Advanced

Use of ultrasound pattern recognition by expert operators to identify borderline ovarian tumors: a study of diagnostic performance and interobserver agreement

Yazbek, J.; Ameye, L.; Timmerman, D.; Testa, A. C.; Valentin, Lil LU ; Holland, T. K.; Van Holsbeke, C. and Jurkovic, D. (2010) In Ultrasound in Obstetrics & Gynecology 35(1). p.84-88
Abstract
Objective To assess the accuracy and reproducibility of ultrasound 'pattern recognition' for the diagnosis of borderline ovarian tumors by asking experienced ultrasound operators to evaluate representative images of different types of adnexal tumor. Methods Digitally stored static two-dimensional B-mode images of representative cases of benign, borderline and invasive malignant ovarian tumors were independently assessed by three expert sonologists who bad not performed the original real-time ultrasound examination. The outcome measures included diagnostic accuracy and interobserver agreement in the diagnosis of benign, borderline or invasive malignant ovarian tumors. Results One hundred and sixty-six cases were included in the final data... (More)
Objective To assess the accuracy and reproducibility of ultrasound 'pattern recognition' for the diagnosis of borderline ovarian tumors by asking experienced ultrasound operators to evaluate representative images of different types of adnexal tumor. Methods Digitally stored static two-dimensional B-mode images of representative cases of benign, borderline and invasive malignant ovarian tumors were independently assessed by three expert sonologists who bad not performed the original real-time ultrasound examination. The outcome measures included diagnostic accuracy and interobserver agreement in the diagnosis of benign, borderline or invasive malignant ovarian tumors. Results One hundred and sixty-six cases were included in the final data analysis. A correct classification was made by all three experts in 83% of the primary invasive cancers, 76% of the benign masses and in 44% of the borderline malignant tumors (P < 0.01). The experts showed a tendency to misclassify borderline tumors as benign rather than primary invasive (ratio of 8 : 1 for Expert A, 4 : 1 for B and 6 : 1 for C). The interobserver agreement between any two experts was very good when they were tested for their ability to discriminate between invasive and non-invasive (benign and borderline) ovarian tumors (Cohen's kappa 0.85-0.88), but poorer for the discrimination between malignant (invasive and borderline) and benign tumors (kappa 0.70-0.78). Conclusions The accuracy of ultrasound diagnosis of borderline tumors is lower in comparison with benign and invasive malignant lesions. The diagnostic performance and interobserver agreement are better when the outcomes are dichotomized into non-invasive and invasive malignant lesions, as opposed to the traditional diagnosis of benign and malignant tumors. Copyright (c) 2009 ISUOG. Published by John Wiley & Sons, Ltd. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
pattern recognition, neoplasms, ovarian, malignant, interobserver agreement, benign, borderline, ultrasonography
in
Ultrasound in Obstetrics & Gynecology
volume
35
issue
1
pages
84 - 88
publisher
John Wiley & Sons
external identifiers
  • wos:000273679800014
  • scopus:74049118004
ISSN
1469-0705
DOI
10.1002/uog.7334
language
English
LU publication?
yes
id
7e7a1614-474d-4ffd-b12c-15577aeaa198 (old id 1547411)
date added to LUP
2010-02-24 09:05:11
date last changed
2018-05-29 10:22:33
@article{7e7a1614-474d-4ffd-b12c-15577aeaa198,
  abstract     = {Objective To assess the accuracy and reproducibility of ultrasound 'pattern recognition' for the diagnosis of borderline ovarian tumors by asking experienced ultrasound operators to evaluate representative images of different types of adnexal tumor. Methods Digitally stored static two-dimensional B-mode images of representative cases of benign, borderline and invasive malignant ovarian tumors were independently assessed by three expert sonologists who bad not performed the original real-time ultrasound examination. The outcome measures included diagnostic accuracy and interobserver agreement in the diagnosis of benign, borderline or invasive malignant ovarian tumors. Results One hundred and sixty-six cases were included in the final data analysis. A correct classification was made by all three experts in 83% of the primary invasive cancers, 76% of the benign masses and in 44% of the borderline malignant tumors (P &lt; 0.01). The experts showed a tendency to misclassify borderline tumors as benign rather than primary invasive (ratio of 8 : 1 for Expert A, 4 : 1 for B and 6 : 1 for C). The interobserver agreement between any two experts was very good when they were tested for their ability to discriminate between invasive and non-invasive (benign and borderline) ovarian tumors (Cohen's kappa 0.85-0.88), but poorer for the discrimination between malignant (invasive and borderline) and benign tumors (kappa 0.70-0.78). Conclusions The accuracy of ultrasound diagnosis of borderline tumors is lower in comparison with benign and invasive malignant lesions. The diagnostic performance and interobserver agreement are better when the outcomes are dichotomized into non-invasive and invasive malignant lesions, as opposed to the traditional diagnosis of benign and malignant tumors. Copyright (c) 2009 ISUOG. Published by John Wiley &amp; Sons, Ltd.},
  author       = {Yazbek, J. and Ameye, L. and Timmerman, D. and Testa, A. C. and Valentin, Lil and Holland, T. K. and Van Holsbeke, C. and Jurkovic, D.},
  issn         = {1469-0705},
  keyword      = {pattern recognition,neoplasms,ovarian,malignant,interobserver agreement,benign,borderline,ultrasonography},
  language     = {eng},
  number       = {1},
  pages        = {84--88},
  publisher    = {John Wiley & Sons},
  series       = {Ultrasound in Obstetrics & Gynecology},
  title        = {Use of ultrasound pattern recognition by expert operators to identify borderline ovarian tumors: a study of diagnostic performance and interobserver agreement},
  url          = {http://dx.doi.org/10.1002/uog.7334},
  volume       = {35},
  year         = {2010},
}