Tampere University of Technology

TUTCRIS Research Portal

Zonal segmentation of prostate using multispectral magnetic resonance images

Research output: Contribution to journalArticleScientificpeer-review

Standard

Zonal segmentation of prostate using multispectral magnetic resonance images. / Makni, N.; Iancu, A.; Colot, O.; Puech, P.; Mordon, S.; Betrouni, N.

In: Medical Physics, Vol. 38, No. 11, 11.2011, p. 6093-6105.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Makni, N, Iancu, A, Colot, O, Puech, P, Mordon, S & Betrouni, N 2011, 'Zonal segmentation of prostate using multispectral magnetic resonance images', Medical Physics, vol. 38, no. 11, pp. 6093-6105. https://doi.org/10.1118/1.3651610

APA

Makni, N., Iancu, A., Colot, O., Puech, P., Mordon, S., & Betrouni, N. (2011). Zonal segmentation of prostate using multispectral magnetic resonance images. Medical Physics, 38(11), 6093-6105. https://doi.org/10.1118/1.3651610

Vancouver

Makni N, Iancu A, Colot O, Puech P, Mordon S, Betrouni N. Zonal segmentation of prostate using multispectral magnetic resonance images. Medical Physics. 2011 Nov;38(11):6093-6105. https://doi.org/10.1118/1.3651610

Author

Makni, N. ; Iancu, A. ; Colot, O. ; Puech, P. ; Mordon, S. ; Betrouni, N. / Zonal segmentation of prostate using multispectral magnetic resonance images. In: Medical Physics. 2011 ; Vol. 38, No. 11. pp. 6093-6105.

Bibtex - Download

@article{7e7ce311df284dab95802b56f1c4cb6b,
title = "Zonal segmentation of prostate using multispectral magnetic resonance images",
abstract = "Purpose: To investigate the performance of a new method of automatic segmentation of prostatic multispectral magnetic resonance images into two zones: the peripheral zone and the central gland. Methods: The proposed method is based on a modified version of the evidential C-means clustering algorithm. The evidential C-means optimization process was modified to introduce spatial neighborhood information. A priori knowledge of the prostate's zonal morphology was modeled as a geometric criterion and used as an additional data source to enhance the differentiation of the two zones. Results: Thirty-one clinical magnetic resonance imaging series were used to validate the method, and interobserver variability was taken into account in assessing its accuracy. The mean Dice Similarity Coefficient was 89 for the central gland and 80 for the peripheral zone, as validated by a consensus from expert radiologist segmentation. Conclusions: The method was statistically insensitive to variations in patient age, prostate volume and the presence of tumors, which increases its feasibility in a clinical context.",
keywords = "central gland, multispectral MRI, peripheral zone, prostate, Segmentation",
author = "N. Makni and A. Iancu and O. Colot and P. Puech and S. Mordon and N. Betrouni",
year = "2011",
month = "11",
doi = "10.1118/1.3651610",
language = "English",
volume = "38",
pages = "6093--6105",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "American Association of Physicists in Medicine",
number = "11",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Zonal segmentation of prostate using multispectral magnetic resonance images

AU - Makni, N.

AU - Iancu, A.

AU - Colot, O.

AU - Puech, P.

AU - Mordon, S.

AU - Betrouni, N.

PY - 2011/11

Y1 - 2011/11

N2 - Purpose: To investigate the performance of a new method of automatic segmentation of prostatic multispectral magnetic resonance images into two zones: the peripheral zone and the central gland. Methods: The proposed method is based on a modified version of the evidential C-means clustering algorithm. The evidential C-means optimization process was modified to introduce spatial neighborhood information. A priori knowledge of the prostate's zonal morphology was modeled as a geometric criterion and used as an additional data source to enhance the differentiation of the two zones. Results: Thirty-one clinical magnetic resonance imaging series were used to validate the method, and interobserver variability was taken into account in assessing its accuracy. The mean Dice Similarity Coefficient was 89 for the central gland and 80 for the peripheral zone, as validated by a consensus from expert radiologist segmentation. Conclusions: The method was statistically insensitive to variations in patient age, prostate volume and the presence of tumors, which increases its feasibility in a clinical context.

AB - Purpose: To investigate the performance of a new method of automatic segmentation of prostatic multispectral magnetic resonance images into two zones: the peripheral zone and the central gland. Methods: The proposed method is based on a modified version of the evidential C-means clustering algorithm. The evidential C-means optimization process was modified to introduce spatial neighborhood information. A priori knowledge of the prostate's zonal morphology was modeled as a geometric criterion and used as an additional data source to enhance the differentiation of the two zones. Results: Thirty-one clinical magnetic resonance imaging series were used to validate the method, and interobserver variability was taken into account in assessing its accuracy. The mean Dice Similarity Coefficient was 89 for the central gland and 80 for the peripheral zone, as validated by a consensus from expert radiologist segmentation. Conclusions: The method was statistically insensitive to variations in patient age, prostate volume and the presence of tumors, which increases its feasibility in a clinical context.

KW - central gland

KW - multispectral MRI

KW - peripheral zone

KW - prostate

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=80855128862&partnerID=8YFLogxK

U2 - 10.1118/1.3651610

DO - 10.1118/1.3651610

M3 - Article

VL - 38

SP - 6093

EP - 6105

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 11

ER -