Model library for deformable model-based segmentation of 3-D brain MR-images

Juha Koikkalainen; Jyrki Lötjönen

doi:10.1007/3-540-45786-0_67

Model library for deformable model-based segmentation of 3-D brain MR-images

Juha Koikkalainen, Jyrki Lötjönen

VTT Technical Research Centre of Finland

Helsinki University of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

7 Citations (Scopus)

Abstract

A novel method to use model libraries in segmentation is introduced. Using similarity measures one model from model library is selected. This model is then used in model-based segmentation. The proposed method is simple, straightforward and fast. Various similarity measures, both voxel and edge measures, were examined. Two different segmentation methods were used for validating the functionality of the proposed procedure. Results show that a statistically significant improvement in segmentation accuracy was achieved in each study case.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention
Subtitle of host publication	MICCAI 2002
Publisher	Springer
Pages	540-547
ISBN (Electronic)	978-3-540-45786-2
ISBN (Print)	978-3-540-44224-0
DOIs	https://doi.org/10.1007/3-540-45786-0_67
Publication status	Published - 2002
MoE publication type	A4 Article in a conference publication
Event	5th International Conference on Medical Imagae Computing and Computer-Assisted Intervention (MICCAI 2002) - Tokyo, Japan Duration: 25 Sept 2002 → 28 Sept 2002 Conference number: 5

Publication series

Series	Lecture Notes in Computer Science
Volume	2488
ISSN	0302-9743

Conference

Conference	5th International Conference on Medical Imagae Computing and Computer-Assisted Intervention (MICCAI 2002)
Abbreviated title	MICCAI 2002
Country/Territory	Japan
City	Tokyo
Period	25/09/02 → 28/09/02

Access to Document

10.1007/3-540-45786-0_67

Cite this

@inproceedings{652f8daac58646868d2ee33112c0723d,

title = "Model library for deformable model-based segmentation of 3-D brain MR-images",

abstract = "A novel method to use model libraries in segmentation is introduced. Using similarity measures one model from model library is selected. This model is then used in model-based segmentation. The proposed method is simple, straightforward and fast. Various similarity measures, both voxel and edge measures, were examined. Two different segmentation methods were used for validating the functionality of the proposed procedure. Results show that a statistically significant improvement in segmentation accuracy was achieved in each study case.",

author = "Juha Koikkalainen and Jyrki L{\"o}tj{\"o}nen",

note = "CA2: TTE5 CA: TTE Project code: T2SU00362; 5th International Conference on Medical Imagae Computing and Computer-Assisted Intervention (MICCAI 2002), MICCAI 2002 ; Conference date: 25-09-2002 Through 28-09-2002",

year = "2002",

doi = "10.1007/3-540-45786-0_67",

language = "English",

isbn = "978-3-540-44224-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "540--547",

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

address = "Germany",

}

Koikkalainen, J & Lötjönen, J 2002, Model library for deformable model-based segmentation of 3-D brain MR-images. in Medical Image Computing and Computer-Assisted Intervention: MICCAI 2002. Springer, Lecture Notes in Computer Science, vol. 2488, pp. 540-547, 5th International Conference on Medical Imagae Computing and Computer-Assisted Intervention (MICCAI 2002), Tokyo, Japan, 25/09/02. https://doi.org/10.1007/3-540-45786-0_67

Model library for deformable model-based segmentation of 3-D brain MR-images. / Koikkalainen, Juha; Lötjönen, Jyrki.
Medical Image Computing and Computer-Assisted Intervention: MICCAI 2002. Springer, 2002. p. 540-547 (Lecture Notes in Computer Science, Vol. 2488).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Model library for deformable model-based segmentation of 3-D brain MR-images

AU - Koikkalainen, Juha

AU - Lötjönen, Jyrki

N1 - Conference code: 5

PY - 2002

Y1 - 2002

N2 - A novel method to use model libraries in segmentation is introduced. Using similarity measures one model from model library is selected. This model is then used in model-based segmentation. The proposed method is simple, straightforward and fast. Various similarity measures, both voxel and edge measures, were examined. Two different segmentation methods were used for validating the functionality of the proposed procedure. Results show that a statistically significant improvement in segmentation accuracy was achieved in each study case.

AB - A novel method to use model libraries in segmentation is introduced. Using similarity measures one model from model library is selected. This model is then used in model-based segmentation. The proposed method is simple, straightforward and fast. Various similarity measures, both voxel and edge measures, were examined. Two different segmentation methods were used for validating the functionality of the proposed procedure. Results show that a statistically significant improvement in segmentation accuracy was achieved in each study case.

U2 - 10.1007/3-540-45786-0_67

DO - 10.1007/3-540-45786-0_67

M3 - Conference article in proceedings

SN - 978-3-540-44224-0

T3 - Lecture Notes in Computer Science

SP - 540

EP - 547

BT - Medical Image Computing and Computer-Assisted Intervention

PB - Springer

T2 - 5th International Conference on Medical Imagae Computing and Computer-Assisted Intervention (MICCAI 2002)

Y2 - 25 September 2002 through 28 September 2002

ER -

Model library for deformable model-based segmentation of 3-D brain MR-images

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this