Discriminative Random Field Segmentation of Lung Nodules in CT Studies

Discriminative Random Field Segmentation of Lung Nodules in CT Studies

The ability to conduct high-quality semiautomatic 3D segmentation of lung nodules in CT scans is of high value to busy radiologists. Discriminative random fields (DRFs) were used to segment 3D volumes of lung nodules in CT scan data using only one seed point per nodule. Optimal parameters for the DR...

Full description

Bibliographic Details
Main Authors: Brian Liu, Ashish Raj
Format: Article
Language:English
Published: Hindawi Limited 2013-01-01
Series:Computational and Mathematical Methods in Medicine
Online Access:http://dx.doi.org/10.1155/2013/683216
id doaj-a928eccb2dff4d14b073c971238fcdc5
record_format Article
spelling doaj-a928eccb2dff4d14b073c971238fcdc52020-11-24T23:19:01ZengHindawi LimitedComputational and Mathematical Methods in Medicine1748-670X1748-67182013-01-01201310.1155/2013/683216683216Discriminative Random Field Segmentation of Lung Nodules in CT StudiesBrian Liu0Ashish Raj1Cornell University, Ithaca, NY 14853, USAWeill Cornell Medical College, New York, NY 10065, USAThe ability to conduct high-quality semiautomatic 3D segmentation of lung nodules in CT scans is of high value to busy radiologists. Discriminative random fields (DRFs) were used to segment 3D volumes of lung nodules in CT scan data using only one seed point per nodule. Optimal parameters for the DRF inference were first found using simulated annealing. These parameters were then used to solve the inference problem using the graph cuts algorithm. Results of the segmentation exhibited high precision and recall. The system can be adapted to facilitate the process of longitudinal studies but will still require human checking for failed cases.http://dx.doi.org/10.1155/2013/683216
collection DOAJ
language English
format Article
sources DOAJ
author Brian Liu
Ashish Raj
spellingShingle Brian Liu
Ashish Raj
Discriminative Random Field Segmentation of Lung Nodules in CT Studies
Computational and Mathematical Methods in Medicine
author_facet Brian Liu
Ashish Raj
author_sort Brian Liu
title Discriminative Random Field Segmentation of Lung Nodules in CT Studies
title_short Discriminative Random Field Segmentation of Lung Nodules in CT Studies
title_full Discriminative Random Field Segmentation of Lung Nodules in CT Studies
title_fullStr Discriminative Random Field Segmentation of Lung Nodules in CT Studies
title_full_unstemmed Discriminative Random Field Segmentation of Lung Nodules in CT Studies
title_sort discriminative random field segmentation of lung nodules in ct studies
publisher Hindawi Limited
series Computational and Mathematical Methods in Medicine
issn 1748-670X
1748-6718
publishDate 2013-01-01
description The ability to conduct high-quality semiautomatic 3D segmentation of lung nodules in CT scans is of high value to busy radiologists. Discriminative random fields (DRFs) were used to segment 3D volumes of lung nodules in CT scan data using only one seed point per nodule. Optimal parameters for the DRF inference were first found using simulated annealing. These parameters were then used to solve the inference problem using the graph cuts algorithm. Results of the segmentation exhibited high precision and recall. The system can be adapted to facilitate the process of longitudinal studies but will still require human checking for failed cases.
url http://dx.doi.org/10.1155/2013/683216
work_keys_str_mv AT brianliu discriminativerandomfieldsegmentationoflungnodulesinctstudies
AT ashishraj discriminativerandomfieldsegmentationoflungnodulesinctstudies
_version_ 1725578967520378880

Similar Items