EP01.13: A new method for placental volume measurements using tracked two‐dimensional ultrasound and automatic image segmentation

Placental volume measurements can potentially identify high-risk pregnancies. However, with currently available ultrasound modalities, placental volume measurements are unreliable. We aimed to develop and validate a new method for placental volume measurement using a two-dimensionsal (2D) ultrasound probe with position tracking and automatic image segmentation. We included 43 pregnancies at gestational week 27 and acquired placental images by a 2D ultrasound probe with position tracking. The probe could be freely moved and thus view the whole placenta. We segmented 2583 2D images manually and trained a convolutional neural network (CNN) for automatic image segmentation. The automatically segmented 2D images were combined with tracking data to create a 3D placenta and calculate the placental volume, this was also done based on manually segmented 2D images. For 15 of the included pregnancies, placental volume was also estimated based on MRI examinations. The MRI images of the placentas were manually segmented, and the calculated volume based on MRI was used as our gold standard. The CNN demonstrated good performance in automatic image segmentation, achieving an F1-score of 0.84. The correlation between tracked 2D ultrasound using automatically segmented images and MRI-based placental volume measurements (absolute agreement intraclass correlation coefficient (ICC) 0.58, 95% CI 0.13–0.84) was similar to the correlation between placental volume based on manually segmented 2D images and MRI-based placental volume (ICC 0.59 95% CI 0.13–0.84). Tracked 2D ultrasound with automatic image segmentation is a promising new method for placental volume measurements. Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.