Automated ultrasound segmentation technique for placental volume determination
Fetal growth restriction during pregnancy can lead to a variety of complications, including still birth and increased risk of cardiovascular and metabolic disease later in life. Placental volume can be used to predict adverse regency outcomes, including risk of an infant being small for gestational age; however, determination of placental volume is time consuming, requiring an operator to manually identify and annotate the placenta. In this episode, Sally Collins and Pádraig Looney describe the development of a technique that allows for automated segmentation of the placenta and volume determination from 3D ultrasound images. This technique has potential for wide-spread use for predicting small gestational age.
Related articles
Abstract
We present a new technique to fully automate the segmentation of an organ from 3D ultrasound (3D-US) volumes, using the placenta as the target organ. Image analysis tools to estimate organ volume do exist but are too time consuming and operator dependant. Fully automating the segmentation process would potentially allow the use of placental volume to screen for increased risk of pregnancy complications. The placenta was segmented from 2,393 first trimester 3D-US volumes using a semiautomated technique. This was quality controlled by three operators to produce the “ground-truth” data set. A fully convolutional neural network (OxNNet) was trained using this ground-truth data set to automatically segment the placenta. OxNNet delivered state-of-the-art automatic segmentation. The effect of training set size on the performance of OxNNet demonstrated the need for large data sets. The clinical utility of placental volume was tested by looking at predictions of small-for-gestational-age babies at term. The receiver-operating characteristics curves demonstrated almost identical results between OxNNet and the ground-truth). Our results demonstrated good similarity to the ground-truth and almost identical clinical results for the prediction of SGA.
Authors
Pádraig Looney, Gordon N. Stevenson, Kypros H. Nicolaides, Walter Plasencia, Malid Molloholli, Stavros Natsis, Sally L. Collins
