Generalized Overlap Measures for Evaluation and Validation in Medical Image Analysis

Measures of overlap of labelled regions of images, such as the Dice and Tanimoto coefficients, have been extensively used to evaluate image registration and segmentation algorithms. Modern studies can include multiple labels defined on multiple images yet most evaluation schemes report one overlap p...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2006-11, Vol.25 (11), p.1451-1461
Main Authors: Crum, W.R., Camara, O., Hill, D.L.G.
Format: Article
Language:English
Subjects:
Algorithms
Biomedical imaging
Brain
Brain - anatomy & histology
Computation
Fuzzy logic
Fuzzy set theory
Fuzzy sets
Hausdorff distance
Humans
Image analysis
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image registration
Image segmentation
Information Storage and Retrieval - methods
Labels
Magnetic analysis
Magnetic resonance
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Magnetic Resonance Imaging - standards
morphological operations
Pattern Recognition, Automated - methods
Pattern Recognition, Automated - standards
Quality Assurance, Health Care - methods
Quality Assurance, Health Care - standards
registration
Reproducibility of Results
Segmentation
Sensitivity and Specificity
Similarity
Studies
Subtraction Technique
Testing
validation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Measures of overlap of labelled regions of images, such as the Dice and Tanimoto coefficients, have been extensively used to evaluate image registration and segmentation algorithms. Modern studies can include multiple labels defined on multiple images yet most evaluation schemes report one overlap per labelled region, simply averaged over multiple images. In this paper, common overlap measures are generalized to measure the total overlap of ensembles of labels defined on multiple test images and account for fractional labels using fuzzy set theory. This framework allows a single "figure-of-merit" to be reported which summarises the results of a complex experiment by image pair, by label or overall. A complementary measure of error, the overlap distance, is defined which captures the spatial extent of the nonoverlapping part and is related to the Hausdorff distance computed on grey level images. The generalized overlap measures are validated on synthetic images for which the overlap can be computed analytically and used as similarity measures in nonrigid registration of three-dimensional magnetic resonance imaging (MRI) brain images. Finally, a pragmatic segmentation ground truth is constructed by registering a magnetic resonance atlas brain to 20 individual scans, and used with the overlap measures to evaluate publicly available brain segmentation algorithms
ISSN:0278-0062
1558-254X
DOI:10.1109/TMI.2006.880587