A fully automatic algorithm for segmentation of the breasts in DCE-MR images

Valentina Giannini, Anna Vignati, Lia Morra, Diego Persano, Davide Brizzi, Luca Carbonaro, Alberto Bert, Francesco Sardanelli, Daniele Regge

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Automatic segmentation of the breast and axillary region is an important preprocessing step for automatic lesion detection in breast MR and dynamic contrast-enhanced-MR studies. In this paper, we present a fully automatic procedure based on the detection of the upper border of the pectoral muscle. Compared with previous methods based on thresholding, this method is more robust to noise and field inhomogeneities. The method was quantitatively evaluated on 31 cases acquired from two centers by comparing the results with a manual segmentation. Results indicate good overall agreement within the reference segmentation (overlap=0.79±0.09, recall=0.95±0.02, precision=0.82±0.1).

Original languageEnglish
Title of host publication2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Pages3146-3149
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 - Buenos Aires, Argentina
Duration: Aug 31 2010Sep 4 2010

Other

Other2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
CountryArgentina
CityBuenos Aires
Period8/31/109/4/10

Fingerprint

Muscle

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Giannini, V., Vignati, A., Morra, L., Persano, D., Brizzi, D., Carbonaro, L., ... Regge, D. (2010). A fully automatic algorithm for segmentation of the breasts in DCE-MR images. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 (pp. 3146-3149). [5627191] https://doi.org/10.1109/IEMBS.2010.5627191

A fully automatic algorithm for segmentation of the breasts in DCE-MR images. / Giannini, Valentina; Vignati, Anna; Morra, Lia; Persano, Diego; Brizzi, Davide; Carbonaro, Luca; Bert, Alberto; Sardanelli, Francesco; Regge, Daniele.

2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. p. 3146-3149 5627191.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Giannini, V, Vignati, A, Morra, L, Persano, D, Brizzi, D, Carbonaro, L, Bert, A, Sardanelli, F & Regge, D 2010, A fully automatic algorithm for segmentation of the breasts in DCE-MR images. in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10., 5627191, pp. 3146-3149, 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10, Buenos Aires, Argentina, 8/31/10. https://doi.org/10.1109/IEMBS.2010.5627191
Giannini V, Vignati A, Morra L, Persano D, Brizzi D, Carbonaro L et al. A fully automatic algorithm for segmentation of the breasts in DCE-MR images. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. p. 3146-3149. 5627191 https://doi.org/10.1109/IEMBS.2010.5627191
Giannini, Valentina ; Vignati, Anna ; Morra, Lia ; Persano, Diego ; Brizzi, Davide ; Carbonaro, Luca ; Bert, Alberto ; Sardanelli, Francesco ; Regge, Daniele. / A fully automatic algorithm for segmentation of the breasts in DCE-MR images. 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. pp. 3146-3149
@inproceedings{d82b538b0c5c4082af6b39f354fc4143,
title = "A fully automatic algorithm for segmentation of the breasts in DCE-MR images",
abstract = "Automatic segmentation of the breast and axillary region is an important preprocessing step for automatic lesion detection in breast MR and dynamic contrast-enhanced-MR studies. In this paper, we present a fully automatic procedure based on the detection of the upper border of the pectoral muscle. Compared with previous methods based on thresholding, this method is more robust to noise and field inhomogeneities. The method was quantitatively evaluated on 31 cases acquired from two centers by comparing the results with a manual segmentation. Results indicate good overall agreement within the reference segmentation (overlap=0.79±0.09, recall=0.95±0.02, precision=0.82±0.1).",
author = "Valentina Giannini and Anna Vignati and Lia Morra and Diego Persano and Davide Brizzi and Luca Carbonaro and Alberto Bert and Francesco Sardanelli and Daniele Regge",
year = "2010",
doi = "10.1109/IEMBS.2010.5627191",
language = "English",
isbn = "9781424441235",
pages = "3146--3149",
booktitle = "2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10",

}

TY - GEN

T1 - A fully automatic algorithm for segmentation of the breasts in DCE-MR images

AU - Giannini, Valentina

AU - Vignati, Anna

AU - Morra, Lia

AU - Persano, Diego

AU - Brizzi, Davide

AU - Carbonaro, Luca

AU - Bert, Alberto

AU - Sardanelli, Francesco

AU - Regge, Daniele

PY - 2010

Y1 - 2010

N2 - Automatic segmentation of the breast and axillary region is an important preprocessing step for automatic lesion detection in breast MR and dynamic contrast-enhanced-MR studies. In this paper, we present a fully automatic procedure based on the detection of the upper border of the pectoral muscle. Compared with previous methods based on thresholding, this method is more robust to noise and field inhomogeneities. The method was quantitatively evaluated on 31 cases acquired from two centers by comparing the results with a manual segmentation. Results indicate good overall agreement within the reference segmentation (overlap=0.79±0.09, recall=0.95±0.02, precision=0.82±0.1).

AB - Automatic segmentation of the breast and axillary region is an important preprocessing step for automatic lesion detection in breast MR and dynamic contrast-enhanced-MR studies. In this paper, we present a fully automatic procedure based on the detection of the upper border of the pectoral muscle. Compared with previous methods based on thresholding, this method is more robust to noise and field inhomogeneities. The method was quantitatively evaluated on 31 cases acquired from two centers by comparing the results with a manual segmentation. Results indicate good overall agreement within the reference segmentation (overlap=0.79±0.09, recall=0.95±0.02, precision=0.82±0.1).

UR - http://www.scopus.com/inward/record.url?scp=78650843650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650843650&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2010.5627191

DO - 10.1109/IEMBS.2010.5627191

M3 - Conference contribution

SN - 9781424441235

SP - 3146

EP - 3149

BT - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

ER -