Uncertainty-driven forest predictors for vertebra localization and segmentation

Item Type:	Article
Title:	Uncertainty-driven forest predictors for vertebra localization and segmentation
Creators Name:	Richmond, D. and Kainmueller, D. and Glocker, B. and Rother, C. and Myers, G.
Abstract:	Accurate localization, identification and segmentation of vertebrae is an important task in medical and biological image analysis. The prevailing approach to solve such a task is to first generate pixelindependent features for each vertebra, e.g. via a random forest predictor, which are then fed into an MRF-based objective to infer the optimal MAP solution of a constellation model. We abandon this static, twostage approach and mix feature generation with model-based inference in a new, more flexible, way. We evaluate our method on two data sets with different objectives. The first is semantic segmentation of a 21-part body plan of zebrafish embryos in microscopy images, and the second is localization and identification of vertebrae in benchmark human CT.
Keywords:	Random Forest, True Positive Rate, Constellation Model, Appearance Model, Probabilistic Inference
Source:	Lecture Notes in Computer Science
Title of Book:	Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015
ISSN:	0302-9743
ISBN:	978-3-319-24552-2
Publisher:	Springer
Volume:	9349
Page Range:	653-660
Date:	2015
Official Publication:	https://doi.org/10.1007/978-3-319-24553-9_80

Repository Staff Only: item control page