Research Article
Developing Image Processing Meta-Algorithms with
Data Mining of Multiple Metrics
Kelvin Leung,
1,2
Alexandre Cunha,
3
A. W. Toga,
4
and D. Stott Parker
2
1
Intel Corporation, 3600 Julliette Ln., Mail Stop SC12-301, Santa Clara, CA 95054, USA
2
UCLA Computer Science Department, Los Angeles, CA 90095-1596, USA
3
Caltech Center for Advanced Computing Research (CACR), Pasadena, CA 91125, USA
4
USC Laboratory of Neuroimaging (LONI), Los Angeles, CA 90007, USA
Correspondence should be addressed to Kelvin Leung; kelvin.t.leung@intel.com
Received 7 May 2013; Revised 26 November 2013; Accepted 26 November 2013; Published 5 February 2014
Academic Editor: Facundo Ballester
Copyright © 2014 Kelvin Leung et al. his is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
People oten use multiple metrics in image processing, but here we take a novel approach of mining the values of batteries of
metrics on image processing results. We present a case for extending image processing methods to incorporate automated mining
of multiple image metric values. Here by a metric we mean any image similarity or distance measure, and in this paper we consider
intensity-based and statistical image measures and focus on registration as an image processing problem. We show how it is possible
to develop meta-algorithms that evaluate diferent image processing results with a number of diferent metrics and mine the results
in an automated fashion so as to select the best results. We show that the mining of multiple metrics ofers a variety of potential
beneits for many image processing problems, including improved robustness and validation.
1. Introduction
Every year many articles are published in the area of biomedi-
cal image registration that introduce new metrics for biomed-
ical images, covering both distance/diference measures and
similarity measures. here are many reasons for this interest
in metrics. However, the abundance of methods creates a
basic dilemma for practitioners seeking high-performance
imaging systems: which metric should be used?
his paper reports on an efort spanning ive years at
UCLA, studying this question, and developing schemes that
use multiple methods and multiple evaluation metrics to
obtain better image processing results. In much the same way
that ensemble methods yield better results in data mining,
this efort explored sotware combinations of metrics that
yielded improved methods for registration in neuroimaging.
In this paper we consider two families of image similarity
metrics: intensity-based metrics (metrics of the intensity or
luminosity values of voxels) and statistical metrics (metrics
of their distributions). here are at least three reasons why
use of multiple metrics can be important in image processing
as follows.
(i) Metrics are performance measures, so awareness
of them is a prerequisite for good performance.
Although it is common to commit ab initio to a single
registration algorithm and metric, algorithms and
metrics difer signiicantly, and choices among them
can have important consequences.
(ii) here are inherent limits to image processing per-
formance. From this perspective, image processing
methods are little more than optimizers that rest
on assumptions about prior distributions of images
and validation as experimental veriication of these
distributions. However, if metric values can be treated
as samples of prior distributions on performance
measures, we can mitigate some of these limits.
(iii) he key point of this paper is that the results of
diferent image processing algorithms and parameter
settings can be evaluated under multiple metrics, and
the metric values can then be analyzed with data
mining to identify the best results. he tracking of
metric value results permits investigation of which
image processing methods give better results for
Hindawi Publishing Corporation
Computational and Mathematical Methods in Medicine
Volume 2014, Article ID 383465, 7 pages
http://dx.doi.org/10.1155/2014/383465