Validation of Graph Theoretic Segmentation of the Pectoral Muscle

Fei Ma; Mariusz Bajger; John Slavotinek; Murk Bottema

doi:10.1007/11783237_86

Validation of Graph Theoretic Segmentation of the Pectoral Muscle

Fei Ma, Mariusz Bajger, John Slavotinek, Murk Bottema

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

3 Citations (Scopus)

Abstract

Two graph theoretic methods are used in conjunction with active contours to segment the pectoral muscle in 82 screening mammograms. To validate the method, the boundaries are also marked by four radiologists with different levels of experience in mammography. The simultaneous truth and performance level estimation (STAPLE) method is used to estimate the true boundary and to estimate the sensitivity and specificity of the segmentation schemes. The performance of one of the two algorithms is found not differ significantly from radiologists.

Original language	English
Title of host publication	Validation of Graph Theoretic Segmentation of the Pectoral Muscle
Place of Publication	Berlin
Publisher	Springer
Pages	642-649
Number of pages	8
ISBN (Electronic)	978-3-540-35627-1
ISBN (Print)	978-3-540-35625-7
DOIs	https://doi.org/10.1007/11783237_86
Publication status	Published - 2006
Event	8th International Workshop, IWDM 2006 - Duration: 18 Jun 2006 → …

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	4046

Conference

Conference	8th International Workshop, IWDM 2006
Period	18/06/06 → …

Access to Document

10.1007/11783237_86Licence: In Copyright

Cite this

@inproceedings{1857769668a340808f5251854126e7fb,

title = "Validation of Graph Theoretic Segmentation of the Pectoral Muscle",

abstract = "Two graph theoretic methods are used in conjunction with active contours to segment the pectoral muscle in 82 screening mammograms. To validate the method, the boundaries are also marked by four radiologists with different levels of experience in mammography. The simultaneous truth and performance level estimation (STAPLE) method is used to estimate the true boundary and to estimate the sensitivity and specificity of the segmentation schemes. The performance of one of the two algorithms is found not differ significantly from radiologists.",

author = "Fei Ma and Mariusz Bajger and John Slavotinek and Murk Bottema",

year = "2006",

doi = "10.1007/11783237_86",

language = "English",

isbn = "978-3-540-35625-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "642--649",

booktitle = "Validation of Graph Theoretic Segmentation of the Pectoral Muscle",

note = "8th International Workshop, IWDM 2006 ; Conference date: 18-06-2006",

}

Validation of Graph Theoretic Segmentation of the Pectoral Muscle. / Ma, Fei; Bajger, Mariusz ; Slavotinek, John et al.

Validation of Graph Theoretic Segmentation of the Pectoral Muscle. Berlin : Springer , 2006. p. 642-649 (Lecture Notes in Computer Science; Vol. 4046).

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

TY - GEN

T1 - Validation of Graph Theoretic Segmentation of the Pectoral Muscle

AU - Ma, Fei

AU - Bajger, Mariusz

AU - Slavotinek, John

AU - Bottema, Murk

PY - 2006

Y1 - 2006

N2 - Two graph theoretic methods are used in conjunction with active contours to segment the pectoral muscle in 82 screening mammograms. To validate the method, the boundaries are also marked by four radiologists with different levels of experience in mammography. The simultaneous truth and performance level estimation (STAPLE) method is used to estimate the true boundary and to estimate the sensitivity and specificity of the segmentation schemes. The performance of one of the two algorithms is found not differ significantly from radiologists.

AB - Two graph theoretic methods are used in conjunction with active contours to segment the pectoral muscle in 82 screening mammograms. To validate the method, the boundaries are also marked by four radiologists with different levels of experience in mammography. The simultaneous truth and performance level estimation (STAPLE) method is used to estimate the true boundary and to estimate the sensitivity and specificity of the segmentation schemes. The performance of one of the two algorithms is found not differ significantly from radiologists.

U2 - 10.1007/11783237_86

DO - 10.1007/11783237_86

M3 - Conference contribution

SN - 978-3-540-35625-7

T3 - Lecture Notes in Computer Science

SP - 642

EP - 649

BT - Validation of Graph Theoretic Segmentation of the Pectoral Muscle

PB - Springer

CY - Berlin

T2 - 8th International Workshop, IWDM 2006

Y2 - 18 June 2006

ER -

Validation of Graph Theoretic Segmentation of the Pectoral Muscle

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this