Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis

Jessie Thomson; Terence O'Neill; David Felson; Timothy Cootes

doi:10.1007/978-3-319-47157-0_6

Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis

Jessie Thomson, Terence O'Neill, David Felson, Timothy Cootes

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We present a fully automatic system for identifying osteophytes on knee radiographs, and for estimating the widely used Kellgren-Lawrence (KL) grade for Osteoarthritis (OA). We have compared three advanced modelling and texture techniques. We found that a Random Forest trained using Haar-features achieved good results, but the optimal results are obtained by combining shape modelling and texture features. The system achieves the best reported performance for identifying osteophytes (AUC: 0.85), for measuring KL grades and for classifying OA (AUC: 0.93), with an error rate half that of the previous best method.

Original language	English
Title of host publication	Machine Learning in Medical Imaging
Subtitle of host publication	7th International workshop, MLMI 2016 held in conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Proceedings
Editors	Li Wang, Ehsan Adeli, Qian Wang, Yinghuan Shi, Heung-Il Suk
Place of Publication	Switzerland
Publisher	Springer Nature
Pages	45-52
Number of pages	8
ISBN (Print)	9783319471563
DOIs	https://doi.org/10.1007/978-3-319-47157-0_6
Publication status	Published - 1 Oct 2016

Publication series

Name	Lecture Notes in Computer Science (LNCS)
Publisher	Springer
Volume	10019
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Access to Document

10.1007/978-3-319-47157-0_6

Arthritis Research UK Centre of Excellence in Epidemiology.
Symmons, D. (PI), Bruce, I. (CoI), Dixon, W. (CoI), Felson, D. (CoI), Hyrich, K. (CoI), Lunt, M. (CoI), Mcbeth, J. (CoI), O'Neill, T. (CoI) & Verstappen, S. (CoI)
1/08/13 → 31/07/18
Project: Research

Cite this

Thomson, J., O'Neill, T., Felson, D., & Cootes, T. (2016). Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis. In L. Wang, E. Adeli, Q. Wang, Y. Shi, & H.-I. Suk (Eds.), Machine Learning in Medical Imaging: 7th International workshop, MLMI 2016 held in conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Proceedings (pp. 45-52). (Lecture Notes in Computer Science (LNCS); Vol. 10019). Springer Nature. https://doi.org/10.1007/978-3-319-47157-0_6

Thomson, Jessie ; O'Neill, Terence ; Felson, David et al. / Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis. Machine Learning in Medical Imaging: 7th International workshop, MLMI 2016 held in conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Proceedings. editor / Li Wang ; Ehsan Adeli ; Qian Wang ; Yinghuan Shi ; Heung-Il Suk. Switzerland : Springer Nature, 2016. pp. 45-52 (Lecture Notes in Computer Science (LNCS)).

@inproceedings{bd6e895155e748cb87beffede4d6166b,

title = "Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis",

abstract = "We present a fully automatic system for identifying osteophytes on knee radiographs, and for estimating the widely used Kellgren-Lawrence (KL) grade for Osteoarthritis (OA). We have compared three advanced modelling and texture techniques. We found that a Random Forest trained using Haar-features achieved good results, but the optimal results are obtained by combining shape modelling and texture features. The system achieves the best reported performance for identifying osteophytes (AUC: 0.85), for measuring KL grades and for classifying OA (AUC: 0.93), with an error rate half that of the previous best method.",

author = "Jessie Thomson and Terence O'Neill and David Felson and Timothy Cootes",

year = "2016",

month = oct,

day = "1",

doi = "10.1007/978-3-319-47157-0_6",

language = "English",

isbn = "9783319471563",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer Nature",

pages = "45--52",

editor = "Li Wang and Ehsan Adeli and Qian Wang and Yinghuan Shi and Heung-Il Suk",

booktitle = "Machine Learning in Medical Imaging",

address = "United States",

}

Thomson, J, O'Neill, T, Felson, D & Cootes, T 2016, Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis. in L Wang, E Adeli, Q Wang, Y Shi & H-I Suk (eds), Machine Learning in Medical Imaging: 7th International workshop, MLMI 2016 held in conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Proceedings. Lecture Notes in Computer Science (LNCS), vol. 10019, Springer Nature, Switzerland, pp. 45-52. https://doi.org/10.1007/978-3-319-47157-0_6

Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis. / Thomson, Jessie; O'Neill, Terence; Felson, David et al.
Machine Learning in Medical Imaging: 7th International workshop, MLMI 2016 held in conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Proceedings. ed. / Li Wang; Ehsan Adeli; Qian Wang; Yinghuan Shi; Heung-Il Suk. Switzerland: Springer Nature, 2016. p. 45-52 (Lecture Notes in Computer Science (LNCS); Vol. 10019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis

AU - Thomson, Jessie

AU - O'Neill, Terence

AU - Felson, David

AU - Cootes, Timothy

PY - 2016/10/1

Y1 - 2016/10/1

N2 - We present a fully automatic system for identifying osteophytes on knee radiographs, and for estimating the widely used Kellgren-Lawrence (KL) grade for Osteoarthritis (OA). We have compared three advanced modelling and texture techniques. We found that a Random Forest trained using Haar-features achieved good results, but the optimal results are obtained by combining shape modelling and texture features. The system achieves the best reported performance for identifying osteophytes (AUC: 0.85), for measuring KL grades and for classifying OA (AUC: 0.93), with an error rate half that of the previous best method.

AB - We present a fully automatic system for identifying osteophytes on knee radiographs, and for estimating the widely used Kellgren-Lawrence (KL) grade for Osteoarthritis (OA). We have compared three advanced modelling and texture techniques. We found that a Random Forest trained using Haar-features achieved good results, but the optimal results are obtained by combining shape modelling and texture features. The system achieves the best reported performance for identifying osteophytes (AUC: 0.85), for measuring KL grades and for classifying OA (AUC: 0.93), with an error rate half that of the previous best method.

U2 - 10.1007/978-3-319-47157-0_6

DO - 10.1007/978-3-319-47157-0_6

M3 - Conference contribution

SN - 9783319471563

T3 - Lecture Notes in Computer Science (LNCS)

SP - 45

EP - 52

BT - Machine Learning in Medical Imaging

A2 - Wang, Li

A2 - Adeli, Ehsan

A2 - Wang, Qian

A2 - Shi, Yinghuan

A2 - Suk, Heung-Il

PB - Springer Nature

CY - Switzerland

ER -

Thomson J, O'Neill T, Felson D, Cootes T. Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis. In Wang L, Adeli E, Wang Q, Shi Y, Suk HI, editors, Machine Learning in Medical Imaging: 7th International workshop, MLMI 2016 held in conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Proceedings. Switzerland: Springer Nature. 2016. p. 45-52. (Lecture Notes in Computer Science (LNCS)). doi: 10.1007/978-3-319-47157-0_6

Detecting osteophytes in radiographs of the knee to diagnose Osteoarthritis

Abstract

Publication series

Access to Document

Fingerprint

Projects

Arthritis Research UK Centre of Excellence in Epidemiology.

Cite this