Paper Info
Title
Tumor segmentation with multi-modality image in Conditional Random Field framework with logistic regression models.
Abstract
We have developed a semi-automatic method for multi-modality image segmentation aimed at reducing the manual process time via machine learning while preserving human guidance. Rather than reliance on heuristics, human oversight and expert training from images is incorporated into logistic regression models. The latter serve to estimate the probability of tissue class assignment for each voxel as well as the probability of tissue boundary occurring between neighboring voxels given the multi-modal image intensities. The regression models provide parameters for a Conditional Random Field (CRF) framework that defines an energy function with the regional and boundary probabilistic terms. Using this CRF, a max-flow/min-cut algorithm is used to segment other slices in the 3D image set automatically with options of addition user input. We apply this approach to segment visible tumors in multi-modal medical volumetric images.
Year
DOI
Venue
2014
10.1109/EMBC.2014.6945105
EMBC
Keywords
DocType
Volume
energy function,computerised tomography,expert training,regional probabilistic term,user input,learning (artificial intelligence),multimodality image segmentation,regression analysis,image segmentation,3d image set,human guidance,multimodal image intensities,multimodal medical volumetric images,biomedical mri,manual process time,semiautomatic method,max-flow/min-cut algorithm,positron emission tomography,heuristics,conditional random field framework,tissue boundary probability,tumours,crf,logistic regression models,tissue class assignment probability,machine learning,visible tumor segmentation,human oversight,boundary probabilistic term,medical image processing,neighboring voxels,probability
Conference
2014
ISSN
Citations 
PageRank 
1557-170X
1
0.35
References 
Authors
7
3
Name
Order
Citations
PageRank
Yu-chi Hu110.35
Michael Grossberg211.03
Gig Mageras310.35