Predicting knee cartilage loss using adaptive partitioning of cartilage thickness maps

Dan Richter Jørgensen; Erik Bjørnager Dam; Martin Lillholm

doi:10.1016/j.compbiomed.2013.05.012

Predicting knee cartilage loss using adaptive partitioning of cartilage thickness maps

Dan Richter Jørgensen, Erik Bjørnager Dam, Martin Lillholm

Department of Computer Science

5 Citations (Scopus)

Abstract

This study investigates whether measures of knee cartilage thickness can predict future loss of knee cartilage. A slow and a rapid progressor group was determined using longitudinal data, and anatomically aligned cartilage thickness maps were extracted from MRI at baseline. A novel machine learning framework was then trained using these maps. Compared to measures of mean cartilage plate thickness, group separation was increased by focusing on local cartilage differences. This result is central for clinical trials where inclusion of rapid progressors may help reduce the period needed to study effects of new disease-modifying drugs for osteoarthritis.

Original language	English
Journal	Computers in Biology and Medicine
Volume	43
Issue number	8
Pages (from-to)	1045-1052
Number of pages	8
ISSN	0010-4825
DOIs	https://doi.org/10.1016/j.compbiomed.2013.05.012
Publication status	Published - 1 Sept 2013

Access to Document

10.1016/j.compbiomed.2013.05.012

Cite this

@article{705067d66c794325b61de77b67a53776,

title = "Predicting knee cartilage loss using adaptive partitioning of cartilage thickness maps",

abstract = "This study investigates whether measures of knee cartilage thickness can predict future loss of knee cartilage. A slow and a rapid progressor group was determined using longitudinal data, and anatomically aligned cartilage thickness maps were extracted from MRI at baseline. A novel machine learning framework was then trained using these maps. Compared to measures of mean cartilage plate thickness, group separation was increased by focusing on local cartilage differences. This result is central for clinical trials where inclusion of rapid progressors may help reduce the period needed to study effects of new disease-modifying drugs for osteoarthritis.",

keywords = "Osteoarthritis, Knee MRI, Cartilage thickness, Clinical trials, Machine learning, Classification, Spatial data mining, Dimensionality reduction",

author = "J{\o}rgensen, {Dan Richter} and Dam, {Erik Bj{\o}rnager} and Martin Lillholm",

year = "2013",

month = sep,

day = "1",

doi = "10.1016/j.compbiomed.2013.05.012",

language = "English",

volume = "43",

pages = "1045--1052",

journal = "Computers in Biology and Medicine",

issn = "0010-4825",

publisher = "Pergamon Press",

number = "8",

}

TY - JOUR

T1 - Predicting knee cartilage loss using adaptive partitioning of cartilage thickness maps

AU - Jørgensen, Dan Richter

AU - Dam, Erik Bjørnager

AU - Lillholm, Martin

PY - 2013/9/1

Y1 - 2013/9/1

N2 - This study investigates whether measures of knee cartilage thickness can predict future loss of knee cartilage. A slow and a rapid progressor group was determined using longitudinal data, and anatomically aligned cartilage thickness maps were extracted from MRI at baseline. A novel machine learning framework was then trained using these maps. Compared to measures of mean cartilage plate thickness, group separation was increased by focusing on local cartilage differences. This result is central for clinical trials where inclusion of rapid progressors may help reduce the period needed to study effects of new disease-modifying drugs for osteoarthritis.

AB - This study investigates whether measures of knee cartilage thickness can predict future loss of knee cartilage. A slow and a rapid progressor group was determined using longitudinal data, and anatomically aligned cartilage thickness maps were extracted from MRI at baseline. A novel machine learning framework was then trained using these maps. Compared to measures of mean cartilage plate thickness, group separation was increased by focusing on local cartilage differences. This result is central for clinical trials where inclusion of rapid progressors may help reduce the period needed to study effects of new disease-modifying drugs for osteoarthritis.

KW - Osteoarthritis

KW - Knee MRI

KW - Cartilage thickness

KW - Clinical trials

KW - Machine learning

KW - Classification

KW - Spatial data mining

KW - Dimensionality reduction

U2 - 10.1016/j.compbiomed.2013.05.012

DO - 10.1016/j.compbiomed.2013.05.012

M3 - Journal article

C2 - 23773813

SN - 0010-4825

VL - 43

SP - 1045

EP - 1052

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

IS - 8

ER -

Predicting knee cartilage loss using adaptive partitioning of cartilage thickness maps

Abstract

Access to Document

Fingerprint

Cite this