Developing and testing an algorithm for automatic segmentation of the fetal face from three-dimensional ultrasound images

Abstract

Fetal craniofacial abnormalities are challenging to detect and diagnose on prenatal ultrasound (US). Image segmentation and computer analysis of three-dimensional US volumes of the fetal face may provide an objective measure to quantify fetal facial features and identify abnormalities. We have developed and tested an atlas-based partially automated facial segmentation algorithm; however, the volumes require additional manual segmentation (MS), which is time and labour intensive and may preclude this method from clinical adoption. These manually refined segmentations can then be used as a reference (atlas) by the partially automated segmentation algorithm to improve algorithmic performance with the aim of eliminating the need for manual refinement and developing a fully automated system. This study assesses the inter- and intra-operator variability of MS and tests an optimized version of our automatic segmentation (AS) algorithm. The manual refinements of 15 fetal faces performed by three operators and repeated by one operator were assessed by Dice score, average symmetrical surface distance and volume difference. The performance of the partially automatic algorithm with difference size atlases was evaluated by Dice score and computational time. Assessment of the manual refinements showed low inter- and intra-operator variability demonstrating its suitability for optimizing the AS algorithm. The algorithm showed improved performance following an increase in the atlas size in turn reducing the need for manual refinement.

Keywords: craniofacial abnormalities; image segmentation; three-dimensional ultrasound.

Figure 1.

Example of an automatically segmented (AS) fetal face before (left) and after (right) manual refinement of the AS has been performed.

Figure 2.

Examples of the segmentation produced by the automatic algorithm (top), the corresponding 3D US volume (middle) and the final segmentation following manual refinement (bottom).

Figure 3.

A schematic of the workflow for this study. The manual refinements of Op_1_#1 were then progressively added to the original set of 20 images in order to increase the atlas size.

Figure 4.

Rendering of the lowest (left column) and highest (right column) MS agreement between the three operators and repeated segmentation of operator 1 as assessed by the Dice score.

Figure 5.

Dice score (a), segmentation volume (c) and computational time (e) plotted for each AS, and boxplot of their distribution (b,d,f) obtained with the different atlases tested.

Figure 6.

Lowest (top) and highest (bottom) Dice scores for the AS of each atlas: for A_20 (red), A_25 (blue), A_30 (green) and A_35 (orange) compared to the MS (white) as assessed by the Dice score.