Feasibility of three-dimensional reconstruction and automated measurement of fetal long bones using 5D Long Bone

Artificial intelligence in obstetric ultrasound: A scoping review

The objective is to summarize the current use of artificial intelligence (AI) in obstetric ultrasound. PubMed, Cochrane Library, and ClinicalTrials.gov databases were searched using the following keywords "neural networks", OR "artificial intelligence", OR "machine learning", OR "deep learning", AND "obstetrics", OR "obstetrical", OR "fetus", OR "foetus", OR "fetal", OR "foetal", OR "pregnancy", or "pregnant", AND "ultrasound" from inception through May 2022. The search was limited to the English language. Studies were eligible for inclusion if they described the use of AI in obstetric ultrasound. Obstetric ultrasound was defined as the process of obtaining ultrasound images of a fetus, amniotic fluid, or placenta. AI was defined as the use of neural networks, machine learning, or deep learning methods. The authors' search identified a total of 127 papers that fulfilled our inclusion criteria. The current uses of AI in obstetric ultrasound include first trimester pregnancy ultrasound, assessment of placenta, fetal biometry, fetal echocardiography, fetal neurosonography, assessment of fetal anatomy, and other uses including assessment of fetal lung maturity and screening for risk of adverse pregnancy outcomes. AI holds the potential to improve the ultrasound efficiency, pregnancy outcomes in low resource settings, detection of congenital malformations and prediction of adverse pregnancy outcomes.

Artificial Intelligence in Prenatal Ultrasound Diagnosis

The application of artificial intelligence (AI) technology to medical imaging has resulted in great breakthroughs. Given the unique position of ultrasound (US) in prenatal screening, the research on AI in prenatal US has practical significance with its application to prenatal US diagnosis improving work efficiency, providing quantitative assessments, standardizing measurements, improving diagnostic accuracy, and automating image quality control. This review provides an overview of recent studies that have applied AI technology to prenatal US diagnosis and explains the challenges encountered in these applications.

On the Epistemic Status of Prenatal Ultrasound: Are Ultrasound Scans Photographic Pictures?

Medical imaging is predominantly a visual field. In this context, prenatal ultrasound images assume intense social, ethical, and psychological significance by virtue of the subject they represent: the fetus. This feature, along with the sophistication introduced by three-dimensional (3D) ultrasound imaging that allows improved visualization of the fetus, has contributed to the common impression that prenatal ultrasound scans are like photographs of the fetus. In this article we discuss the consistency of such a comparison. First, we investigate the epistemic role of both analogic and digital photographic images as visual information-providing representations holding a high degree of objectivity. Second, we examine the structure and process of production of ultrasound scans and argue that a comparison between two-dimensional (2D) ultrasound and photography is justified. This is in contrast to 3D ultrasound images that, due to the intensive mathematical processing involved in their production, present some structural issues that obfuscate their ontological and epistemic status.

Fetal biometry in ultrasound: A new approach to assess the long-term impact of simulation on learning patterns

CONTEXT

Simulation-based education (SBE) has demonstrated its acceptability and effectiveness in improving ultrasound training. Because of the high cost of its implementation (investment in equipment and supervision), a pragmatic assessment of the transfer of skills learned in SBE to clinical practice and the identification of its optimal scheduling conditions have been requested to optimize its input.

OBJECTIVES

To quantify the long-term impact of simulation-based education (SBE) on the adequate performance of ultrasound fetal biometry measurements (I). The secondary objective was to identify the temporal patterns that enhanced SBE input in learning (II).

METHODS

Trainees were arbitrarily assigned to a 6-month course in obstetric ultrasound with or without an SBE workshop. In the SBE group, the workshop was implemented 'before' or at an 'early' or a 'late-stage' of the course. Those who did not receive SBE were the control group. The ultrasound skills of all trainees were prospectively collected, evaluated by calculating the delta between OSAUS (Objective Structured Assessment of Ultrasound Skills) scores before and after the course (I). Concomitantly, the accuracy of trainees' measurements was assessed throughout the course by verifying their correlation with the corresponding measurements by their supervisors. The percentage of trainees able to perform five consecutive sets of correct measurements in the control group and in each SBE subgroup were compared (II).

RESULTS

The study included 61 trainees (39 SBE and 22 controls). Comparisons between groups showed no significant difference in the quantitative assessment of skill enhancement (difference in the pre- and post-internship OSAUS score: 1.09 ± 0.87 in the SBE group and 0.72 ± 0.98 in the control group) (I). Conversely, the predefined acceptable skill level was reached by a significantly higher proportion of trainees in the 'early' SBE subgroup (74%, compared with 30% in the control group, P<0.01)(II).

CONCLUSIONS

The quantitative assessment does not support the existence of long-term benefits from SBE training, although the qualitative assessment confirmed SBE helped to raise the minimal level within a group when embedded in an 'early' stage of a practical course.

Prospective assessment of reproducibility of three-dimensional ultrasound for fetal biometry

PURPOSE

To compare fetal ultrasound measurements performed by two observers with different levels of experience and evaluate the potential contribution of the use of three-dimensional (3D) ultrasound on repeatability, reproducibility and agreement of two-dimensional (2D) and 3D-derived measurements.

MATERIALS AND METHODS

Two observers (one senior and one junior) measured head circumference (HC), abdominal circumference (AC) and femur length (FL) in 33 fetuses (20 to 40 weeks of gestation). Each observer performed two series of 2D measurements and two series of 3D measurements (i.e., measurements derived from triplane volume processing). Measurements were converted into Z-scores according to gestational age. Variability between the different series of measurements was studied using Bland-Altmann plots and intra-class correlation coefficients (ICC).

RESULTS

Agreement with the 2D measurements of the senior observer was higher in 3D than in 2D for the junior observer (systematic differences of -0.4, -0.2 and -0.8 Z-score vs. -0.1, -0.1 and -0.6 for HC, AC and FL on 2D and 3D datasets, respectively). The use of 3D ultrasound improved junior observer repeatability (ICC=0.94, 0.88, 0.90 vs. 0.94, 0.94 and 0.96 for HC, AC and FL in 2D and 3D, respectively). The reproducibility was greater using the junior observer 3D datasets (ICC=0.75, 0.60 and 0.45 vs. 0.79, 0.89 and 0.63 for HC, AC and FL, respectively).

CONCLUSION

The use of 3D ultrasound improves the consistency of the measurements performed by a junior observer and increases the overall repeatability and reproducibility of measurements performed by observers with different levels of experience.

Optimization of Fetal Biometry With 3D Ultrasound and Image Recognition (EPICEA): protocol for a prospective cross-sectional study

CONTEXT

Variability in 2D ultrasound (US) is related to the acquisition of planes of reference and the positioning of callipers and could be reduced in combining US volume acquisitions and anatomical structures recognition.

OBJECTIVES

The primary objective is to assess the consistency between 3D measurements (automated and manual) extracted from a fetal US volume with standard 2D US measurements (I). Secondary objectives are to evaluate the feasibility of the use of software to obtain automated measurements of the fetal head, abdomen and femur from US acquisitions (II) and to assess the impact of automation on intraobserver and interobserver reproducibility (III).

METHODS AND ANALYSIS

225 fetuses will be measured at 16-30 weeks of gestation. For each fetus, six volumes (two for head, abdomen and thigh, respectively) will be prospectively acquired after performing standard 2D biometry measurements (head and abdominal circumference, femoral length). Each volume will be processed later by both a software and an operator to extract the reference planes and to perform the corresponding measurements. The different sets of measurements will be compared using Bland-Altman plots to assess the agreement between the different processes (I). The feasibility of using the software in clinical practice will be assessed through the failure rate of processing and the score of quality of measurements (II). Interclass correlation coefficients will be used to evaluate the intraobserver and interobserver reproducibility (III).

ETHICS AND DISSEMINATION

The study and related consent forms were approved by an institutional review board (CPP SUD-EST 3) on 2 October 2018, under reference number 2018-033 B. The study has been registered in https://clinicaltrials.gov registry on 23 January 2019, under the number NCT03812471. This study will enable an improved understanding and dissemination of the potential benefits of 3D automated measurements and is a prerequisite for the design of intention to treat randomised studies assessing their impact.

TRIAL REGISTRATION NUMBER

NCT03812471; Pre-results.

Automated Fractional Limb Volume Measurements Improve the Precision of Birth Weight Predictions in Late Third-Trimester Fetuses

OBJECTIVES

Fetal soft tissue can be assessed by using fractional limb volume as a proxy for in utero nutritional status. We investigated automated fractional limb volume for rapid estimate fetal weight assessment.

METHODS

Pregnant women were prospectively scanned for 2- and 3-dimensional fetal biometric measurements within 4 days of delivery. Performance of birth weight prediction models was compared: (1) Hadlock (Am J Obstet Gynecol 1985; 151:333-337; biparietal diameter, abdominal circumference, and femur diaphysis length); and (2) Lee (Ultrasound Obstet Gynecol 2009; 34:556-565; biparietal diameter, abdominal circumference, and automated fractional limb volume). Percent differences were calculated: [(estimated birth weight - actual birth weight) ÷ (actual birth weight] × 100. Systematic errors (accuracy) were summarized as signed mean percent differences. Random errors (precision) were calculated as ± 1 SD of percent differences.

RESULTS

Fifty neonates were delivered at 39.4 weeks' gestation. The Hadlock model generated the most accurate birth weight (0.31%) with a mean random error of ±7.9%. Despite systematic underestimations, the most precise results occurred with fractional arm volume (-9.1% ± 5.1%) and fractional thigh (-5.2% ± 5.2%) models. The size and distribution of these prediction errors were improved after correction for systematic errors.

CONCLUSIONS

Automated fractional limb volume measurements can improve the precision of weight predictions in third-trimester fetuses. Correction factors may be necessary to adjust underestimated systematic errors when using automated fractional limb volume with prediction models that are based on manual tracing of fetal limb soft tissue borders.

Five-dimensional long bones biometry for estimation of femur length and fetal weight at term compared to two-dimensional ultrasound: a pilot study

BACKGROUND/OBJECTIVE

This study aimed to evaluate accuracy of five-dimensional long bones (5D LB) compared to two-dimensional ultrasound (2DUS) biometry to predict fetal weight among normal term women.

METHODS

Fifty six normal term women were recruited at Ain Shams Maternity Hospital, Egypt from 14 May to 30 November 2015. Fetal weight was estimated by Hadlock's IV formula using 2DUS and 5D LB. Estimated fetal weights (EFW) by 2DUS and 5D LB were compared with actual birth weights (ABW).

RESULTS

Mean femur length (FL) was 7.07 ± 0.73 cm and 6.74 ± 0.67 cm by 2DUS and 5D LB (p = .02). EFW was 3309.86 ± 463.06 g by 2DUS and 3205.46 ± 447.85 g by 5D LB (p = .25). No statistical difference was observed between ABW and EFW by 2DUS (p = .7) or 5D LB (p = .45). Positive correlation was found between EFW by 2DUS, 5D LB, and ABW (r = 0.67 and 0.7; p < .001). There was strong agreement between FL measured by 2DUS and 5D LB (ICC = 0.78), and perfect agreement between EFW by 2DUS and EFW by 5D LB (ICC = 0.918). 2DUS and 5D LB showed mean absolute percentage error for EFW of 10 ± 7% and 8 ± 7% compared to ABW (p = .15).

CONCLUSIONS

2DUS and 5D LB had same accuracy for fetal weight estimation at normal term pregnancy.