Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Preoperative diagnosis of ovarian tumors using Bayesian kernel-based methods

Van Calster, B. ; Timmerman, D. ; Lu, C. ; Suykens, J. A. K. ; Valentin, Lil LU orcid ; Van Holsbeke, C. ; Amant, F. ; Vergote, I. and Van Huffel, S. (2007) In Ultrasound in Obstetrics & Gynecology 29(5). p.496-504
Abstract
Objectives To develop flexible classifiers that predict malignancy in adnexal masses using a large database from nine centers. Methods The database consisted of 1066 patients with at least one persistent adnexal mass for which a large amount of clinical and ultrasound data were recorded. The outcome of interest was the histological classification of the adnexal mass as benign or malignant. The outcome was predicted using Bayesian least squares support vector machines in comparison with relevance vector machines. The models were developed on a training set (n = 754) and tested on a test set (n = 312). Results Twenty-five percent of the patients (n = 266) bad a malignant tumor. Variable selection resulted in a set of 12 variables for the... (More)
Objectives To develop flexible classifiers that predict malignancy in adnexal masses using a large database from nine centers. Methods The database consisted of 1066 patients with at least one persistent adnexal mass for which a large amount of clinical and ultrasound data were recorded. The outcome of interest was the histological classification of the adnexal mass as benign or malignant. The outcome was predicted using Bayesian least squares support vector machines in comparison with relevance vector machines. The models were developed on a training set (n = 754) and tested on a test set (n = 312). Results Twenty-five percent of the patients (n = 266) bad a malignant tumor. Variable selection resulted in a set of 12 variables for the models: age, maximal diameter of the ovary, maximal diameter of the solid component, personal history of ovarian cancer, hormonal therapy, very strong intratumoral blood flow (i.e. color score 4), ascites, presumed ovarian origin of tumor, multilocular-solid tumor, blood flow within papillary projections, irregular internal cyst wall and acoustic shadows. Test set area under the receiver-operating characteristics curve (AUC) for all models exceeded 0.940, with a sensitivity above 90% and a specificity above 80% for all models. The least squares support vector machine model with linear kernel performed very well, with an AUC of 0.946, 91% sensitivity and 84% specificity. The models performed well in the test sets of all the centers. Conclusions Bayesian kernel-based methods can accurately separate malignant from benign masses. The robustness of the models will be investigated in future studies. Copyright (c) 2007 ISUOG. Published by John Wiley & Sons, Ltd. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
relevance vector, ovarian tumor classification, logistic regression, bayesian evidence framework, least squares support vector machines, machines, ultrasound
in
Ultrasound in Obstetrics & Gynecology
volume
29
issue
5
pages
496 - 504
publisher
John Wiley & Sons Inc.
external identifiers
  • wos:000246878800004
  • scopus:34249740082
ISSN
1469-0705
DOI
10.1002/uog.3996
language
English
LU publication?
yes
id
69f1b2f5-4287-4098-8aee-f1afb58ae954 (old id 651236)
date added to LUP
2016-04-01 16:56:35
date last changed
2022-01-28 23:12:08
@article{69f1b2f5-4287-4098-8aee-f1afb58ae954,
  abstract     = {{Objectives To develop flexible classifiers that predict malignancy in adnexal masses using a large database from nine centers. Methods The database consisted of 1066 patients with at least one persistent adnexal mass for which a large amount of clinical and ultrasound data were recorded. The outcome of interest was the histological classification of the adnexal mass as benign or malignant. The outcome was predicted using Bayesian least squares support vector machines in comparison with relevance vector machines. The models were developed on a training set (n = 754) and tested on a test set (n = 312). Results Twenty-five percent of the patients (n = 266) bad a malignant tumor. Variable selection resulted in a set of 12 variables for the models: age, maximal diameter of the ovary, maximal diameter of the solid component, personal history of ovarian cancer, hormonal therapy, very strong intratumoral blood flow (i.e. color score 4), ascites, presumed ovarian origin of tumor, multilocular-solid tumor, blood flow within papillary projections, irregular internal cyst wall and acoustic shadows. Test set area under the receiver-operating characteristics curve (AUC) for all models exceeded 0.940, with a sensitivity above 90% and a specificity above 80% for all models. The least squares support vector machine model with linear kernel performed very well, with an AUC of 0.946, 91% sensitivity and 84% specificity. The models performed well in the test sets of all the centers. Conclusions Bayesian kernel-based methods can accurately separate malignant from benign masses. The robustness of the models will be investigated in future studies. Copyright (c) 2007 ISUOG. Published by John Wiley & Sons, Ltd.}},
  author       = {{Van Calster, B. and Timmerman, D. and Lu, C. and Suykens, J. A. K. and Valentin, Lil and Van Holsbeke, C. and Amant, F. and Vergote, I. and Van Huffel, S.}},
  issn         = {{1469-0705}},
  keywords     = {{relevance vector; ovarian tumor classification; logistic regression; bayesian evidence framework; least squares support vector machines; machines; ultrasound}},
  language     = {{eng}},
  number       = {{5}},
  pages        = {{496--504}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{Ultrasound in Obstetrics & Gynecology}},
  title        = {{Preoperative diagnosis of ovarian tumors using Bayesian kernel-based methods}},
  url          = {{http://dx.doi.org/10.1002/uog.3996}},
  doi          = {{10.1002/uog.3996}},
  volume       = {{29}},
  year         = {{2007}},
}