Paper Info
Title
Detecting mild traumatic brain injury using dynamic low level context
Abstract
Mild traumatic brain injury is difficult to detect in standard magnetic resonance (MR) images due to the low contrast appearance of lesions. In this paper a discriminative approach is presented, using a classifier to directly estimates the posterior probability of lesion at every voxel using low-level context learned from previous classifiers. Both visual features including multiple texture measures, and context features, which include novel features such as proximity, directional distance, and posterior marginal edge distance, are used. The context is also taken from previous time points, so the system automatically captures the dynamics of the injury progression. The approach is tested on an mTBI rat model using MR imaging at multiple time points. Our results show an improved performance in both the dice score and convergence rate compared to other approaches.
Year
DOI
Venue
2013
10.1109/ICIP.2013.6738241
Image Processing
Keywords
Field
DocType
brain,feature extraction,image texture,magnetic resonance imaging,medical image processing,probability,MR images,MR imaging,context features,convergence rate,dice score,directional distance,dynamic low level context,injury progression,lesion,mTBI rat model,mild traumatic brain injury,multiple texture measures,posterior marginal edge distance,posterior probability,proximity,standard magnetic resonance images,voxel,Context,Dynamic,Low Contrast,Magnetic Resonance Imaging,Traumatic Brain injury
Voxel,Computer vision,Pattern recognition,Computer science,Image texture,Feature extraction,Posterior probability,Artificial intelligence,Classifier (linguistics),Discriminative model,Traumatic brain injury,Magnetic resonance imaging
Conference
ISSN
Citations 
PageRank 
1522-4880
1
0.36
References 
Authors
7
4
Name
Order
Citations
PageRank
Anthony C. Bianchi181.56
Bir Bhanu23356380.19
Virginia Donovan361.19
Andre Obenaus472.16