Clinical workflow of sonographers performing fetal anomaly ultrasound scans: deep-learning-based analysis.

OBJECTIVE: Despite decades of obstetric scanning, the field of sonographer workflow remains largely unexplored. In the second trimester, sonographers use scan guidelines to guide their acquisition of standard planes and structures; however, the scan-acquisition order is not prescribed. Using deep-learning-based video analysis, the aim of this study was to develop a deeper understanding of the clinical workflow undertaken by sonographers during second-trimester anomaly scans. METHODS: We collected prospectively full-length video recordings of routine second-trimester anomaly scans. Important scan events in the videos were identified by detecting automatically image freeze and image/clip save. The video immediately preceding and following the important event was extracted and labeled as one of 11 commonly acquired anatomical structures. We developed and used a purposely trained and tested deep-learning annotation model to label automatically the large number of scan events. Thus, anomaly scans were partitioned as a sequence of anatomical planes or fetal structures obtained over time. RESULTS: A total of 496 anomaly scans performed by 14 sonographers were available for analysis. UK guidelines specify that an image or videoclip of five different anatomical regions must be stored and these were detected in the majority of scans: head/brain was detected in 97.2% of scans, coronal face view (nose/lips) in 86.1%, abdomen in 93.1%, spine in 95.0% and femur in 92.3%. Analyzing the clinical workflow, we observed that sonographers were most likely to begin their scan by capturing the head/brain (in 24.4% of scans), spine (in 23.2%) or thorax/heart (in 22.8%). The most commonly identified two-structure transitions were: placenta/amniotic fluid to maternal anatomy, occurring in 44.5% of scans; head/brain to coronal face (nose/lips) in 42.7%; abdomen to thorax/heart in 26.1%; and three-dimensional/four-dimensional face to sagittal face (profile) in 23.7%. Transitions between three or more consecutive structures in sequence were uncommon (up to 13% of scans). None of the captured anomaly scans shared an entirely identical sequence. CONCLUSIONS: We present a novel evaluation of the anomaly scan acquisition process using a deep-learning-based analysis of ultrasound video. We note wide variation in the number and sequence of structures obtained during routine second-trimester anomaly scans. Overall, each anomaly scan was found to be unique in its scanning sequence, suggesting that sonographers take advantage of the fetal position and acquire the standard planes according to their visibility rather than following a strict acquisition order. © 2022 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

How often do we identify fetal abnormalities during routine third-trimester ultrasound? A systematic review and meta-analysis.

BACKGROUND: Routine third-trimester ultrasound is frequently offered to pregnant women to identify fetuses with abnormal growth. Infrequently, a congenital anomaly is incidentally detected. OBJECTIVE: To establish the prevalence and type of fetal anomalies detected during routine third-trimester scans using a systematic review and meta-analysis. SEARCH STRATEGY: Electronic databases (MEDLINE, Embase and the Cochrane library) from inception until August 2019. SELECTION CRITERIA: Population-based studies (randomised control trials, prospective and retrospective cohorts) reporting abnormalities detected at the routine third-trimester ultrasound performed in unselected populations with prior screening. Case reports, case series, case-control studies and reviews without original data were excluded. DATA COLLECTION AND ANALYSIS: Prevalence and type of anomalies detected in the third trimester. We calculated pooled prevalence as the number of anomalies per 1000 scans with 95% confidence intervals. Publication bias was assessed. MAIN RESULTS: The literature search identified 9594 citations: 13 studies were eligible representing 141 717 women; 643 were diagnosed with an unexpected abnormality. The pooled prevalence of a new abnormality diagnosed was 3.68 per 1000 women scanned (95% CI 2.72-4.78). The largest groups of abnormalities were urogenital (55%), central nervous system abnormalities (18%) and cardiac abnormalities (14%). CONCLUSION: Combining data from 13 studies and over 140 000 women, we show that during routine third-trimester ultrasound, an incidental fetal anomaly will be found in about 1 in 300 scanned women. This information should be taken into account when taking consent from women for third-trimester ultrasound and when designing and assessing cost of third-trimester ultrasound screening programmes. TWEETABLE ABSTRACT: One in 300 women attending a third-trimester scan will have a finding of a fetal abnormality.

Fetal cerebellar growth and Sylvian fissure maturation: international standards from Fetal Growth Longitudinal Study of INTERGROWTH-21st Project.

OBJECTIVE: To construct international ultrasound-based standards for fetal cerebellar growth and Sylvian fissure maturation. METHODS: Healthy, well nourished pregnant women, enrolled at < 14 weeks' gestation in the Fetal Growth Longitudinal Study (FGLS) of INTERGROWTH-21st , an international multicenter, population-based project, underwent serial three-dimensional (3D) fetal ultrasound scans every 5 ± 1 weeks until delivery in study sites located in Brazil, India, Italy, Kenya and the UK. In the present analysis, only those fetuses that underwent developmental assessment at 2 years of age were included. We measured the transcerebellar diameter and assessed Sylvian fissure maturation using two-dimensional ultrasound images extracted from available 3D fetal head volumes. The appropriateness of pooling data from the five sites was assessed using variance component analysis and standardized site differences. For each Sylvian fissure maturation score (left or right side), mean gestational age and 95% CI were calculated. Transcerebellar diameter was modeled using fractional polynomial regression, and goodness of fit was assessed. RESULTS: Of those children in the original FGLS cohort who had developmental assessment at 2 years of age, 1130 also had an available 3D ultrasound fetal head volume. The sociodemographic characteristics and pregnancy/perinatal outcomes of the study sample confirmed the health and low-risk status of the population studied. In addition, the fetuses had low morbidity and adequate growth and development at 2 years of age. In total, 3016 and 2359 individual volumes were available for transcerebellar-diameter and Sylvian-fissure analysis, respectively. Variance component analysis and standardized site differences showed that the five study populations were sufficiently similar on the basis of predefined criteria for the data to be pooled to produce international standards. A second-degree fractional polynomial provided the best fit for modeling transcerebellar diameter; we then estimated gestational-age-specific 3rd , 50th and 97th smoothed centiles. Goodness-of-fit analysis comparing empirical centiles with smoothed centile curves showed good agreement. The Sylvian fissure increased in maturation with advancing gestation, with complete overlap of the mean gestational age and 95% CIs between the sexes for each development score. No differences in Sylvian fissure maturation between the right and left hemispheres were observed. CONCLUSION: We present, for the first time, international standards for fetal cerebellar growth and Sylvian fissure maturation throughout pregnancy based on a healthy fetal population that exhibited adequate growth and development at 2 years of age. © 2020 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Discovering Salient Anatomical Landmarks by Predicting Human Gaze.

Anatomical landmarks are a crucial prerequisite for many medical imaging tasks. Usually, the set of landmarks for a given task is predefined by experts. The landmark locations for a given image are then annotated manually or via machine learning methods trained on manual annotations. In this paper, in contrast, we present a method to automatically discover and localize anatomical landmarks in medical images. Specifically, we consider landmarks that attract the visual attention of humans, which we term visually salient landmarks. We illustrate the method for fetal neurosonographic images. First, full-length clinical fetal ultrasound scans are recorded with live sonographer gaze-tracking. Next, a convolutional neural network (CNN) is trained to predict the gaze point distribution (saliency map) of the sonographers on scan video frames. The CNN is then used to predict saliency maps of unseen fetal neurosonographic images, and the landmarks are extracted as the local maxima of these saliency maps. Finally, the landmarks are matched across images by clustering the landmark CNN features. We show that the discovered landmarks can be used within affine image registration, with average landmark alignment errors between 4.1% and 10.9% of the fetal head long axis length.

Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology.

Artificial intelligence (AI) uses data and algorithms to aim to draw conclusions that are as good as, or even better than, those drawn by humans. AI is already part of our daily life; it is behind face recognition technology, speech recognition in virtual assistants (such as Amazon Alexa, Apple's Siri, Google Assistant and Microsoft Cortana) and self-driving cars. AI software has been able to beat world champions in chess, Go and recently even Poker. Relevant to our community, it is a prominent source of innovation in healthcare, already helping to develop new drugs, support clinical decisions and provide quality assurance in radiology. The list of medical image-analysis AI applications with USA Food and Drug Administration or European Union (soon to fall under European Union Medical Device Regulation) approval is growing rapidly and covers diverse clinical needs, such as detection of arrhythmia using a smartwatch or automatic triage of critical imaging studies to the top of the radiologist's worklist. Deep learning, a leading tool of AI, performs particularly well in image pattern recognition and, therefore, can be of great benefit to doctors who rely heavily on images, such as sonologists, radiographers and pathologists. Although obstetric and gynecological ultrasound are two of the most commonly performed imaging studies, AI has had little impact on this field so far. Nevertheless, there is huge potential for AI to assist in repetitive ultrasound tasks, such as automatically identifying good-quality acquisitions and providing instant quality assurance. For this potential to thrive, interdisciplinary communication between AI developers and ultrasound professionals is necessary. In this article, we explore the fundamentals of medical imaging AI, from theory to applicability, and introduce some key terms to medical professionals in the field of ultrasound. We believe that wider knowledge of AI will help accelerate its integration into healthcare. © 2020 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology.

Expected-value bias in routine third-trimester growth scans.

OBJECTIVES: Operators performing fetal growth scans are usually aware of the gestational age of the pregnancy, which may lead to expected-value bias when performing biometric measurements. We aimed to evaluate the incidence of expected-value bias in routine fetal growth scans and assess its impact on standard biometric measurements. METHODS: We collected prospectively full-length video recordings of routine ultrasound growth scans coupled with operator eye tracking. Expected value was defined as the gestational age at the time of the scan, based on the estimated due date that was established at the dating scan. Expected-value bias was defined as occurring when the operator looked at the measurement box on the screen during the process of caliper adjustment before saving a measurement. We studied the three standard biometric planes on which measurements of head circumference (HC), abdominal circumference (AC) and femur length (FL) are obtained. We evaluated the incidence of expected-value bias and quantified the impact of biased measurements. RESULTS: We analyzed 272 third-trimester growth scans, performed by 16 operators, during which a total of 1409 measurements (354 HC, 703 AC and 352 FL; including repeat measurements) were obtained. Expected-value bias occurred in 91.4% of the saved standard biometric plane measurements (85.0% for HC, 92.9% for AC and 94.9% for FL). The operators were more likely to adjust the measurements towards the expected value than away from it (47.7% vs 19.7% of measurements; P < 0.001). On average, measurements were corrected by 2.3 ± 5.6, 2.4 ± 10.4 and 3.2 ± 10.4 days of gestation towards the expected gestational age for the HC, AC, and FL measurements, respectively. Additionally, we noted a statistically significant reduction in measurement variance once the operator was biased (P = 0.026). Comparing the lowest and highest possible estimated fetal weight (using the smallest and largest biased HC, AC and FL measurements), we noted that the discordance, in percentage terms, was 10.1% ± 6.5%, and that in 17% (95% CI, 12-21%) of the scans, the fetus could be considered as small-for-gestational age or appropriate-for-gestational age if using the smallest or largest possible measurements, respectively. Similarly, in 13% (95% CI, 9-16%) of scans, the fetus could be considered as large-for-gestational age or appropriate-for-gestational age if using the largest or smallest possible measurements, respectively. CONCLUSIONS: During routine third-trimester growth scans, expected-value bias frequently occurs and significantly changes standard biometric measurements obtained. © 2019 the Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology.

Spatio-Temporal Partitioning and Description of Full-Length Routine Fetal Anomaly Ultrasound Scans.

This paper considers automatic clinical workflow description of full-length routine fetal anomaly ultrasound scans using deep learning approaches for spatio-temporal video analysis. Multiple architectures consisting of 2D and 2D + t CNN, LSTM, and convolutional LSTM are investigated and compared. The contributions of short-term and long-term temporal changes are studied, and a multi-stream framework analysis is found to achieve the best top-1 accuracy=0.77 and top-3 accuracy=0.94. Automated partitioning and characterisation on unlabelled full-length video scans show high correlation (ρ=0.95, p=0.0004) with workflow statistics of manually labelled videos, suggesting practicality of proposed methods.