Development and clinical validation of real-time artificial intelligence diagnostic companion for fetal ultrasound examination

3D ultrasound evaluation of fetal ears in prenatal syndrome diagnosis - a comparative study

PURPOSE

The aim of the study was to assess fetal ears on prenatal 3D ultrasound and compare ear surface patterns and measurements between fetuses with syndromes and healthy fetuses.

MATERIALS AND METHODS

Our study is based on 3D ultrasound images of 100 fetuses between the 20th and 37th week of gestation. We compared 50 ears of fetuses with syndromes (syndrome group) to 50 gestational age-matched ears of healthy fetuses (control group). The syndrome group consisted of fetuses with Trisomy 21 (n=13), Trisomy 18 (n=9) and other syndromes (n=28). The evaluation was based on measuring the ear length and width as well as developing categories to describe and compare different ear surface anomalies.

RESULTS

Ears of fetuses with Trisomy 18 were on average 0.423 cm smaller in length (P<0.001) and 0.123 cm smaller in width (P=0.031) and grew on average 0.046 cm less in length per week of gestation (P=0.027) than those of healthy fetuses. Ears of fetuses with Trisomy 21 differed from healthy fetuses regarding the form of the helix (P=0.013) and the ratio of the concha to the auricle (P=0.037). Fetuses with syndromes demonstrated less ear surface details than their controls (syndrome group: P=0.018, P=0.005; other syndromes subgroup: P=0.020). We saw an increased richness of ear surface details at a later gestational age both in the fetuses with syndromes and the healthy fetuses.

CONCLUSION

Ears of fetuses with Trisomy 18 were smaller than their matched controls. Fetuses with syndromes varied in the evaluation of their ear surface from those of healthy fetuses. The ear surface can be analyzed with 3D ultrasound and might be useful as a screening parameter in syndrome diagnosis in the future.

Probe motion during mid-trimester fetal anomaly scan in the clinical setting: A prospective observational study

INTRODUCTION

This study aims to investigate probe motion during full mid-trimester anomaly scans.

METHODS

We undertook a prospective, observational study of obstetric sonographers at a UK University Teaching Hospital. We collected prospectively full-length video recordings of routine second-trimester anomaly scans synchronized with probe trajectory tracking data during the scan. Videos were reviewed and trajectories analyzed using duration, path metrics (path length, velocity, acceleration, jerk, and volume) and angular metrics (spectral arc, angular area, angular velocity, angular acceleration, and angular jerk). These trajectories were then compared according to the participant level of expertise, fetal presentation, and patient BMI.

RESULTS

A total of 17 anomaly scans were recorded. The average velocity of the probe was 12.9 ± 3.4 mm/s for the consultants versus 24.6 ± 5.7 mm/s for the fellows (p = 0.02), the average acceleration 170.4 ± 26.3 mm/s2 versus 328.9 ± 62.7 mm/s2 (p = 0.02), and the average jerk 7491.7 ± 1056.1 mm/s3 versus 14944.1 ± 3146.3 mm/s3 (p = 0.02), the working volume 9.106 ± 4.106 mm3 versus 29.106 ± 11.106 mm3 (p = 0.03), respectively. The angular metrics were not significantly different according to the participant level of expertise, the fetal presentation, or to patients BMI.

CONCLUSION

Some differences in the probe path metrics (velocity, acceleration, jerk and working volume) were noticed according to operator's level.

The Holy Grail of obstetric ultrasound: can artificial intelligence detect hard-to-identify fetal cardiac anomalies?

Linked article: This Editorial comments on articles by Day et al. and Taksøe‐Vester et al.

RTSeg-net: A lightweight network for real-time segmentation of fetal head and pubic symphysis from intrapartum ultrasound images

The segmentation of the fetal head (FH) and pubic symphysis (PS) from intrapartum ultrasound images plays a pivotal role in monitoring labor progression and informing crucial clinical decisions. Achieving real-time segmentation with high accuracy on systems with limited hardware capabilities presents significant challenges. To address these challenges, we propose the real-time segmentation network (RTSeg-Net), a groundbreaking lightweight deep learning model that incorporates innovative distribution shifting convolutional blocks, tokenized multilayer perceptron blocks, and efficient feature fusion blocks. Designed for optimal computational efficiency, RTSeg-Net minimizes resource demand while significantly enhancing segmentation performance. Our comprehensive evaluation on two distinct intrapartum ultrasound image datasets reveals that RTSeg-Net achieves segmentation accuracy on par with more complex state-of-the-art networks, utilizing merely 1.86 M parameters-just 6 % of their hyperparameters-and operating seven times faster, achieving a remarkable rate of 31.13 frames per second on a Jetson Nano, a device known for its limited computing capacity. These achievements underscore RTSeg-Net's potential to provide accurate, real-time segmentation on low-power devices, broadening the scope for its application across various stages of labor. By facilitating real-time, accurate ultrasound image analysis on portable, low-cost devices, RTSeg-Net promises to revolutionize intrapartum monitoring, making sophisticated diagnostic tools accessible to a wider range of healthcare settings.

Automatic segmentation of 15 critical anatomical labels and measurements of cardiac axis and cardiothoracic ratio in fetal four chambers using nnU-NetV2

BACKGROUND

Accurate segmentation of critical anatomical structures in fetal four-chamber view images is essential for the early detection of congenital heart defects. Current prenatal screening methods rely on manual measurements, which are time-consuming and prone to inter-observer variability. This study develops an AI-based model using the state-of-the-art nnU-NetV2 architecture for automatic segmentation and measurement of key anatomical structures in fetal four-chamber view images.

METHODS

A dataset, consisting of 1,083 high-quality fetal four-chamber view images, was annotated with 15 critical anatomical labels and divided into training/validation (867 images) and test (216 images) sets. An AI-based model using the nnU-NetV2 architecture was trained on the annotated images and evaluated using the mean Dice coefficient (mDice) and mean intersection over union (mIoU) metrics. The model's performance in automatically computing the cardiac axis (CAx) and cardiothoracic ratio (CTR) was compared with measurements from sonographers with varying levels of experience.

RESULTS

The AI-based model achieved a mDice coefficient of 87.11% and an mIoU of 77.68% for the segmentation of critical anatomical structures. The model's automated CAx and CTR measurements showed strong agreement with those of experienced sonographers, with respective intraclass correlation coefficients (ICCs) of 0.83 and 0.81. Bland-Altman analysis further confirmed the high agreement between the model and experienced sonographers.

CONCLUSION

We developed an AI-based model using the nnU-NetV2 architecture for accurate segmentation and automated measurement of critical anatomical structures in fetal four-chamber view images. Our model demonstrated high segmentation accuracy and strong agreement with experienced sonographers in computing clinically relevant parameters. This approach has the potential to improve the efficiency and reliability of prenatal cardiac screening, ultimately contributing to the early detection of congenital heart defects.

Introducing Artificial Intelligence in Interpretation of Foetal Cardiotocography: Medical Dataset Curation and Preliminary Coding-An Interdisciplinary Project

Artificial intelligence (AI) is gaining increasing interest in the field of medicine because of its capacity to process big data and pattern recognition. Cardiotocography (CTG) is widely used for the assessment of foetal well-being and uterine contractions during pregnancy and labour. It is characterised by inter- and intraobserver variability in interpretation, which depends on the observers' experience. Artificial intelligence (AI)-assisted interpretation could improve its quality and, thus, intrapartal care. Cardiotocography (CTG) raw signals from labouring women were extracted from the database at the University Hospital of Bern between 2006 and 2019. Later, they were matched with the corresponding foetal outcomes, namely arterial umbilical cord pH and 5-min APGAR score. Excluded were deliveries where data were incomplete, as well as multiple births. Clinical data were grouped regarding foetal pH and APGAR score at 5 min after delivery. Physiological foetal pH was defined as 7.15 and above, and a 5-min APGAR score was considered physiologic when reaching ≥7. With these groups, the algorithm was trained to predict foetal hypoxia. Raw data from 19,399 CTG recordings could be exported. This was accomplished by manually searching the patient's identification numbers (PIDs) and extracting the corresponding raw data from each episode. For some patients, only one episode per pregnancy could be found, whereas for others, up to ten episodes were available. Initially, 3400 corresponding clinical outcomes were found for the 19,399 CTGs (17.52%). Due to the small size, this dataset was rejected, and a new search strategy was elaborated. After further matching and curation, 6141 (31.65%) paired data samples could be extracted (cardiotocography raw data and corresponding maternal and foetal outcomes). Of these, half will be used to train artificial intelligence (AI) algorithms, whereas the other half will be used for analysis of efficacy. Complete data could only be found for one-third of the available population. Yet, to our knowledge, this is the most exhaustive and second-largest cardiotocography database worldwide, which can be used for computer analysis and programming. A further enrichment of the database is planned.

Incremental yield of whole-genome sequencing over chromosomal microarray analysis and exome sequencing for congenital anomalies in prenatal period and infancy: systematic review and meta-analysis

OBJECTIVES

First, to determine the incremental yield of whole-genome sequencing (WGS) over quantitative fluorescence polymerase chain reaction (QF-PCR)/chromosomal microarray analysis (CMA) with and without exome sequencing (ES) in fetuses, neonates and infants with a congenital anomaly that was or could have been detected on prenatal ultrasound. Second, to evaluate the turnaround time (TAT) and quantity of DNA required for testing using these pathways.

METHODS

This review was registered prospectively in December 2022. Ovid MEDLINE, EMBASE, MEDLINE (Web of Science), The Cochrane Library and ClinicalTrials.gov databases were searched electronically (January 2010 to December 2022). Inclusion criteria were cohort studies including three or more fetuses, neonates or infants with (i) one or more congenital anomalies; (ii) an anomaly which was or would have been detectable on prenatal ultrasound; and (iii) negative QF-PCR and CMA. In instances in which the CMA result was unavailable, all cases of causative pathogenic copy number variants > 50 kb were excluded, as these would have been detectable on standard prenatal CMA. Pooled incremental yield was determined using a random-effects model and heterogeneity was assessed using Higgins' I2 test. Subanalyses were performed based on pre- or postnatal cohorts, cases with multisystem anomalies and those meeting the NHS England prenatal ES inclusion criteria.

RESULTS

A total of 18 studies incorporating 902 eligible cases were included, of which eight (44.4%) studies focused on prenatal cohorts, incorporating 755 cases, and the remaining studies focused on fetuses undergoing postmortem testing or neonates/infants with congenital structural anomalies, constituting the postnatal cohort. The incremental yield of WGS over QF-PCR/CMA was 26% (95% CI, 18-36%) (I2  = 86%), 16% (95% CI, 9-24%) (I2  = 85%) and 39% (95% CI, 27-51%) (I2  = 53%) for all, prenatal and postnatal cases, respectively. The incremental yield increased in cases in which sequencing was performed in line with the NHS England prenatal ES criteria (32% (95% CI, 22-42%); I2  = 70%) and in those with multisystem anomalies (30% (95% CI, 19-43%); I2  = 65%). The incremental yield of WGS for variants of uncertain significance (VUS) was 18% (95% CI, 7-33%) (I2  = 74%). The incremental yield of WGS over QF-PCR/CMA and ES was 1% (95% CI, 0-4%) (I2  = 47%). The pooled median TAT of WGS was 18 (range, 1-912) days, and the quantity of DNA required was 100 ± 0 ng for WGS and 350 ± 50 ng for QF-PCR/CMA and ES (P = 0.03).

CONCLUSION

While WGS in cases with congenital anomaly holds great promise, its incremental yield over ES is yet to be demonstrated. However, the laboratory pathway for WGS requires less DNA with a potentially faster TAT compared with sequential QF-PCR/CMA and ES. There was a relatively high rate of VUS using WGS. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

Fetal development is a critical phase in prenatal care, demanding the timely identification of anomalies in ultrasound images to safeguard the well-being of both the unborn child and the mother. Medical imaging has played a pivotal role in detecting fetal abnormalities and malformations. However, despite significant advances in ultrasound technology, the accurate identification of irregularities in prenatal images continues to pose considerable challenges, often necessitating substantial time and expertise from medical professionals. In this review, we go through recent developments in machine learning (ML) methods applied to fetal ultrasound images. Specifically, we focus on a range of ML algorithms employed in the context of fetal ultrasound, encompassing tasks such as image classification, object recognition, and segmentation. We highlight how these innovative approaches can enhance ultrasound-based fetal anomaly detection and provide insights for future research and clinical implementations. Furthermore, we emphasize the need for further research in this domain where future investigations can contribute to more effective ultrasound-based fetal anomaly detection.