Diffusion methods for aligning medical datasets: Location prediction in CT scan images

Ángela Fernández; Neta Rabin; Ronald R. Coifman; Joseph Eckstein

doi:10.1016/j.media.2013.12.009

Diffusion methods for aligning medical datasets: Location prediction in CT scan images

Ángela Fernández, Neta Rabin, Ronald R. Coifman, Joseph Eckstein

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

Abstract

The purpose of this study is to introduce diffusion methods as a tool to label CT scan images according to their position in the human body. A comparative study of different methods based on a k-NN search is carried out and we propose a new, simple and efficient way of applying diffusion techniques that is able to give better location forecasts than methods that can be considered the current state-of-the-art.

Original language	English
Pages (from-to)	425-432
Number of pages	8
Journal	Medical Image Analysis
Volume	18
Issue number	2
DOIs	https://doi.org/10.1016/j.media.2013.12.009
State	Published - Feb 2014
Externally published	Yes

Keywords

Anisotropic diffusion
CT scan images
Diffusion distance
Diffusion methods
Misaligned data

All Science Journal Classification (ASJC) codes

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/j.media.2013.12.009

Cite this

@article{40ee2a801ddf482aae0aa404f70759d9,

title = "Diffusion methods for aligning medical datasets: Location prediction in CT scan images",

abstract = "The purpose of this study is to introduce diffusion methods as a tool to label CT scan images according to their position in the human body. A comparative study of different methods based on a k-NN search is carried out and we propose a new, simple and efficient way of applying diffusion techniques that is able to give better location forecasts than methods that can be considered the current state-of-the-art.",

keywords = "Anisotropic diffusion, CT scan images, Diffusion distance, Diffusion methods, Misaligned data",

author = "{\'A}ngela Fern{\'a}ndez and Neta Rabin and Coifman, \{Ronald R.\} and Joseph Eckstein",

note = "Funding Information: The first author acknowledge support from FPI–UAM grant, partial support from Grant TIN2010-21575-C02-01 of Spain{\textquoteright}s Ministerio de Econom{\'i}a y Competitividad and the UAM–ADIC Chair for Machine Learning in Modeling and Prediction. The authors would like to thank Jos{\'e} R. Dorronsoro for helpful suggestions on how to improve the paper, and they would also like to thank the useful comments and suggestions made by different physicians to motivate this problem.",

year = "2014",

month = feb,

doi = "10.1016/j.media.2013.12.009",

language = "الإنجليزيّة",

volume = "18",

pages = "425--432",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - Diffusion methods for aligning medical datasets

T2 - Location prediction in CT scan images

AU - Fernández, Ángela

AU - Rabin, Neta

AU - Coifman, Ronald R.

AU - Eckstein, Joseph

N1 - Funding Information: The first author acknowledge support from FPI–UAM grant, partial support from Grant TIN2010-21575-C02-01 of Spain’s Ministerio de Economía y Competitividad and the UAM–ADIC Chair for Machine Learning in Modeling and Prediction. The authors would like to thank José R. Dorronsoro for helpful suggestions on how to improve the paper, and they would also like to thank the useful comments and suggestions made by different physicians to motivate this problem.

PY - 2014/2

Y1 - 2014/2

N2 - The purpose of this study is to introduce diffusion methods as a tool to label CT scan images according to their position in the human body. A comparative study of different methods based on a k-NN search is carried out and we propose a new, simple and efficient way of applying diffusion techniques that is able to give better location forecasts than methods that can be considered the current state-of-the-art.

AB - The purpose of this study is to introduce diffusion methods as a tool to label CT scan images according to their position in the human body. A comparative study of different methods based on a k-NN search is carried out and we propose a new, simple and efficient way of applying diffusion techniques that is able to give better location forecasts than methods that can be considered the current state-of-the-art.

KW - Anisotropic diffusion

KW - CT scan images

KW - Diffusion distance

KW - Diffusion methods

KW - Misaligned data

UR - http://www.scopus.com/inward/record.url?scp=84892551462&partnerID=8YFLogxK

U2 - 10.1016/j.media.2013.12.009

DO - 10.1016/j.media.2013.12.009

M3 - مقالة

C2 - 24444669

SN - 1361-8415

VL - 18

SP - 425

EP - 432

JO - Medical Image Analysis

JF - Medical Image Analysis

IS - 2

ER -

Diffusion methods for aligning medical datasets: Location prediction in CT scan images

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this