<scp>ISUOG</scp> Practice Guidelines (updated): fetal cardiac screening

Carvalho, J. S.; Axt-Fliedner, R; Chaoui, Rabih; Copel, Joshua A.; Cuneo, Bettina F.; Goff, Donna A.; Kopylov, Lital Gordin; Hecher, Kurt; Lee, Wesley; Moon-Grady, Anita J.; Mousa, H.; Muñoz, H.; Prefumo, Federico; Quarello, E.; Rychik, Jack; Tutschek, B.; Wiechec, M.

doi:10.1002/uog.26224

Cited by 61 publications

(39 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The situs, size and symmetry of the heart should be assessed. The screening examination of the heart involves the four‐chamber, outflow‐tract and three‐vessel‐and‐trachea views (Figure 2) 22 . Normal cardiothoracic circumference ratio in the third trimester is approximately 0.45 and should be no greater than 0.50.…”

Section: Third‐trimester Ultrasound Scanmentioning

confidence: 99%

“…Normal cardiothoracic circumference ratio in the third trimester is approximately 0.45 and should be no greater than 0.50. Mild asymmetry of the ventricles (right > left) and great arteries (pulmonary > aorta) may be normal in the third trimester, but warrants referral for fetal echocardiography if pronounced (Figure 3) 22 . Chest . The diaphragm should be examined in sagittal and coronal views (Figure 4) (approximately 20% of congenital diaphragmatic hernias are detected only in the third trimester 19 ).…”

Section: Third‐trimester Ultrasound Scanmentioning

confidence: 99%

See 1 more Smart Citation

ISUOG Practice Guidelines: performance of third‐trimester obstetric ultrasound scan

Khalil,

Sotiriadis,

D'Antonio

et al. 2024

Ultrasound in Obstet & Gyne

Self Cite

View full text Add to dashboard Cite

Section: Third‐trimester Ultrasound Scanmentioning

confidence: 99%

Section: Third‐trimester Ultrasound Scanmentioning

confidence: 99%

ISUOG Practice Guidelines: performance of third‐trimester obstetric ultrasound scan

Khalil,

Sotiriadis,

D'Antonio

et al. 2024

Ultrasound in Obstet & Gyne

Self Cite

View full text Add to dashboard Cite

“…The correct assessment of fetal heart anatomy requires evaluation of different fetal anatomical landmarks and cardiac components in well-described standard planes 41,76 . Fetal standard heart planes, such as the four-chamber, left ventricular outflow tract, right ventricular outflow tract and three-vessel-and-trachea views can be acquired automatically using DL models 47,[77][78][79] .…”

Section: Fetal Heartmentioning

confidence: 99%

Use of artificial intelligence and deep learning in fetal ultrasound imaging

Zegarra

Ghi

2023

Ultrasound in Obstet & Gyne

View full text Add to dashboard Cite

Deep learning is considered the leading artificial intelligence tool in image analysis in general. Deep-learning algorithms excel at image recognition, which makes them valuable in medical imaging. Obstetric ultrasound has become the gold standard imaging modality for detection and diagnosis of fetal malformations. However, ultrasound relies heavily on the operator's experience, making it unreliable in inexperienced hands. Several studies have proposed the use of deep-learning models as a tool to support sonographers, in an attempt to overcome these problems inherent to ultrasound. Deep learning has many clinical applications in the field of fetal imaging, including identification of normal and abnormal fetal anatomy and measurement of fetal biometry. In this Review, we provide a comprehensive explanation of the fundamentals of deep learning in fetal imaging, with particular focus on its clinical applicability.

show abstract

“…Prenatal diagnosis of CHD reduces morbidity and mortality and increases therapeutic options. Second‐trimester ultrasound examination is recommended universally due to the potential to identify 90% of cases of severe CHD 3,4 . However, in practice, as few as 30% of these are detected 5 .…”

Section: Introductionmentioning

confidence: 99%

“…Community imaging may differ from that of tertiary centers: scanning expertise may be lower, and captured images may be fewer and may be stored in low‐resolution formats. Different scanning protocols may capture different screening views 4,14 (Figure 1) and may vary among sonographers 15 . Finally, the patient population may vary with respect to several factors, for example the prevalence of CHD and body habitus.…”

Section: Introductionmentioning

confidence: 99%

Deep‐learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection

Athalye,

van Nisselrooij,

Rizvi

et al. 2024

Ultrasound in Obstet & Gyne

Self Cite

View full text Add to dashboard Cite

ObjectiveCongenital heart defects (CHD) are still missed despite nearly universal prenatal ultrasound screening programs, which may result in severe morbidity or even death. Deep machine learning (DL) can automate image recognition from ultrasound. The main aim of this study was to apply a previously developed DL model trained on images from a tertiary center, to fetal ultrasound images obtained during the second‐trimester standard anomaly scan in a low‐risk population. A secondary aim was to compare initial screening diagnosis, which makes use of live imaging at the point of care, with clinicians evaluating only stored images.MethodsAll pregnancies with isolated severe CHD in the Northwestern region of the Netherlands between 2015 and 2016 with available stored images were evaluated, as well as a sample of normal fetuses’ examinations from the same region. We compared initial clinical diagnostic accuracy (made in real time with access to live imaging), model accuracy, and performance of blinded human experts with access only to the stored images (like the model). We analyzed performance by study characteristics such as duration, quality (independently scored by study investigators), number of stored images, and availability of screening views.ResultsA total of 42 normal fetuses and 66 cases of isolated CHD at birth were analyzed. Of the abnormal cases, 31 were missed and 35 were detected at the time of the clinical anatomy scan (sensitivity 53 percent). Model sensitivity and specificity was 91 and 78 percent, respectively. Blinded human experts (n=3) achieved sensitivity and specificity of 55±10 percent (range 47‐67 percent) and 71±13 percent (range 57‐83 percent), respectively. There was a statistically significant difference in model correctness by expert‐graded image quality (p=0.03). Abnormal cases included 19 lesions the model had not encountered in its training; the model's performance (16/19 correct) was not statistically significantly different on previously encountered vs. never before seen lesions (p=0.41).ConclusionsA previously trained DL algorithm had higher sensitivity than initial clinical assessment in detecting CHD in a cohort in which over 50 percent of CHD cases were initially missed clinically. Notably, the DL algorithm performed well on community‐acquired images in a low‐risk population, including lesions it had not been previously exposed to. Furthermore, when both the model and blinded human experts had access to stored images alone, and not the full range of images available to a clinician during a live scan, the model outperformed expert humans. Together, these findings support the proposition that use of DL models can improve prenatal detection of CHD.This article is protected by copyright. All rights reserved.

show abstract

ISUOG Practice Guidelines (updated): fetal cardiac screening

Cited by 61 publications

References 124 publications

ISUOG Practice Guidelines: performance of third‐trimester obstetric ultrasound scan

ISUOG Practice Guidelines: performance of third‐trimester obstetric ultrasound scan

Use of artificial intelligence and deep learning in fetal ultrasound imaging

Deep‐learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection

Contact Info

Product

Resources

About