Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme

Jenny Maria Folkesson; Erik Bjørnager Dam; Ole Fogh Olsen; Paola C. Pettersen; Claus Christiansen

doi:10.1007/11566465

Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme

Jenny Maria Folkesson, Erik Bjørnager Dam, Ole Fogh Olsen, Paola C. Pettersen, Claus Christiansen

35 Citationer (Scopus)

Abstract

Osteoarthritis is characterized by the degeneration of the articular cartilage in joints. We have developed a fully automatic method for segmenting the articular cartilage in knee MR scans based on supervised learning. A binary approximate kNN classifier first roughly separates cartilage from background voxels, then a three-class classifier assigns one of three classes to each voxel that is classified as cartilage by the binary classifier. The resulting sensitivity and specificity are 90.0% and 99.8% respectively for the medial cartilage compartments. We show that an accurate automatic cartilage segmentation is achievable using a low-field MR scanner.

Originalsprog	Engelsk
Titel	Medical Image Computing and Computer-Assisted Intervention – MICCAI
Forlag	<Forlag uden navn>
Publikationsdato	2005
Sider	327-334
ISBN (Trykt)	978-3-540-29327-9
DOI	https://doi.org/10.1007/11566465
Status	Udgivet - 2005
Udgivet eksternt	Ja
Begivenhed	8th International Conference in Medical Image Computing and Computer-Assisted Intervention – MICCAI - Palm Springs, CA, USA Varighed: 29 nov. 2010 → … Konferencens nummer: 8

Konference

Konference	8th International Conference in Medical Image Computing and Computer-Assisted Intervention – MICCAI
Nummer	8
Land/Område	USA
By	Palm Springs, CA
Periode	29/11/2010 → …

Navn	Lecture notes in computer science
Vol/bind	3749/2005
ISSN	0302-9743

Adgang til dokumentet

10.1007/11566465

http://www.springerlink.de/content/cgr3wh5935qah5fy/fulltext.pdf

Citationsformater

Folkesson, J. M., Dam, E. B., Olsen, O. F., Pettersen, P. C., & Christiansen, C. (2005). Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme. I Medical Image Computing and Computer-Assisted Intervention – MICCAI (s. 327-334). <Forlag uden navn>. Lecture notes in computer science Bind 3749/2005 https://doi.org/10.1007/11566465

Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme. / Folkesson, Jenny Maria; Dam, Erik Bjørnager; Olsen, Ole Fogh et al.

Medical Image Computing and Computer-Assisted Intervention – MICCAI. <Forlag uden navn>, 2005. s. 327-334 (Lecture notes in computer science, Bind 3749/2005).

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Folkesson, JM, Dam, EB, Olsen, OF, Pettersen, PC & Christiansen, C 2005, Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme. i Medical Image Computing and Computer-Assisted Intervention – MICCAI. <Forlag uden navn>, Lecture notes in computer science, bind 3749/2005, s. 327-334, 8th International Conference in Medical Image Computing and Computer-Assisted Intervention – MICCAI, Palm Springs, CA, USA, 29/11/2010. https://doi.org/10.1007/11566465

@inproceedings{2bbd92304c3311dd8d9f000ea68e967b,

title = "Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme",

abstract = "Osteoarthritis is characterized by the degeneration of the articular cartilage in joints. We have developed a fully automatic method for segmenting the articular cartilage in knee MR scans based on supervised learning. A binary approximate kNN classifier first roughly separates cartilage from background voxels, then a three-class classifier assigns one of three classes to each voxel that is classified as cartilage by the binary classifier. The resulting sensitivity and specificity are 90.0% and 99.8% respectively for the medial cartilage compartments. We show that an accurate automatic cartilage segmentation is achievable using a low-field MR scanner.",

author = "Folkesson, {Jenny Maria} and Dam, {Erik Bj{\o}rnager} and Olsen, {Ole Fogh} and Pettersen, {Paola C.} and Claus Christiansen",

year = "2005",

doi = "10.1007/11566465",

language = "English",

isbn = "978-3-540-29327-9",

series = "Lecture notes in computer science",

publisher = "<Forlag uden navn>",

pages = "327--334",

booktitle = "Medical Image Computing and Computer-Assisted Intervention – MICCAI",

note = "8th International Conference in Medical Image Computing and Computer-Assisted Intervention – MICCAI ; Conference date: 29-11-2010",

}

TY - GEN

T1 - Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme

AU - Folkesson, Jenny Maria

AU - Dam, Erik Bjørnager

AU - Olsen, Ole Fogh

AU - Pettersen, Paola C.

AU - Christiansen, Claus

N1 - Conference code: 8

PY - 2005

Y1 - 2005

N2 - Osteoarthritis is characterized by the degeneration of the articular cartilage in joints. We have developed a fully automatic method for segmenting the articular cartilage in knee MR scans based on supervised learning. A binary approximate kNN classifier first roughly separates cartilage from background voxels, then a three-class classifier assigns one of three classes to each voxel that is classified as cartilage by the binary classifier. The resulting sensitivity and specificity are 90.0% and 99.8% respectively for the medial cartilage compartments. We show that an accurate automatic cartilage segmentation is achievable using a low-field MR scanner.

AB - Osteoarthritis is characterized by the degeneration of the articular cartilage in joints. We have developed a fully automatic method for segmenting the articular cartilage in knee MR scans based on supervised learning. A binary approximate kNN classifier first roughly separates cartilage from background voxels, then a three-class classifier assigns one of three classes to each voxel that is classified as cartilage by the binary classifier. The resulting sensitivity and specificity are 90.0% and 99.8% respectively for the medial cartilage compartments. We show that an accurate automatic cartilage segmentation is achievable using a low-field MR scanner.

U2 - 10.1007/11566465

DO - 10.1007/11566465

M3 - Article in proceedings

SN - 978-3-540-29327-9

T3 - Lecture notes in computer science

SP - 327

EP - 334

BT - Medical Image Computing and Computer-Assisted Intervention – MICCAI

PB - <Forlag uden navn>

T2 - 8th International Conference in Medical Image Computing and Computer-Assisted Intervention – MICCAI

Y2 - 29 November 2010

ER -

Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme

Abstract

Konference

Adgang til dokumentet

Fingeraftryk

Citationsformater