Automatic image quality assessment and measurement of fetal head in two-dimensional ultrasound image

Abstract

Abstract. Owing to the inconsistent image quality existing in routine obstetric ultrasound (US) scans that leads to a large intraobserver and interobserver variability, the aim of this study is to develop a quality-assured, fully automated US fetal head measurement system. A texton-based fetal head segmentation is used as a prerequisite step to obtain the head region. Textons are calculated using a filter bank designed specific for US fetal head structure. Both shape-and anatomic-based features calculated from the segmented head region are then fed into a random forest classifier to determine the quality of the image (e.g., whether the image is acquired from a correct imaging plane), from which fetal head measurements [biparietal diameter (BPD), occipital-frontal diameter (OFD), and head circumference (HC)] are derived. The experimental results show a good performance of our method for US quality assessment and fetal head measurements. The overall precision for automatic image quality assessment is 95.24% with 87.5% sensitivity and 100% specificity, while segmentation performance shows 99.27% (AE0.26) of accuracy, 97.07% (AE2.3) of sensitivity, 2.23 mm (AE0.74) of the maximum symmetric contour distance, and 0.84 mm (AE0.28) of the average symmetric contour distance. The statistical analysis results using paired t -test and Bland-Altman plots analysis indicate that the 95% limits of agreement for inter observer variability between the automated measurements and the senior expert measurements are 2.7 mm of BPD, 5.8 mm of OFD, and 10.4 mm of HC, whereas the mean differences are −0.038 AE 1.38 mm, −0.20 AE 2.98 mm, and −0.72 AE 5.36 mm, respectively. These narrow 95% limits of agreements indicate a good level of consistency between the automated and the senior expert's measurements.

Are ultrasound foetal circumference measurement methods interchangeable?

“…Intra-and inter-observer variability will remain a limiting factor in foetal biometry and growth assessment; 14,15 in the future this may be addressed by automated measurement 16 and automated quality assessment. 17 Foetal circumference measurement methods are not interchangeable when assessing foetal growth or estimating foetal weight. A standardised method and appropriate charts should be used; since much guidance suggests the use of the derived method and widely used charts and EFW formulae were based on this method, it should be used until evidence supporting change is available.…”

“…Intra- and inter-observer variability will remain a limiting factor in foetal biometry and growth assessment; 14,15 in the future this may be addressed by automated measurement 16 and automated quality assessment. 17…”

Robotic Ultrasound Scanning With Real-Time Image-Based Force Adjustment: Quick Response for Enabling Physical Distancing During the COVID-19 Pandemic

“…US image's quality is usually defined as an ability to see some tissue features or organs in the image. The method proposed in Zhang et al ( 2017 ) developed a method of segmenting the fetus in an US image, using a texton method on the image. The texton method performs segmentation and feature extraction, and a random forest classifier assesses the quality of the image based on the extracted features.…”

Ultrasound Medical Images Classification Based on Deep Learning Algorithms: A Review

“…Methods were tested for automated calculation of gestation age by head, neck, and spine measurement relevant to calculating gestation age [66]. An adaptive approach is used to segment the tissue, in which conventional image processing methods are used [67], or for standard machine learning methods , etc.…”