Semi-automated system for measurement of nuchal translucency thickness

Development of a semi-automated tool to measure fetal abdominal wall thickness during ultrasound at 20 weeks' gestation

OBJECTIVES

To develop a semi-automated tool for measuring fetal abdominal wall thickness (AWT). To validate the software using images captured by other centers and create a nomogram for fetal AWT between 18 and 20 weeks.

METHODS

A semiautomated tool that measured AWT was developed using images captured at the routine 20-week morphology scan. The software was developed using digital images captured routinely during scans of low-risk women. Inter- and intraobserver reliability was assessed between manual and semi-automated measures. The tool was validated using images acquired from other centers. Linear regression and quadratic polynomials were used to create a nomogram for AWT.

RESULTS

The semi-automated tool was able to measure AWT in all images. Interoperator reliability was 0.90 and 0.97 (P < 0.05) for manual and semi-automated methods, respectively. Measurement agreement varied between three operators from moderate to excellent (0.77, 0.87, 0.92), with overall agreement being good (0.85). The tool could be successfully applied to 89% of images from other centers. A nomogram was generated for AWT measurements of fetuses at 18-20 weeks in normal, low risk mothers.

CONCLUSION

Semi-automated measurement of AWT was feasible using images captured during the routine 20-week scan. This approach had lower inter- and intraobserver variability compared to manual measurement.

The 'Radiant Effect': Recent Sonographic Image-Enhancing Technique and Its Impact on Nuchal Translucency Measurements

Background: This study assesses the effects of the 'Radiant' image enhancement technique on fetal nuchal translucency (NT) measurements during first-trimester sonographic exams. Methods: A retrospective analysis of 263 ultrasound images of first-trimester midsagittal sections was conducted. NT measurements were obtained using a semi-automatic tool. Statistical methods were applied to compare NT measurements with and without 'Radiant' enhancement. An in vitro setup with predefined line distances provided additional data. Results: Incremental increases in NT measurements were observed with varying levels of 'Radiant' application: an average increase of 0.19 mm with 'Radiant min', 0.24 mm with 'Radiant mid', and 0.30 mm with 'Radiant max.' The in vitro results supported these findings, showing consistent effects on line thickness and measurement accuracy, with the smallest mean deviation occurring at the 'Radiant mid' setting. Conclusions: 'Radiant' image enhancement leads to significant increases in NT measurements. To avoid systematic biases in clinical assessments, it is advisable to disable 'Radiant' during NT measurement procedures. Further studies are necessary to corroborate these findings and to consider updates to the NT reference tables based on this technology.

Exploring the potential of machine learning in gynecological care: a review

Gynecological health remains a critical aspect of women's overall well-being, with profound implications for maternal and reproductive outcomes. This comprehensive review synthesizes the current state of knowledge on four pivotal aspects of gynecological health: preterm birth, breast cancer and cervical cancer and infertility treatment. Machine learning (ML) has emerged as a transformative technology with the potential to revolutionize gynecology and women's healthcare. The subsets of AI, namely, machine learning (ML) and deep learning (DL) methods, have aided in detecting complex patterns from huge datasets and using such patterns in making predictions. This paper investigates how machine learning (ML) algorithms are employed in the field of gynecology to tackle crucial issues pertaining to women's health. This paper also investigates the integration of ultrasound technology with artificial intelligence (AI) during the initial, intermediate, and final stages of pregnancy. Additionally, it delves into the diverse applications of AI throughout each trimester.This review paper provides an overview of machine learning (ML) models, introduces natural language processing (NLP) concepts, including ChatGPT, and discusses the clinical applications of artificial intelligence (AI) in gynecology. Additionally, the paper outlines the challenges in utilizing machine learning within the field of gynecology.

Deep-learning computer vision can identify increased nuchal translucency in the first trimester of pregnancy

OBJECTIVE

Many fetal anomalies can already be diagnosed by ultrasound in the first trimester of pregnancy. Unfortunately, in clinical practice, detection rates for anomalies in early pregnancy remain low. Our aim was to use an automated image segmentation algorithm to detect one of the most common fetal anomalies: a thickened nuchal translucency (NT), which is a marker for genetic and structural anomalies.

METHODS

Standardized mid-sagittal ultrasound images of the fetal head and chest were collected for 560 fetuses between 11 and 13 weeks and 6 days of gestation, 88 (15.7%) of whom had an NT thicker than 3.5 mm. Image quality was graded as high or low by two fetal medicine experts. Images were divided into a training-set (n = 451, 55 thick NT) and a test-set (n = 109, 33 thick NT). We then trained a U-Net convolutional neural network to segment the fetus and the NT region and computed the NT:fetus ratio of these regions. The ability of this ratio to separate thick (anomalous) NT regions from healthy, typical NT regions was first evaluated in ground-truth segmentation to validate the metric and then with predicted segmentation to validate our algorithm, both using the area under the receiver operator curve (AUROC).

RESULTS

The ground-truth NT:fetus ratio detected thick NTs with 0.97 AUROC in both the training and test sets. The fetus and NT regions were detected with a Dice score of 0.94 in the test set. The NT:fetus ratio based on model segmentation detected thick NTs with an AUROC of 0.96 relative to clinician labels. At a 91% specificity, 94% of thick NT cases were detected (sensitivity) in the test set. The detection rate was statistically higher (p = 0.003) in high versus low-quality images (AUROC 0.98 vs. 0.90, respectively).

CONCLUSION

Our model provides an explainable deep-learning method for detecting increased NT. This technique can be used to screen for other fetal anomalies in the first trimester of pregnancy.

Automatic measurement of fetal anterior neck lower jaw angle in nuchal translucency scans

This study aims at suggesting an end-to-end algorithm based on a U-net-optimized generative adversarial network to predict anterior neck lower jaw angles (ANLJA), which are employed to define fetal head posture (FHP) during nuchal translucency (NT) measurement. We prospectively collected 720 FHP images (half hyperextension and half normal posture) and regarded manual measurement as the gold standard. Seventy percent of the FHP images (half hyperextension and half normal posture) were used to fit models, and the rest to evaluate them in the hyperextension group, normal posture group (NPG), and total group. The root mean square error, explained variation, and mean absolute percentage error (MAPE) were utilized for the validity assessment; the two-sample t test, Mann-Whitney U test, Wilcoxon signed-rank test, Bland-Altman plot, and intraclass correlation coefficient (ICC) for the reliability evaluation. Our suggested algorithm outperformed all the competitors in all groups and indices regarding validity, except for the MAPE, where the Inception-v3 surpassed ours in the NPG. The two-sample t test and Mann-Whitney U test indicated no significant difference between the suggested method and the gold standard in group-level comparison. The Wilcoxon signed-rank test revealed significant differences between our new approach and the gold standard in personal-level comparison. All points in Bland-Altman plots fell between the upper and lower limits of agreement. The inter-ICCs of ultrasonographers, our proposed algorithm, and its opponents were graded good reliability, good or moderate reliability, and moderate or poor reliability, respectively. Our proposed approach surpasses the competition and is as reliable as manual measurement.

Artificial intelligence as a new answer to old challenges in maternal-fetal medicine and obstetrics

BACKGROUND

Following the latest trends in the development of artificial intelligence (AI), the possibility of processing an immense amount of data has created a breakthrough in the medical field. Practitioners can now utilize AI tools to advance diagnostic protocols and improve patient care.

OBJECTIVE

The aim of this article is to present the importance and modalities of AI in maternal-fetal medicine and obstetrics and its usefulness in daily clinical work and decision-making process.

METHODS

A comprehensive literature review was performed by searching PubMed for articles published from inception up until August 2023, including the search terms "artificial intelligence in obstetrics", "maternal-fetal medicine", and "machine learning" combined through Boolean operators. In addition, references lists of identified articles were further reviewed for inclusion.

RESULTS

According to recent research, AI has demonstrated remarkable potential in improving the accuracy and timeliness of diagnoses in maternal-fetal medicine and obstetrics, e.g., advancing perinatal ultrasound technique, monitoring fetal heart rate during labor, or predicting mode of delivery. The combination of AI and obstetric ultrasound can help optimize fetal ultrasound assessment by reducing examination time and improving diagnostic accuracy while reducing physician workload.

CONCLUSION

The integration of AI in maternal-fetal medicine and obstetrics has the potential to significantly improve patient outcomes, enhance healthcare efficiency, and individualized care plans. As technology evolves, AI algorithms are likely to become even more sophisticated. However, the successful implementation of AI in maternal-fetal medicine and obstetrics needs to address challenges related to interpretability and reliability.

Application and Progress of Artificial Intelligence in Fetal Ultrasound

Prenatal ultrasonography is the most crucial imaging modality during pregnancy. However, problems such as high fetal mobility, excessive maternal abdominal wall thickness, and inter-observer variability limit the development of traditional ultrasound in clinical applications. The combination of artificial intelligence (AI) and obstetric ultrasound may help optimize fetal ultrasound examination by shortening the examination time, reducing the physician's workload, and improving diagnostic accuracy. AI has been successfully applied to automatic fetal ultrasound standard plane detection, biometric parameter measurement, and disease diagnosis to facilitate conventional imaging approaches. In this review, we attempt to thoroughly review the applications and advantages of AI in prenatal fetal ultrasound and discuss the challenges and promises of this new field.

Use of artificial intelligence in obstetrics: not quite ready for prime time

Artificial intelligence is finding several applications in healthcare settings. This study aimed to report evidence on the effectiveness of artificial intelligence application in obstetrics. Through a narrative review of literature, we described artificial intelligence use in different obstetrical areas as follows: prenatal diagnosis, fetal heart monitoring, prediction and management of pregnancy-related complications (preeclampsia, preterm birth, gestational diabetes mellitus, and placenta accreta spectrum), and labor. Artificial intelligence seems to be a promising tool to help clinicians in daily clinical activity. The main advantages that emerged from this review are related to the reduction of inter- and intraoperator variability, time reduction of procedures, and improvement of overall diagnostic performance. However, nowadays, the diffusion of these systems in routine clinical practice raises several issues. Reported evidence is still very limited, and further studies are needed to confirm the clinical applicability of artificial intelligence. Moreover, better training of clinicians designed to use these systems should be ensured, and evidence-based guidelines regarding this topic should be produced to enhance the strengths of artificial systems and minimize their limits.

Applications of artificial intelligence in obstetrics

Artificial intelligence, which has been applied as an innovative technology in multiple fields of healthcare, analyzes large amounts of data to assist in disease prediction, prevention, and diagnosis, as well as in patient monitoring. In obstetrics, artificial intelligence has been actively applied and integrated into our daily medical practice. This review provides an overview of artificial intelligence systems currently used for obstetric diagnostic purposes, such as fetal cardiotocography, ultrasonography, and magnetic resonance imaging, and demonstrates how these methods have been developed and clinically applied.

Using deep-learning in fetal ultrasound analysis for diagnosis of cystic hygroma in the first trimester

Objective

To develop and internally validate a deep-learning algorithm from fetal ultrasound images for the diagnosis of cystic hygromas in the first trimester.

Methods

All first trimester ultrasound scans with a diagnosis of a cystic hygroma between 11 and 14 weeks gestation at our tertiary care centre in Ontario, Canada were studied. Ultrasound scans with normal nuchal translucency were used as controls. The dataset was partitioned with 75% of images used for model training and 25% used for model validation. Images were analyzed using a DenseNet model and the accuracy of the trained model to correctly identify cases of cystic hygroma was assessed by calculating sensitivity, specificity, and the area under the receiver-operating characteristic (ROC) curve. Gradient class activation heat maps (Grad-CAM) were generated to assess model interpretability.

Results

The dataset included 289 sagittal fetal ultrasound images;129 cystic hygroma cases and 160 normal NT controls. Overall model accuracy was 93% (95% CI: 88–98%), sensitivity 92% (95% CI: 79–100%), specificity 94% (95% CI: 91–96%), and the area under the ROC curve 0.94 (95% CI: 0.89–1.0). Grad-CAM heat maps demonstrated that the model predictions were driven primarily by the fetal posterior cervical area.

Conclusions

Our findings demonstrate that deep-learning algorithms can achieve high accuracy in diagnostic interpretation of cystic hygroma in the first trimester, validated against expert clinical assessment.

How much does depth matter? Magnetically controlled growing rod distraction directly influenced by rod tissue depth

PURPOSE

Magnetically controlled growing rod (MCGR) for the treatment of early-onset scoliosis (EOS) is a relatively innovative technique. MCGR benefits over traditional growing rods are known but limitations and complications are being revealed. The purpose of this study was to examine the importance of tissue depth on rod lengthening.

METHODS

A single-institution retrospective review of 72 MCGR patients was performed. Ultrasound measured rod distraction. Differences in programmed and actual distraction, and complications were recorded. Tissue depths and achieved length were averaged and used to construct a regression to account for variability.

RESULTS

Percentage of std and offset orientation rod lengthening relative to the programmed distraction was inversely proportional to rod depth (std R = 0.50, p = 0.002) (offset R = 0.60, p < 0.001). Expected std rod lengthening achieved decreased by 1.46%/mm depth. Expected offset rod lengthening achieved decreased by 1.68%/mm depth. 28 pts (38.9%) sustained complications. Age, sex, BMI, standard tissue depth, and/or offset tissue depth had no predictive ability with respect to complications sustained (overall model R = 0.31, p = 0.36).

CONCLUSION

In a series of EOS surgical patients treated with MCGRs, the relationship between percentage of programmed lengthening achieved as well as total lengthening was inversely proportional to tissue depth of the rod. There was a trend towards increasing frequency of complications recorded with decreasing tissue depth though this was not significant. These data can help with surgical planning during MCGR placement.

Artificial Intelligence in Obstetric Ultrasound: An Update and Future Applications

Artificial intelligence (AI) can support clinical decisions and provide quality assurance for images. Although ultrasonography is commonly used in the field of obstetrics and gynecology, the use of AI is still in a stage of infancy. Nevertheless, in repetitive ultrasound examinations, such as those involving automatic positioning and identification of fetal structures, prediction of gestational age (GA), and real-time image quality assurance, AI has great potential. To realize its application, it is necessary to promote interdisciplinary communication between AI developers and sonographers. In this review, we outlined the benefits of AI technology in obstetric ultrasound diagnosis by optimizing image acquisition, quantification, segmentation, and location identification, which can be helpful for obstetric ultrasound diagnosis in different periods of pregnancy.

Automatic Fetal Middle Sagittal Plane Detection in Ultrasound Using Generative Adversarial Network

Background and Objective: In the first trimester of pregnancy, fetal growth, and abnormalities can be assessed using the exact middle sagittal plane (MSP) of the fetus. However, the ultrasound (US) image quality and operator experience affect the accuracy. We present an automatic system that enables precise fetal MSP detection from three-dimensional (3D) US and provides an evaluation of its performance using a generative adversarial network (GAN) framework. Method: The neural network is designed as a filter and generates masks to obtain the MSP, learning the features and MSP location in 3D space. Using the proposed image analysis system, a seed point was obtained from 218 first-trimester fetal 3D US volumes using deep learning and the MSP was automatically extracted. Results: The experimental results reveal the feasibility and excellent performance of the proposed approach between the automatically and manually detected MSPs. There was no significant difference between the semi-automatic and automatic systems. Further, the inference time in the automatic system was up to two times faster than the semi-automatic approach. Conclusion: The proposed system offers precise fetal MSP measurements. Therefore, this automatic fetal MSP detection and measurement approach is anticipated to be useful clinically. The proposed system can also be applied to other relevant clinical fields in the future.

A Novel Intelligent Scan Assistant System for Early Pregnancy Diagnosis by Ultrasound: Clinical Decision Support System Evaluation Study

Background

Early pregnancy ultrasound scans are usually performed by nonexpert examiners in obstetrics/gynecology (OB/GYN) emergency departments. Establishing the precise diagnosis of pregnancy location is key for appropriate management of early pregnancies, and experts are usually able to locate a pregnancy in the first scan. A decision-support system based on a semantic, expert-validated knowledge base may improve the diagnostic performance of nonexpert examiners for early pregnancy transvaginal ultrasound.

Objective

This study aims to evaluate a novel Intelligent Scan Assistant System for early pregnancy ultrasound to diagnose the pregnancy location and determine the image quality.

Methods

Two trainees performed virtual transvaginal ultrasound examinations of early pregnancy cases with and without the system. The ultrasound images and reports were blindly reviewed by two experts using scoring methods. A diagnosis of pregnancy location and ultrasound image quality were compared between scans performed with and without the system.

Results

Each trainee performed a virtual vaginal examination for all 32 cases with and without use of the system. The analysis of the 128 resulting scans showed higher quality of the images (quality score: +23%; P<.001), less images per scan (4.6 vs 6.3 [without the CDSS]; P<.001), and higher confidence in reporting conclusions (trust score: +20%; P<.001) with use of the system. Further, use of the system cost an additional 8 minutes per scan. We observed a correct diagnosis of pregnancy location in 39 (61%) and 52 (81%) of 64 scans in the nonassisted mode and assisted mode, respectively. Additionally, an exact diagnosis (with precise ectopic location) was made in 30 (47%) and 49 (73%) of the 64 scans without and with use of the system, respectively. These differences in diagnostic performance (+20% for correct location diagnosis and +30% for exact diagnosis) were both statistically significant (P=.002 and P<.001, respectively).

Conclusions

The Intelligent Scan Assistant System is based on an expert-validated knowledge base and demonstrates significant improvement in early pregnancy scanning, both in diagnostic performance (pregnancy location and precise diagnosis) and scan quality (selection of images, confidence, and image quality).

Prenatal Screening Markers for Down Syndrome: Sensitivity, Specificity, Positive and Negative Expected Value Method

Background

Genetic screening for chromosomopathy is performed in the first trimester of pregnancy by determining fetal nuchal translucency (NT), and the pregnancy associated plasma protein-A (PAPP-A) and free human chorionic gonadotropin (free-beta HCG) biomarkers in maternal serum.

Methods

We tested the sensitivity, specificity, positive and negative expected values of each marker with the aim of setting a model for prenatal screening readings. Statistical data treatment has been performed on a sample of 340 pregnant women with positive results of prenatal screening.

Results

Sensitivity of PAPP-A was 0.6250 (probability 62.50%), free beta HCG 0.5893 (58.93%), NT 0.1785 (17.85%). Specificity of PAPP-A was 0.5106 (probability 51.06%), free beta HCG 0.5246 (52.46%), NT 0.9718 (97.18%). Positive expected value of PAPP-A was 0.2011 (probability 20.11%), free beta HCG 0.1964 (19.64%), NT 0.556 (55.56%). Negative expected value of PAPP-A was 0.8735 (probability 87.35%), free beta HCG 0.8662 (86.62%), NT 0.8571 (85.71%). The NT marker has a significantly higher specificity, which means that its normal value will significantly reduce the final risk of trisomy 21. The sensitivity of NT is much lower than that of biochemical markers, which means that a pathological value of NT does not have a significant influence on the final risk, i.e. the significantly higher sensitivity of biochemical markers will reduce the final risk of trisomy 21.

Conclusions

The analyses stress the importance of using a software which has the possibility to separate the level of a biochemical risk by correlating PAPP-A and free beta HCG and, by adding the NT marker, calculate the level of a final risk of Down syndrome.

Automated localization and segmentation techniques for B-mode ultrasound images: A review

B-mode ultrasound imaging is used extensively in medicine. Hence, there is a need to have efficient segmentation tools to aid in computer-aided diagnosis, image-guided interventions, and therapy. This paper presents a comprehensive review on automated localization and segmentation techniques for B-mode ultrasound images. The paper first describes the general characteristics of B-mode ultrasound images. Then insight on the localization and segmentation of tissues is provided, both in the case in which the organ/tissue localization provides the final segmentation and in the case in which a two-step segmentation process is needed, due to the desired boundaries being too fine to locate from within the entire ultrasound frame. Subsequenly, examples of some main techniques found in literature are shown, including but not limited to shape priors, superpixel and classification, local pixel statistics, active contours, edge-tracking, dynamic programming, and data mining. Ten selected applications (abdomen/kidney, breast, cardiology, thyroid, liver, vascular, musculoskeletal, obstetrics, gynecology, prostate) are then investigated in depth, and the performances of a few specific applications are compared. In conclusion, future perspectives for B-mode based segmentation, such as the integration of RF information, the employment of higher frequency probes when possible, the focus on completely automatic algorithms, and the increase in available data are discussed.

Automatic detection and measurement of nuchal translucency

In this paper we propose a new methodology to support the physician both to identify automatically the nuchal region and to obtain a correct thickness measurement of the nuchal translucency. The thickness of the nuchal translucency is one of the main markers for screening of chromosomal defects such as trisomy 13, 18 and 21. Its measurement is performed during ultrasound scanning in the first trimester of pregnancy. The proposed methodology is mainly based on wavelet and multi resolution analysis. The performance of our method was analysed on 382 random frames, representing mid-sagittal sections, uniformly extracted from real clinical ultrasound videos of 12 patients. According to the ground-truth provided by an expert physician, we obtained a true positive rate equal to 99.95% with respect to the nuchal region detection and about 64% of measurements present an error equal to 1 pixel (which corresponds to 0.1mm), respectively.

True Reproducibility of UltraSound Techniques (TRUST): systematic review of reliability studies in obstetrics and gynecology

OBJECTIVES

To examine the quality of methods used and the accuracy of the interpretation of agreement in existing studies that examine the reliability of ultrasound measurements and judgments in obstetrics and gynecology.

METHODS

A systematic search of MEDLINE was performed on 25 March 2014, looking for studies that examined the reliability of ultrasound measurements and judgments in obstetrics and gynecology with evaluation of concordance (CCC) or intraclass (ICC) correlation coefficients or kappa as a main objective.

RESULTS

Seven hundred and thirty-three records were examined on the basis of their title and abstract, of which 141 full-text articles were examined completely for eligibility. We excluded 29 studies because they did not report CCC/ICC/kappa, leaving 112 studies that were included in our analysis. Two studies reported both ICC and kappa and were counted twice, therefore, the number used as the denominator in the analyses was 114. Only 16/114 (14.0%) studies were considered to be well designed (independent acquisition and blinded analysis) and to have interpreted the results properly. Most errors occurring in the studies are likely to overestimate the reliability of the method examined.

CONCLUSIONS

The vast majority of published studies examined had important flaws in design, interpretation and/or reporting. Such limitations are important to identify as they might create false confidence in the existing measurements and judgments, jeopardizing clinical practice and future research. Specific guidelines aimed at improving the quality of reproducibility studies that examine ultrasound methods should be encouraged.

Optimal caliper placement: manual vs automated methods

OBJECTIVE

To examine the inter- and intra-operator repeatability of manual placement of callipers in the assessment of basic biometric measurements and to compare the results to an automated calliper placement system.

METHODS

Stored ultrasound images of 95 normal fetuses between 19 and 25 weeks' gestation were used. Five operators (two experts, one resident and two students) were asked to measure the BPD, OFD and FL two times manually and automatically. For each operator, intra-operator repeatability of the manual and automated measurements was assessed by within operator standard deviation. For the assessment of the interoperator repeatability, the mean of the four manual measurements by the two experts was used as the gold standard.The relative bias of the manual measurement of the three non-expert operators and the operator-independent automated measurement were compared with the gold standard measurement by means and 95% confidence interval.

RESULTS

In 88.4% of the 95 cases, the automated measurement algorithm was able to obtain appropriate measurements of the BPD, OFD, AC and FL. Within operator standard deviations of the manual measurements ranged between 0.15 and 1.56, irrespective of the experience of the operator.Using the automated biometric measurement system, there was no difference between the measurements of each operator. As far as the inter-operator repeatability is concerned, the difference between the manual measurements of the two students, the resident, and the gold standard was between -0.10 and 2.53 mm. The automated measurements tended to be closer to the gold standard but did not reach statistical significance.

CONCLUSION

In about 90% of the cases, it was possible to obtain basic biometric measurements with an automated system. The use of automated measurements resulted in a significant improvement of the intra-operator but not of the inter-operator repeatability, but measurements were not significantly closer to the gold standard of expert examiners.

Multimodality 3-dimensional volumetric ultrasound in obstetrics and gynecology with an emphasis in HDlive technique

HDlive (high-definition live or real-time US), a new ultrasound software, combines a movable virtual adjustable light source in a software that calculates the proportion of light reflecting through surface structures, depending on light direction. The light source can be manually positioned to illuminate the desired area of interest. The ultrasound technician can control light intensity to create shadows that enhance image quality. HDlive is an innovation that will render even more realistic images of fetal anatomy and of gynecologic lesions. The full potential of this new technology is yet to be determined and deserves scientific evaluation.

The influence of image setting on intracranial translucency measurement by manual and semi-automated system

OBJECTIVE

To investigate the agreement between manual and semi-automated system and the effect of different image settings on intracranial translucency (IT) measurement.

METHODS

A prospective study was conducted on 55 women carrying singleton pregnancy who attended first trimester Down syndrome screening. IT was measured both manually and by semi-automated system at the same default image setting. The IT measurements were then repeated with the post-processing changes in the image setting one at a time. The difference in IT measurements between the altered and the original images were assessed.

RESULTS

Intracranial translucency was successfully measured on 55 images both manually and by semi-automated method. There was strong agreement in IT measurements between the two methods with a mean difference (manual minus semi-automated) of 0.011 mm (95% confidence interval--0.052 mm-0.094 mm). There were statistically significant variations in both manual and semi-automated IT measurement after changing the Gain and the Contrast. The greatest changes occurred when the Contrast was reduced to 1 (IT reduced by 0.591 mm in semi-automated; 0.565 mm in manual), followed by when the Gain was increased to 15 (IT reduced by 0.424 mm in semi-automated; 0.524 mm in manual).

CONCLUSIONS

The image settings may affect IT identification and measurement. Increased Gain and reduced Contrast are the most influential factors and may cause under-measurement of IT.

Reliability of manual and semi-automated measurements of nuchal translucency by experienced operators

OBJECTIVE

To compare intra-/inter-operator reliability of manual and semi-automated NT measurement by experienced operators.

METHODS

Images of 103 fetuses at 11 to 13+6weeks were selected. Two operators performed NT measurement independently 3 times each using both manual and semi-automated methods. Intraoperator reliability of the methods was evaluated using ICCs; interoperator reliability was assessed via correlation between the means of the 3 measurements of each operator. Agreement between the 2 methods was evaluated via Bland-Altman plot.

RESULTS

ICCs for the manual method were 0.80 (95% CI, 0.73-0.85) for operator 1 and 0.82 (95% CI, 0.76-0.87) for operator 2; ICCs for the semi-automated method were 0.80 (95% CI, 0.74-0.85) for operator 1 and 0.82 (95% CI, 0.76-0.86) for operator 2. Interoperator reliability for both methods was high: correlation coefficients 0.91 (95% CI, 0.87-0.94) and 0.96 (95% CI, 0.94-0.97) for manual and semi-automated methods, respectively. Mean NT measured by manual and semi-automated methods was 1.15mm and 1.28mm, respectively (P<0.001). Agreement between the methods was good.

CONCLUSION

The reliability of semi-automated NT measurements was comparable to that of the manual method. The new method was reproducible and may be used instead of the manual method in the normal range of NT.

Automatic nuchal translucency measurement from ultrasonography

This paper proposes a fully automatic approach for computing Nuchal Translucency (NT) measurement in an ultrasound scans of the mid-sagittal plane of a fetal head. This is an improvement upon current NT measurement methods which require manual placement of NT measurement points or user-guidance in semi-automatic segmentation of the NT region. The algorithm starts by finding the pose of the fetal head using discriminative learning-based detectors. The fetal head serves as a robust anchoring structure and the NT region is estimated from the statistical relationship between the fetal head and the NT region. Next, the pose of the NT region is locally refined and its inner and outer edge approximately determined via Dijkstra's shortest path applied on the edge-enhanced image. Finally, these two region edges are used to define foreground and background seeds for accurate graph cut segmentation. The NT measurement is computed from the segmented region. Experiments show that the algorithm efficiently and effectively detects the NT region and provides accurate NT measurement which suggests suitability for clinical use.

Umbilical venous blood flow and its measurement in the human fetus

In this review, we evaluate the published methodologies to describe a noninvasive technique for the quantitative assessment of umbilical venous blood flow in the human fetus. We identify a number of variations in the reported methodologies and address some of the common errors associated with Doppler assessment of umbilical venous flow volume. The potential role of umbilical venous flow volumetry in the management of intrauterine growth restriction is briefly evaluated including its utility and reliability in everyday clinical practice.

A new automatic algorithm to extract craniofacial measurements from fetal three-dimensional volumes

OBJECTIVES

Three-dimensional (3D) ultrasound is useful in the prenatal evaluation of fetal craniofacial structures, particularly as it provides a multiplanar view. However, an expert must designate the area of interest and the appropriate view, making measurement of fetal structures using 3D ultrasound both time-consuming and subjective. In this study we propose an image analysis system that measures automatically and precisely the fetal craniofacial structures and evaluate its performance in the second trimester of pregnancy using a new 3D volume analysis algorithm.

METHODS

A universal facial surface template model containing the geometric shape information of a fetal craniofacial structure was constructed from a fetal phantom. Using the proposed image analysis system we fitted this stored template model using a model deformation approach to individual fetal 3D facial volumes from 11 mid-trimester fetuses, and extracted automatically the following standard measurements: biparietal diameter (BPD), occipitofrontal diameter (OFD), interorbital diameter (IOD), bilateral orbital diameter (BOD) and distance between vertex and nasion (VN). The same five parameters were measured manually by an expert and the results compared.

RESULTS

Comparison of the algorithm-based automatic measurements with manual measurements made by an expert gave correlation coefficients of 0.99 for BPD, 0.98 for OFD, 0.80 for BOD, 0.83 for IOD and 0.99 for VN. There were no significant differences between automatic and manual measurements.

CONCLUSION

Our proposed system measures precisely the fetal craniofacial structures using 3D ultrasound, making it potentially useful for clinical service. This system could also be applied to other clinical fields in future testing.

Comparison of nuchal translucency measurements obtained using Volume NT(TM) and two- and three-dimensional ultrasound

OBJECTIVE

To evaluate the feasibility of Volume NT(TM) , a new technique that automatically archives mid-sagittal plane views and measures the maximum nuchal translucency (NT) thickness, by comparing its measurements with those made with conventional two- (2D) and three-dimensional (3D) techniques.

METHODS

This was a prospective study of 130 singleton pregnancies undergoing NT screening at 11 + 0 to 13 + 6 weeks of gestation. Fetuses with enlarged NT or multiple anomalies and those in the prone position were excluded. Success rate of NT measurement was assessed using Volume NT(TM) , 2D and 3D techniques. In cases in which all three techniques were successful, intra- and interobserver bias and levels of agreement for NT measurements within and between techniques were evaluated using Bland-Altman plots.

RESULTS

Of 130 cases enrolled into the study, 16 were excluded from analysis due to enlarged NT (n = 3), prone position (n = 2) or missing data (n = 11). Among the 114 cases analyzed, NT measurement was successful by the conventional 2D method in 95.6% (109/114) of cases and by 3D and Volume NT(TM) measurements in 103 and 93 cases, respectively. Success rate was not significantly different between methods. In 89 cases, NT values were available using all three methods. Among them, mean ± SD 2D-NT was 1.3 ± 0.4 mm, 3D-NT was 1.2 ± 0.4 mm and Volume NT(TM) was 1.3 ± 0.4 mm. The mean differences of the intra- and interobserver variability of each method were not significantly different from zero for each method.

CONCLUSIONS

Volume NT(TM) , a novel technique for automated NT measurement, is apparently reproducible and comparable with conventional 2D and 3D ultrasound techniques for NT measurement.

Intra- and interoperator reliability of manual and semi-automated measurements of intracranial translucency

OBJECTIVES

To assess the reproducibility of fetal intracranial translucency (IT) measurements performed manually or with SonoNT(®), a semi-automated caliper placement technique recently introduced for nuchal translucency thickness (NT) measurement.

METHODS

This was a retrospective study using 116 stored images of the head (mid-sagittal plane) from normal fetuses in dorsoposterior position at 11-13 weeks. Two experienced operators each measured the IT separately, twice manually and twice using the semi-automated software. Intraoperator and interoperator repeatability were assessed. The mean of the two manual measurements of the more experienced Operator 2 was considered as the 'gold standard'.

RESULTS

Seven cases were excluded as the IT could not be recognized by the semi-automated software. In the remaining 109 cases, the interquartile range of the mean IT measurement was 1.9-2.4 mm for Operator 1 and 1.8-2.3 mm for Operator 2 for both the manual and the semi-automated IT measurements. The intraoperator SD for manual measurements was 0.091 mm for Operator 1 and 0.088 mm for Operator 2, and for semi-automated measurements it was 0.054 mm for Operator 1 and 0.067 mm for Operator 2. Concerning interoperator bias of the manual measurements, the mean difference between Operator 1 and Operator 2 was - 0.09 (95% CI, - 0.11 to - 0.07) mm. With respect to the gold standard, the mean bias of the semi-automated measurements was 0.01 (95% CI - 0.01 to 0.03) mm for Operator 1 and - 0.09 (95% CI - 0.11 to - 0.07) mm for Operator 2, indicating good agreement.

CONCLUSIONS

Manual IT measurements are reproducible. In addition, IT can be assessed reliably using the semi-automated NT algorithm, leading to standardization of the IT assessment process.

Effect of image settings on nuchal translucency thickness measurement by a semi-automated system

OBJECTIVE

To investigate whether pre- and post-processing image settings affect NT measurements made by a semi-automatic method (SAM).

METHODS

Different image settings (e.g. gain) were either adjusted one at a time on images that had been obtained during fetal NT scans (post-processing, n = 66), or adjusted one at a time during live scanning and image acquisition of the adult posterior tibial artery (pre-processing group, n = 91). The NT and luminal diameter of the posterior tibial artery, respectively, were measured by SAM on all original and adjusted images.

RESULTS

Alteration of the image settings resulted in a statistically significant effect on the measurements taken by SAM, with an average pair difference ranging from 0.001 mm to 0.139 mm. Most of the differences were small and therefore the clinical impact would be negligible. The pair differences were greatest with a very high contrast setting, or without tissue harmonic imaging (THI); the paired difference in measurement in those with vs those without THI was more than 0.1 mm in over 40% of cases.

CONCLUSIONS

Measurements made by SAM are affected by image settings.