Fetal Skull Segmentation in 3D Ultrasound via Structured Geodesic Random Forest
Ultrasound is the primary imaging method for prenatal screening and diagnosis of fetal anomalies. Thanks to its non-invasive and non-ionizing properties, ultrasound allows quick, safe and detailed evaluation of the unborn baby, including the estimation of the gestational age, brain and cranium development. However, the accuracy of traditional 2D fetal biometrics is dependent on operator expertise and subjectivity in 2D plane finding and manual marking. 3D ultrasound has the potential to reduce the operator dependence. In this paper, we propose a new random forest-based segmentation framework for fetal 3D ultrasound volumes, able to efficiently integrate semantic and structural information in the classification process. We introduce a new semantic features space able to encode spatial context via generalized geodesic distance transform. Unlike alternative auto-context approaches, this new set of features is efficiently integrated into the same forest using contextual trees. Finally, we use a new structured labels space as alternative to the traditional atomic class labels, able to capture morphological variability of the target organ. Here, we show the potential of this new general framework segmenting the skull in 3D fetal ultrasound volumes, significantly outperforming alternative random forest-based approaches.
KeywordsRandom forest Generalized geodesic distance Structured class
This research was supported in part by the Marie Sklodowska-Curie Actions of the EU Framework Programme for Research and Innovation, under REA grant agreement 706372.
- 3.International Society of Ultrasound in Obstetrics and Gynecology: Sonographic examination of the fetal central nervous system: Guidelines for performing the basic examination and the fetal neurosonogram. Ultrasound Obstet. Gynecol. 29, 109–116(2007)Google Scholar
- 5.Shen, Y., et al.: Fetal skull analysis in ultrasound images based on iterative randomized Hough transform. SPIE 7265 (2009)Google Scholar
- 6.Namburete, A.I.L., Noble, J.A.: Fetal cranial segmentation in 2D ultrasound images using shape properties of pixel clusters (2013). ISBI: 720–723Google Scholar
- 10.Dollar, P., Zitnick, C.: Structured forests for fast edge detection. In: Proceedings of the ICCV, pp. 1841–1848 (2013)Google Scholar
- 11.Kontschieder, P., et al.: GeoF: Geodesic forests for learning coupled predictors. In: Proceedings of the CVPR (2013)Google Scholar
- 12.Oktay, O., et al.: Stratified decision forests for accurate anatomical landmark localization in cardiac images. TMI 36(1), 332–342 (2017)Google Scholar
- 15.Butt, K., Lim, K.: Determination of Gestational Age by Ultrasound. SOGC Clinical Practice Guidelines, 303 (2015)Google Scholar