Multifractal texture analysis of perfusion lung scans as a potential diagnostic tool for acute pulmonary embolism

Georgia D. Tourassi; Erik D. Frederick; Carey E. Floyd; R. Edward Coleman

doi:10.1016/S0010-4825(00)00024-X

Multifractal texture analysis of perfusion lung scans as a potential diagnostic tool for acute pulmonary embolism

Georgia D. Tourassi, Erik D. Frederick, Carey E. Floyd, R. Edward Coleman

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

19 Scopus citations

Abstract

A computer-assisted diagnostic (CAD) tool was developed for the diagnosis of acute pulmonary embolism (PE) in perfusion lung scans. Forty-five scans (with angiographic proof) were included in the study. The CAD tool was composed of two modules. The first module performs multifractal texture analysis on the posterior view of the perfusion scan. The second module is a decision algorithm that merges the multifractal parameters into a diagnosis regarding the presence or absence of PE. Linear and non-linear decision models were evaluated for the diagnostic task. A consensus neural network significantly outperformed all decision models including the physicians.

Original language	English
Pages (from-to)	15-25
Number of pages	11
Journal	Computers in Biology and Medicine
Volume	31
Issue number	1
DOIs	https://doi.org/10.1016/S0010-4825(00)00024-X
State	Published - Jan 2001
Externally published	Yes

Funding

This work was supported by grant RG 98-0324 from the Whitaker Foundation and in part by grant R29-HL-52826 from the National Heart, Lung, and Blood Institute.

Funders	Funder number
National Heart, Lung, and Blood Institute
Whitaker Foundation	R29-HL-52826

Keywords

Computer-aided diagnosis
Fractal analysis
Image processing
Lung perfusion
Neural networks
Pulmonary embolism

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/S0010-4825(00)00024-X

Cite this

@article{11818dbb24f44608a59319737df9b98a,

title = "Multifractal texture analysis of perfusion lung scans as a potential diagnostic tool for acute pulmonary embolism",

abstract = "A computer-assisted diagnostic (CAD) tool was developed for the diagnosis of acute pulmonary embolism (PE) in perfusion lung scans. Forty-five scans (with angiographic proof) were included in the study. The CAD tool was composed of two modules. The first module performs multifractal texture analysis on the posterior view of the perfusion scan. The second module is a decision algorithm that merges the multifractal parameters into a diagnosis regarding the presence or absence of PE. Linear and non-linear decision models were evaluated for the diagnostic task. A consensus neural network significantly outperformed all decision models including the physicians.",

keywords = "Computer-aided diagnosis, Fractal analysis, Image processing, Lung perfusion, Neural networks, Pulmonary embolism",

author = "Tourassi, {Georgia D.} and Frederick, {Erik D.} and Floyd, {Carey E.} and Coleman, {R. Edward}",

year = "2001",

month = jan,

doi = "10.1016/S0010-4825(00)00024-X",

language = "English",

volume = "31",

pages = "15--25",

journal = "Computers in Biology and Medicine",

issn = "0010-4825",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Multifractal texture analysis of perfusion lung scans as a potential diagnostic tool for acute pulmonary embolism

AU - Tourassi, Georgia D.

AU - Frederick, Erik D.

AU - Floyd, Carey E.

AU - Coleman, R. Edward

PY - 2001/1

Y1 - 2001/1

N2 - A computer-assisted diagnostic (CAD) tool was developed for the diagnosis of acute pulmonary embolism (PE) in perfusion lung scans. Forty-five scans (with angiographic proof) were included in the study. The CAD tool was composed of two modules. The first module performs multifractal texture analysis on the posterior view of the perfusion scan. The second module is a decision algorithm that merges the multifractal parameters into a diagnosis regarding the presence or absence of PE. Linear and non-linear decision models were evaluated for the diagnostic task. A consensus neural network significantly outperformed all decision models including the physicians.

AB - A computer-assisted diagnostic (CAD) tool was developed for the diagnosis of acute pulmonary embolism (PE) in perfusion lung scans. Forty-five scans (with angiographic proof) were included in the study. The CAD tool was composed of two modules. The first module performs multifractal texture analysis on the posterior view of the perfusion scan. The second module is a decision algorithm that merges the multifractal parameters into a diagnosis regarding the presence or absence of PE. Linear and non-linear decision models were evaluated for the diagnostic task. A consensus neural network significantly outperformed all decision models including the physicians.

KW - Computer-aided diagnosis

KW - Fractal analysis

KW - Image processing

KW - Lung perfusion

KW - Neural networks

KW - Pulmonary embolism

UR - http://www.scopus.com/inward/record.url?scp=0035238925&partnerID=8YFLogxK

U2 - 10.1016/S0010-4825(00)00024-X

DO - 10.1016/S0010-4825(00)00024-X

M3 - Article

C2 - 11058691

AN - SCOPUS:0035238925

SN - 0010-4825

VL - 31

SP - 15

EP - 25

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

IS - 1

ER -

Multifractal texture analysis of perfusion lung scans as a potential diagnostic tool for acute pulmonary embolism

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this