Investigation of the Role of Feature Selection and Weighted Voting in Random Forests for 3-D Volumetric Segmentation

• Published in: IEEE transactions on medical imaging Vol. 33; no. 2; pp. 258 - 271
• Main Authors: Yaqub, M., Javaid, M. K., Cooper, C., Noble, J. A.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adult; Algorithms; Biomedical imaging; Brain; Brain - anatomy & histology; Brain magnetic resonance imaging (MRI) segmentation; Classification; Decision Trees; feature selection; Female; Femur - diagnostic imaging; Forests; Humans; Image segmentation; Imaging, Three-Dimensional - methods; Magnetic Resonance Imaging - methods; Pregnancy; Radio frequency; Random Forests (RFs); Segmentation; State of the art; Testing; Three dimensional; three- dimensional (3-D) fetal ultrasound segmentation; Three-dimensional displays; Training; Ultrasonography, Prenatal; Ultrasound; Vegetation
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2013.2284025

This paper describes a novel 3-D segmentation technique posed within the Random Forests (RF) classification framework. Two improvements over the traditional RF framework are considered. Motivated by the high redundancy of feature selection in the traditional RF framework, the first contribution develops methods to improve voxel classification by selecting relatively "strong" features and neglecting "weak" ones. The second contribution involves weighting each tree in the forest during the testing stage, to provide an unbiased and more accurate decision than provided by the traditional RF. To demonstrate the improvement achieved by these enhancements, experimental validation is performed on adult brain MRI and 3-D fetal femoral ultrasound datasets. In a comparison of the new method with a traditional Random Forest, the new method showed a notable improvement in segmentation accuracy. We also compared the new method with other state-of-the-art techniques to place it in context of the current 3-D medical image segmentation literature.