Applications of Advanced Ultrasound Technology in Obstetrics

A comprehensive scoping review on machine learning-based fetal echocardiography analysis

Fetal echocardiography (ultrasound of the fetal heart) plays a vital role in identifying heart defects, allowing clinicians to establish prenatal and postnatal management plans. Machine learning-based methods are emerging to support the automation of fetal echocardiographic analysis; this review presents the findings from a literature review in this area. Searches were queried at leading indexing platforms ACM, IEEE Xplore, PubMed, Scopus, and Web of Science, including papers published until July 2023. In total, 343 papers were found, where 48 papers were selected to compose the detailed review. The reviewed literature presents research on neural network-based methods to identify fetal heart anatomy in classification and segmentation modelling. The reviewed literature uses five categorical technical analysis terms: attention and saliency, coarse to fine, dilated convolution, generative adversarial networks, and spatio-temporal. This review offers a technical overview for those already working in the field and an introduction to those new to the topic.

Fetal and obstetrics manifestations of mitochondrial diseases

During embryonic and neonatal development, mitochondria have essential effects on metabolic and energetic regulation, shaping cell fate decisions and leading to significant short- and long-term effects on embryonic and offspring health. Therefore, perturbation on mitochondrial function can have a pathological effect on pregnancy. Several shreds of evidence collected in preclinical models revealed that severe mitochondrial dysfunction is incompatible with life or leads to critical developmental defects, highlighting the importance of correct mitochondrial function during embryo-fetal development. The mechanism impairing the correct development is unknown and may include a dysfunctional metabolic switch in differentiating cells due to decreased ATP production or altered apoptotic signalling. Given the central role of mitochondria in embryonic and fetal development, the mitochondrial dysfunction typical of Mitochondrial Diseases (MDs) should, in principle, be detectable during pregnancy. However, little is known about the clinical manifestations of MDs in embryonic and fetal development. In this manuscript, we review preclinical and clinical evidence suggesting that MDs may affect fetal development and highlight the fetal and maternal outcomes that may provide a wake-up call for targeted genetic diagnosis.

Repeated diagnostic ultrasound exposure modifies the structural properties of CA1 dendrites and alters the hippocampal transcriptome

The development of neurons is regulated by several spatiotemporally changing factors, which are crucial to give the ability of neurons to form functional networks. While external physical stimuli may impact the early developmental stages of neurons, the medium and long-term consequences of these influences have yet to be thoroughly examined. Using an animal model, this study focuses on the morphological and transcriptome changes of the hippocampus that may occur as a consequence of fetal ultrasound examination. We selectively labeled CA1 neurons of the hippocampus with in-utero electroporation to analyze their morphological features. Furthermore, certain samples also went through RNA sequencing after repetitive ultrasound exposure. US exposure significantly changed several morphological properties of the basal dendritic tree. A notable increase was also observed in the density of spines on the basal dendrites, accompanied by various alterations in individual spine morphology. Transcriptome analysis revealed several up or downregulated genes, which may explain the molecular background of these alterations. Our results suggest that US-derived changes in the dendritic trees of CA1 pyramidal cells might be connected to modification of the transcriptome of the hippocampus and may lead to an increased dendritic input.

Ultrasound Image Analysis with Vision Transformers-Review

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges, such as a low imaging quality and high variability. There is a need to develop advanced automatic US image analysis methods to enhance its diagnostic accuracy and objectivity. Vision transformers, a recent innovation in machine learning, have demonstrated significant potential in various research fields, including general image analysis and computer vision, due to their capacity to process large datasets and learn complex patterns. Their suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformers and discusses their applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in their application in medical US image analysis. Vision transformers have shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and are expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

Clinical Ultrasound Applications in Obstetrics and Gynecology in the Year 2024

Ultrasound imaging stands as a fundamental technology in the realms of obstetrics and gynecology, utilizing high-frequency sound waves to create detailed images of the internal structures of the body [...].

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.

Neonatal head circumference as a risk factor for obstetric anal sphincter injuries: a systematic review and meta-analysis

OBJECTIVE

Between 53% and 79% of women will sustain some degree of perineal laceration during vaginal delivery. Third- and fourth-degree perineal lacerations are known as obstetric anal sphincter injuries. Timely diagnosis and prompt treatment of obstetric anal sphincter injuries can help to prevent the development of severe consequences like fecal incontinence, urinary incontinence, and rectovaginal fistula. Neonatal head circumference is routinely measured postpartum but is often not mentioned as a risk factor for obstetric anal sphincter injuries in clinical guidelines. Thus far, no review article on the risk factors for obstetric anal sphincter injuries has discussed the role of neonatal head circumference. This study aimed to review and analyze the relationship between head circumference and the occurrence of obstetric anal sphincter injuries among previous studies to conclude whether head circumference should be recognized as an important risk factor.

DATA SOURCES

Through study screening on Google Scholar, PubMed, Scopus, and Science Direct for articles published between 2013 to 2023, followed by assessment of eligibility, this study ended up reviewing 25 studies, 17 of which were included in the meta-analysis.

STUDY ELIGIBILITY CRITERIA

Only studies that reported both the neonatal head circumference and the occurrence of obstetric anal sphincter injuries were included in this review.

METHODS

The included studies were appraised using the Dartmouth Library risk of bias assessment checklist. Qualitative synthesis was based on the study population, findings, adjusted confounding factors, and suggested causative links in each study. Quantitative synthesis was conducted using calculation and pooling of odds ratios and inverse variance using Review Manager 5.4.1.

RESULTS

A statistically significant association between head circumference and obstetric anal sphincter injuries was reported in 21 of 25 studies; 4 studies reported that head circumference was a true independent risk factor. A meta-analysis of the studies that reported neonatal head circumference as a dichotomous categorical variable with a cutoff point of 35±1 cm yielded statistically significant pooled results (odds ratio, 1.92; 95% confidence interval, 1.80-2.04).

CONCLUSION

The risk for obstetric anal sphincter injuries increased as the neonatal head circumference increased-this should be considered in decision-making during labor and postpartum management to attain the best outcome.

Safety of early cumulus cell removal combined with early rescue ICSI in the prevention of fertilization failure

RESEARCH QUESTION

What are the clinical outcomes and safety implications of early cumulus cell removal after short-term insemination combined with early rescue intracytoplasmic sperm injection (ICSI) in preventing fertilization failure?

DESIGN

In this retrospective study, a total of 14,360 cycles were divided into four groups based on insemination method and fertilization ability: conventional IVF group (n = 5519); early cumulus cell removal group (n = 4107); conventional ICSI group (n = 4215); and early rescue ICSI group (where failed or low fertilization was predicted, n = 519). Fertilization outcomes, pregnancy outcomes, neonatal outcomes and birth defects were analysed by comparing the early cumulus cell removal group with the conventional IVF group, and the early rescue ICSI group with the conventional ICSI group.

RESULTS

There were no significant differences in the outcomes of fertilization, pregnancy, neonates or birth defects between the conventional IVF group and the early cumulus cell removal group (P > 0.05). When compared with the conventional ICSI group, the early rescue ICSI group had similar rates of two pronuclei (2PN) at fertilization, clinical pregnancy, miscarriage, ectopic pregnancy, live birth, sex, mean gestational age, very low birthweight, macrosomia and birth defects (P > 0.05) but a higher polyploidy rate, lower high-quality embryo rate (both P < 0.001), lower twin pregnancy rate (P < 0.01), lower rate of low birthweight, and a higher rate of normal birthweight (both P = 0.024).

CONCLUSIONS

Early cumulus cell removal combined with early rescue ICSI led to good pregnancy and neonatal outcomes without an increase in birth defects. This approach could therefore be an effective and safe method for patients with fertilization failure in conventional IVF.

Nomogram based on the final antepartum ultrasound features before delivery for predicting failed spontaneous vaginal delivery in nulliparous women

Background

Accurate identification of nulliparous women with failed spontaneous vaginal delivery (SVD) is crucial to minimize the hazards associated with obstetrical intervention (OI). While abnormal labor progression can be identified with intrapartum ultrasonography, labor-related complications may be unavoidable due to the limited time window left to the obstetrician. Antepartum ultrasound enables sufficient obstetric planning. However, there is typically a longer gap between ultrasound assessment and delivery that often lowers the prediction accuracy compared to intrapartum ultrasonography.

Objective

In this study, antepartum ultrasound assessment was included to each fetal ultrasound examination after 36 weeks of gestation until the onset of labor. We aim to establish a nomogram to predict the likelihood of failed SVD in nulliparous women using the last antepartum ultrasound findings before labor beginning.

Methods

Of the 2,143 nulliparous women recruited, 1,373 were included in a training cohort and 770 in a validation cohort, based on their delivery date. Maternal and perinatal characteristics, as well as perinatal ultrasound parameters were collected. In the training cohort, the screened correlates of SVD failure were used to develop a nomogram for determining whether a nulliparous woman would experience SVD failure. This model was validated in both training and validation cohorts.

Results

SVD failure affected 217 nulliparous women (10.13%). In the training cohort, SVD failure was independently associated with BMI [odds ratio (OR) = 1.636], FHC (OR = 1.194), CL (OR = 1.398), and PCA (OR = 0.824) (all P < 0.05). They constituted a nomogram to estimate the individual risk of SVD failure. The model obtained clinical net benefits in both the training and validation cohorts and was validated to present strong discrimination and calibration.

Conclusion

The developed nomogram based on the last antepartum ultrasound findings may be helpful in avoiding OI and its related complications by assessing the likelihood of a failed SVD in nulliparous women.

Multitask Deep Neural Network for the Fully Automatic Measurement of the Angle of Progression

The angle of progression (AoP) for assessing fetal head (FH) descent during labor is measured from the standard plane of transperineal ultrasound images as the angle between a line through the long axis of pubic symphysis (PS) and a second line from the right end of PS tangentially to the contour of the FH. This paper presents a multitask network with a shared feature encoder and three task-special decoders for standard plane recognition (Task1), image segmentation (Task2) of PS and FH, and endpoint detection (Task3) of PS. Based on the segmented FH and two endpoints of PS from standard plane images, we determined the right FH tangent point that passes through the right endpoint of PS and then computed the AoP using the above three points. In this paper, the efficient channel attention unit is introduced into the shared feature encoder for improving the robustness of layer region encoding, while an attention fusion module is used to promote cross-branch interaction between the encoder for Task2 and that for Task3, and a shape-constrained loss function is designed for enhancing the robustness to noise based on the convex shape-prior. We use Pearson's correlation coefficient and the Bland–Altman graph to assess the degree of agreement. The dataset includes 1964 images, where 919 images are nonstandard planes, and the other 1045 images are standard planes including PS and FH. We achieve a classification accuracy of 92.26%, and for the AoP calculation, an absolute mean (STD) value of the difference in AoP (∆AoP) is 3.898° (3.192°), the Pearson's correlation coefficient between manual and automated AoP was 0.964 and the Bland-Altman plot demonstrates they were statistically significant (P < 0.05). In conclusion, our approach can achieve a fully automatic measurement of AoP with good efficiency and may help labor progress in the future.

Pregnant women's knowledge, attitude, and associated factors toward obstetric ultrasound in public hospitals, Ethiopia, 2021: Multi-centered cross-sectional study

BACKGROUND

Obstetric ultrasound is a harmless, cheap, and noninvasive imaging modality that helps to scan a pregnant mother and delivers parents with a real-time image of the fetus. As the number of pregnancies rises globally, the demand for obstetric ultrasound becomes even more pressing.

OBJECTIVES

To assess pregnant women's knowledge, attitude, and associated factors toward obstetric ultrasound in public hospitals, Ethiopia.

METHODS

Institutional based cross-sectional study was employed. Systematic random technique was used to select 419 pregnant women from 10 April 2021 through 2 June 2021. A structured questionnaire was used to collect data during a face-to-face interview. Then the data were coded, cleaned, and entered into Epidemiological data version (EPIDATA) 3.1 and exported to the statistical package for Social Science version 23.0 for analyses. Bivariate and multivariable logistic regression model was used to identify statistically significant associations between dependent and independent variables. The odds ratio at 95% confidence interval with p-value 0.05% was considered statistically significant.

RESULT

The majority of the study participants, 179 (42.8%), have ages ⩾ 25 years. Magnitude of having good knowledge and positive attitude of pregnant women toward obstetric ultrasound was 35.5% and 69.5%, respectively. Residence (adjusted odds ratio: 3.934; 95% confidence interval: 3.125-6.761), educational status (adjusted odds ratio: 3.614; 95% confidence interval: 1.986-5.964), and parity (adjusted odds ratio: 2.7621; 95% confidence interval: 1.68-3.275) were significantly associated with knowledge. Whereas exposure to obstetrical ultrasound in current pregnancy (adjusted odds ratio: 2.726; 95% confidence interval: 1.632-3.629), knowledge on obstetrical ultrasound (adjusted odds ratio: 3.92; 95% confidence interval: 1.324-3.120), and educational status (adjusted odds ratio: 2.84; 95% confidence interval: 1.337-3.381) were significantly associated with attitude.

CONCLUSION

The level of good knowledge and positive attitude toward obstetric ultrasound was 35.5% and 69.5%, respectively, and it can be improved with appropriate interventions like ensuring the practice of obstetric ultrasound scan to all antenatal women. Obstetric care providers at the antenatal care units should advice pregnant women for obstetric ultrasound scan as per World Health Organization recommendations of one obstetric ultrasound scan before 24 weeks of gestation.