Use of varying constraints in optimal 3-D graph search for segmentation of macular optical coherence tomography images

Authors:
Mona Haeker;Michael D. Abràmoff;Xiaodong Wu;Randy Kardon;Milan Sonka
Affiliations:
Departments of Electrical & Computer Engineering and Departments of Biomedical Engineering, The University of Iowa, Iowa City, IA;Departments of Electrical & Computer Engineering and Departments of Ophthalmology & Visual Sciences, The University of Iowa, Iowa City, IA;Departments of Electrical & Computer Engineering, The University of Iowa, Iowa City, IA;Departments of Ophthalmology & Visual Sciences, The University of Iowa, Iowa City, IA;Departments of Electrical & Computer Engineering and Departments of Ophthalmology & Visual Sciences, The University of Iowa, Iowa City, IA
Venue:
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Year:
2007

Citing 4
Cited 0

Optimal Net Surface Problems with Applications

ICALP '02 Proceedings of the 29th International Colloquium on Automata, Languages and Programming
Interactive Organ Segmentation Using Graph Cuts

MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Incorporation of regional information in optimal 3-D graph search with application for intraretinal layer segmentation of optical coherence tomography images

IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging

Quantified Score

Hi-index	0.00

Visualization

Abstract

An optimal 3-D graph search approach designed for simultaneous multiple surface detection is extended to allow for varying smoothness and surface interaction constraints instead of the traditionally used constant constraints. We apply the method to the intraretinal layer segmentation of 24 3-D optical coherence tomography (OCT) images, learning the constraints from examples in a leave-one-subject-out fashion. Introducing the varying constraints decreased the mean unsigned border positioning errors (mean error of 7.3 ± 3.7 µm using varying constraints compared to 8.3 ± 4.9 µm using constant constraints and 8.2 ± 3.5 µm for the inter-observer variability).