behavioral responses to pain, avoiding the potential for both short- and long-term sequelae. As the medical evidence has shifted in acknowledging fetal pain perception prior to viability, there has been a gradual change in the fetal pain debate, from disputing the existence of fetal pain to debating the significance of fetal pain. The presence of fetal pain creates tension in the practice of medicine with respect to beneficence and nonmaleficence.

Frontal tangential coronal view two-dimensional ultrasonography in assessment of fetal face [mouth and nose] in comparison with four-dimensional ultrasonography

Background

The fetal face reflects strictly the development of the fetal brain during its growth. Four-dimensional (4D) examination permits continuous monitoring of the examined parts of fetal face and surface. The final performance of obstetric sonographic images depends upon multiple factors, such as fetal lie, uterine wall, abdominal wall fat, amniotic fluid, and the number of gestations which may limit the optimum performance of (4D) ultrasound. The two-dimensional (2D) ultrasound is the first choice due to its wide availability, low cost, and real-time capabilities. The tangential view obtained by (2D) ultrasound coronal sections through the face showed the nose, nostril, lips, eye, lens, and hard palate.

Results

One hundred and sixty fetuses showed straight forwards obstetric examination by both 2D and 4D examinations with identical final reports. While the total number of fetuses with clear images by 2D frontal tangential coronal examination was 191 cases, only 29 cases failed, whereas 170 cases obtained clear images by 4D examination, and 50 cases failed. Both 2D and 4D ultrasound failed to obtain clear images of 19 cases, while 4D failed for 31 cases, and 2D failed for 10 cases. 2D imaging was found to be significantly better than 4D imaging, with a P value of 0.009.

Conclusion

2D ultrasound using the frontal tangential coronal view is an essential part of the fetal examination and more superior than 4D ultrasound in assessing facial anatomy and anomalies, as well comparable to 4D ultrasound as regards fascial expression.

Recognition of facial expression of fetuses by artificial intelligence (AI)

OBJECTIVES

The development of the artificial intelligence (AI) classifier to recognize fetal facial expressions that are considered as being related to the brain development of fetuses as a retrospective, non-interventional pilot study.

METHODS

Images of fetal faces with sonography obtained from outpatient pregnant women with a singleton fetus were enrolled in routine conventional practice from 19 to 38 weeks of gestation from January 1, 2020, to September 30, 2020, with completely de-identified data. The images were classified into seven categories, such as eye blinking, mouthing, face without any expression, scowling, smiling, tongue expulsion, and yawning. The category in which the number of fetuses was less than 10 was eliminated before preparation. Next, we created a deep learning AI classifier with the data. Statistical values such as accuracy for the test dataset and the AI confidence score profiles for each category per image for all data were obtained.

RESULTS

The number of fetuses/images in the rated categories were 14/147, 23/302, 33/320, 8/55, and 10/72 for eye blinking, mouthing, face without any expression, scowling, and yawning, respectively. The accuracy of the AI fetal facial expression for the entire test data set was 0.985. The accuracy/sensitivity/specificity values were 0.996/0.993/1.000, 0.992/0.986/1.000, 0.985/1.000/0.979, 0.996/0.888/1.000, and 1.000/1.000/1.000 for the eye blinking, mouthing, face without any expression, scowling categories, and yawning, respectively.

CONCLUSIONS

The AI classifier has the potential to objectively classify fetal facial expressions. AI can advance fetal brain development research using ultrasound.

Analgesia for fetal pain during prenatal surgery: 10 years of progress

Some doubts on the necessity and safety of providing analgesia to the fetus during prenatal surgery were raised 10 years ago. They were related to four matters: fetal sleep due to neuroinhibitors in fetal blood, the immaturity of the cerebral cortex, safety, and the need for fetal direct analgesia. These objections now seem obsolete. This review shows that neuroinhibitors give fetuses at most some transient sedation, but not a complete analgesia, that the cerebral cortex is not indispensable to feel pain, when subcortical structures for pain perception are present, and that maternal anesthesia seems not sufficient to anesthetize the fetus. Current drugs used for maternal analgesia pass through the placenta only partially so that they cannot guarantee a sufficient analgesia to the fetus. Extraction indices, that is, how much each analgesic drug crosses the placenta, are provided here. We here report safety guidelines for fetal direct analgesia. In conclusion, the human fetus can feel pain when it undergoes surgical interventions and direct analgesia must be provided to it. IMPACT: Fetal pain is evident in the second half of pregnancy. Progress in the physiology of fetal pain, which is reviewed in this report, supports the notion that the fetus reacts to painful interventions during fetal surgery. Evidence here reported shows that it is an error to believe that the fetus is in a continuous and unchanging state of sedation and analgesia. Data are given that disclose that drugs used for maternal analgesia cross the placenta only partially, so that they cannot guarantee a sufficient analgesia to the fetus. Safety guidelines are given for fetal direct analgesia.

Prenatal effects of maternal nutritional stress and mental health on the fetal movement profile

Purpose

Prenatal sub-optimal nutrition and exposure to maternal stress, anxiety and depression in pregnancy have been linked to increased postnatal morbidity and mortality. Fetal growth is most vulnerable to maternal dietary deficiencies, such as those evident in hyperemesis gravidarum (HG), early in pregnancy. The purpose of this pilot study was to examine the effects of HG on fetal movement profiles as a measure of fetal healthy development in the 3rd trimester of pregnancy, and to assess whether nutritional stress on the mother can be evaluated using isotopic analysis of hair.

Method

We analyzed fetal movement profiles using 4D ultrasound scans at 32- and 36-weeks' gestation. Fetuses of women (N = 6) diagnosed with HG, having lost more than 10% of their body weight in the first trimester of pregnancy were compared to a healthy group (N = 6), controlling for stress, depression and anxiety. We tested carbon and nitrogen isotope ratios in maternal hair as a measure of both diet and nutritional changes due to catabolism of body proteins and fats.

Results

HG and catabolism were significantly correlated (p = 0.02). Furthermore, at 32-weeks' gestation movement profiles of fetuses of mothers with HG differed significantly from the movement profiles of fetuses of healthy mothers. Fetuses of mothers suffering from HG showed a significantly increased ratio of fine-grained movements at 32 weeks (p = 0.008); however, there were no significant differences detectable at 36-weeks' gestation.

Conclusion

The effect of HG on fetal development as expressed by variations in fetal movement profiles in this pilot study suggest that prenatal effects of HG can be measured using movement profiles. Isotope analysis of hair can supplement this with information on nutritional imbalances early in pregnancy.

Electronic supplementary material

The online version of this article (10.1007/s00404-020-05571-w) contains supplementary material, which is available to authorized users.