A robust point-matching algorithm for autoradiograph alignment

Anand Rangarajan; Haili Chui; Eric Mjolsness; Suguna Pappu; Lila Davachi; Patricia Goldman-Rakic; James Duncan

doi:10.1016/S1361-8415(97)85008-6

A robust point-matching algorithm for autoradiograph alignment

Anand Rangarajan, Haili Chui, Eric Mjolsness, Suguna Pappu, Lila Davachi, Patricia Goldman-Rakic, James Duncan

Psychology

Research output: Contribution to journal › Article › peer-review

Abstract

We present a novel method for the geometric alignment of autoradiographs of the brain. The method is based on finding the spatial mapping and the one-to-one correspondences (or homologies) between point features extracted from the images and rejecting non-homologies as outliers. In this way, we attempt to account for the local, natural and artifactual differences between the autoradiograph slices. We have used the resulting automated algorithm on a set of left prefrontal cortex autoradiograph slices, specifically demonstrated its ability to perform point outlier rejection, validated its robustness property using synthetically generated spatial mappings and provided an anecdotal visual comparison with the well-known iterated closest-point (ICP) algorithm. Visualization of a stack of aligned left prefrontal cortex autoradiograph slices is also provided.

Original language	English (US)
Pages (from-to)	379-398
Number of pages	20
Journal	Medical Image Analysis
Volume	1
Issue number	4
DOIs	https://doi.org/10.1016/S1361-8415(97)85008-6
State	Published - 1997

Keywords

3-D reconstruction
Alignment
Correspondence
Deterministic annealing
Linear assignment problem
Outlier rejection
Permutation matrix
Point matching
Primate autoradiographs
Registration
Robustness
Similarity transform
Softassign
Spatial mapping

ASJC Scopus subject areas

Radiological and Ultrasound Technology
Radiology Nuclear Medicine and imaging
Computer Vision and Pattern Recognition
Health Informatics
Computer Graphics and Computer-Aided Design

Access to Document

10.1016/S1361-8415(97)85008-6

Cite this

@article{2c7e24d64e4b42abb65d4dd1c4e3cf41,

title = "A robust point-matching algorithm for autoradiograph alignment",

abstract = "We present a novel method for the geometric alignment of autoradiographs of the brain. The method is based on finding the spatial mapping and the one-to-one correspondences (or homologies) between point features extracted from the images and rejecting non-homologies as outliers. In this way, we attempt to account for the local, natural and artifactual differences between the autoradiograph slices. We have used the resulting automated algorithm on a set of left prefrontal cortex autoradiograph slices, specifically demonstrated its ability to perform point outlier rejection, validated its robustness property using synthetically generated spatial mappings and provided an anecdotal visual comparison with the well-known iterated closest-point (ICP) algorithm. Visualization of a stack of aligned left prefrontal cortex autoradiograph slices is also provided.",

keywords = "3-D reconstruction, Alignment, Correspondence, Deterministic annealing, Linear assignment problem, Outlier rejection, Permutation matrix, Point matching, Primate autoradiographs, Registration, Robustness, Similarity transform, Softassign, Spatial mapping",

author = "Anand Rangarajan and Haili Chui and Eric Mjolsness and Suguna Pappu and Lila Davachi and Patricia Goldman-Rakic and James Duncan",

note = "Funding Information: We thank the reviewers (two in particular) for their numerous comments, suggestions and criticisms. This project is partially supported by a grant from the Whitaker Foundation to Anand Rangarajan. We also thank Gene Gindi, Steven Gold and Hemant Tagare for helpful comments and Jim Rambo for his help in visualizing the stack of autoradiographs.",

year = "1997",

doi = "10.1016/S1361-8415(97)85008-6",

language = "English (US)",

volume = "1",

pages = "379--398",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier",

number = "4",

}

TY - JOUR

T1 - A robust point-matching algorithm for autoradiograph alignment

AU - Rangarajan, Anand

AU - Chui, Haili

AU - Mjolsness, Eric

AU - Pappu, Suguna

AU - Davachi, Lila

AU - Goldman-Rakic, Patricia

AU - Duncan, James

N1 - Funding Information: We thank the reviewers (two in particular) for their numerous comments, suggestions and criticisms. This project is partially supported by a grant from the Whitaker Foundation to Anand Rangarajan. We also thank Gene Gindi, Steven Gold and Hemant Tagare for helpful comments and Jim Rambo for his help in visualizing the stack of autoradiographs.

PY - 1997

Y1 - 1997

N2 - We present a novel method for the geometric alignment of autoradiographs of the brain. The method is based on finding the spatial mapping and the one-to-one correspondences (or homologies) between point features extracted from the images and rejecting non-homologies as outliers. In this way, we attempt to account for the local, natural and artifactual differences between the autoradiograph slices. We have used the resulting automated algorithm on a set of left prefrontal cortex autoradiograph slices, specifically demonstrated its ability to perform point outlier rejection, validated its robustness property using synthetically generated spatial mappings and provided an anecdotal visual comparison with the well-known iterated closest-point (ICP) algorithm. Visualization of a stack of aligned left prefrontal cortex autoradiograph slices is also provided.

AB - We present a novel method for the geometric alignment of autoradiographs of the brain. The method is based on finding the spatial mapping and the one-to-one correspondences (or homologies) between point features extracted from the images and rejecting non-homologies as outliers. In this way, we attempt to account for the local, natural and artifactual differences between the autoradiograph slices. We have used the resulting automated algorithm on a set of left prefrontal cortex autoradiograph slices, specifically demonstrated its ability to perform point outlier rejection, validated its robustness property using synthetically generated spatial mappings and provided an anecdotal visual comparison with the well-known iterated closest-point (ICP) algorithm. Visualization of a stack of aligned left prefrontal cortex autoradiograph slices is also provided.

KW - 3-D reconstruction

KW - Alignment

KW - Correspondence

KW - Deterministic annealing

KW - Linear assignment problem

KW - Outlier rejection

KW - Permutation matrix

KW - Point matching

KW - Primate autoradiographs

KW - Registration

KW - Robustness

KW - Similarity transform

KW - Softassign

KW - Spatial mapping

UR - http://www.scopus.com/inward/record.url?scp=0031215936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031215936&partnerID=8YFLogxK

U2 - 10.1016/S1361-8415(97)85008-6

DO - 10.1016/S1361-8415(97)85008-6

M3 - Article

C2 - 9873917

AN - SCOPUS:0031215936

SN - 1361-8415

VL - 1

SP - 379

EP - 398

JO - Medical Image Analysis

JF - Medical Image Analysis

IS - 4

ER -

A robust point-matching algorithm for autoradiograph alignment

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this