Limits...
Subvoxel accurate graph search using non-Euclidean graph space.

Abràmoff MD, Wu X, Lee K, Tang L - PLoS ONE (2014)

Bottom Line: A deformation field calculated from the volume data adaptively changes regional node density so that node density varies with the inverse of the expected cost.Our approach allows improved accuracy in volume data acquired with the same hardware, and also, preserved accuracy with lower resolution, more cost-effective, image acquisition equipment.The method is not limited to any specific imaging modality and readily extensible to higher dimensions.

View Article: PubMed Central - PubMed

Affiliation: Department of Ophthalmology and Visual Sciences, Stephen A Wynn Institute for Vision Research, Department of Biomedical Engineering, and Department of Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, United States of America; Iowa City Veterans Administration Medical Center, Iowa City, Iowa, United States of America.

ABSTRACT
Graph search is attractive for the quantitative analysis of volumetric medical images, and especially for layered tissues, because it allows globally optimal solutions in low-order polynomial time. However, because nodes of graphs typically encode evenly distributed voxels of the volume with arcs connecting orthogonally sampled voxels in Euclidean space, segmentation cannot achieve greater precision than a single unit, i.e. the distance between two adjoining nodes, and partial volume effects are ignored. We generalize the graph to non-Euclidean space by allowing non-equidistant spacing between nodes, so that subvoxel accurate segmentation is achievable. Because the number of nodes and edges in the graph remains the same, running time and memory use are similar, while all the advantages of graph search, including global optimality and computational efficiency, are retained. A deformation field calculated from the volume data adaptively changes regional node density so that node density varies with the inverse of the expected cost. We validated our approach using optical coherence tomography (OCT) images of the retina and 3-D MR of the arterial wall, and achieved statistically significant increased accuracy. Our approach allows improved accuracy in volume data acquired with the same hardware, and also, preserved accuracy with lower resolution, more cost-effective, image acquisition equipment. The method is not limited to any specific imaging modality and readily extensible to higher dimensions.

Show MeSH

Related in: MedlinePlus

One B-scan of the down-sampled OCT volume.(a) One B-scan; (b) Two corresponding surfaces were identified by both conventional graph search and non-Euclidean graph search.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4196762&req=5

pone-0107763-g010: One B-scan of the down-sampled OCT volume.(a) One B-scan; (b) Two corresponding surfaces were identified by both conventional graph search and non-Euclidean graph search.

Mentions: The original OCT volumes were down-sampled to voxels, resulting in “input volume data”. The uneven down-sampling rate compensates for the highly anisotropic nature of typical OCT data and makes the partial volume effects clearly visible. The two surfaces were identified in these “input volume data” using the conventional graph search approach and our new non-Euclidean graph search approach (Fig. 10).


Subvoxel accurate graph search using non-Euclidean graph space.

Abràmoff MD, Wu X, Lee K, Tang L - PLoS ONE (2014)

One B-scan of the down-sampled OCT volume.(a) One B-scan; (b) Two corresponding surfaces were identified by both conventional graph search and non-Euclidean graph search.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4196762&req=5

pone-0107763-g010: One B-scan of the down-sampled OCT volume.(a) One B-scan; (b) Two corresponding surfaces were identified by both conventional graph search and non-Euclidean graph search.
Mentions: The original OCT volumes were down-sampled to voxels, resulting in “input volume data”. The uneven down-sampling rate compensates for the highly anisotropic nature of typical OCT data and makes the partial volume effects clearly visible. The two surfaces were identified in these “input volume data” using the conventional graph search approach and our new non-Euclidean graph search approach (Fig. 10).

Bottom Line: A deformation field calculated from the volume data adaptively changes regional node density so that node density varies with the inverse of the expected cost.Our approach allows improved accuracy in volume data acquired with the same hardware, and also, preserved accuracy with lower resolution, more cost-effective, image acquisition equipment.The method is not limited to any specific imaging modality and readily extensible to higher dimensions.

View Article: PubMed Central - PubMed

Affiliation: Department of Ophthalmology and Visual Sciences, Stephen A Wynn Institute for Vision Research, Department of Biomedical Engineering, and Department of Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, United States of America; Iowa City Veterans Administration Medical Center, Iowa City, Iowa, United States of America.

ABSTRACT
Graph search is attractive for the quantitative analysis of volumetric medical images, and especially for layered tissues, because it allows globally optimal solutions in low-order polynomial time. However, because nodes of graphs typically encode evenly distributed voxels of the volume with arcs connecting orthogonally sampled voxels in Euclidean space, segmentation cannot achieve greater precision than a single unit, i.e. the distance between two adjoining nodes, and partial volume effects are ignored. We generalize the graph to non-Euclidean space by allowing non-equidistant spacing between nodes, so that subvoxel accurate segmentation is achievable. Because the number of nodes and edges in the graph remains the same, running time and memory use are similar, while all the advantages of graph search, including global optimality and computational efficiency, are retained. A deformation field calculated from the volume data adaptively changes regional node density so that node density varies with the inverse of the expected cost. We validated our approach using optical coherence tomography (OCT) images of the retina and 3-D MR of the arterial wall, and achieved statistically significant increased accuracy. Our approach allows improved accuracy in volume data acquired with the same hardware, and also, preserved accuracy with lower resolution, more cost-effective, image acquisition equipment. The method is not limited to any specific imaging modality and readily extensible to higher dimensions.

Show MeSH
Related in: MedlinePlus