Segmentation of ultrasound images of fetal anatomic structures using random forest for low-cost settings
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2015 (1094687X) , 793-796
Abstract
In ultrasound imaging, manual extraction of contours of fetal anatomic structures from echographic images have been found to be very challenging due to speckles and low contrast characteristic features. Contours extracted are therefore associated with variability of human observers. In this case, the contours that are extracted are not reproducible and hence not reliable. This challenge has called for the need to develop a method that can accurately segment the fetal anatomic structures. This will help to estimate and measure the contours of the structures of fetal bodies such as the head circumference, femur length, etc. Most recent methods are able to integrate global shape and appearance. The drawback to most of these methods is that, they are not able to handle localized appearance variations. They only rely on an assumption of Gaussian gray value distribution and also require initialization near the optimal solution. In this manuscript random forest is used to segment head contour in fetal ultrasound scans acquired in low-cost settings, such as acquisition performed in rural areas of low-income countries using low-cost portable machines.Keywords
This publication has 10 references indexed in Scilit:
- Evaluation and Comparison of Current Fetal Ultrasound Image Segmentation Methods for Biometric Measurements: A Grand ChallengeIEEE Transactions on Medical Imaging, 2013
- Fetal cranial segmentation in 2D ultrasound images using shape properties of pixel clusters2013
- Decision Forests for Computer Vision and Medical Image Analysis2013
- Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised LearningFoundations and Trends in Computer Graphics and Vision, 2012
- Statistical Region-Based Segmentation of Ultrasound ImagesUltrasound in Medicine & Biology, 2009
- Detection and Measurement of Fetal Anatomies from Ultrasound Images using a Constrained Probabilistic Boosting TreeIEEE Transactions on Medical Imaging, 2008
- Object Class Segmentation using Random Forests2008
- Maximum likelihood segmentation of ultrasound images with Rayleigh distributionIEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2005
- Segmentation of fetal ultrasound imagesUltrasound in Medicine & Biology, 2005
- ULTRASONIC MEASUREMENT OF FETAL ABDOMEN CIRCUMFERENCE IN THE ESTIMATION OF FETAL WEIGHTBJOG: An International Journal of Obstetrics & Gynaecology, 1975