Using Bayesian neural networks with ARD input selection to detect malignant ovarian masses prior to surgery

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Abstract

In this paper, we applied Bayesian multi-layer perceptrons (MLP) using the evidence procedure to predict malignancy of ovarian masses in a large (n = 1,066) multi-centre data set. Automatic relevance determination (ARD) was used to select the most relevant inputs. Fivefold cross-validation (5CV) and repeated 5CV was used to select the optimal combination of input set and number of hidden neurons. Results indicate good performance of the models with area under the receiver operating characteristic curve values of 0.93-0.94 on independent data. Comparison with a linear benchmark model and a previously developed logistic regression model shows that the present problem is very well linearly separable. A resampling analysis further shows that the number of hidden neurons specified in the ARD analyses for input selection may influence model performance. This paper shows that Bayesian MLPs, although not frequently used, are a useful tool for detecting malignant ovarian tumours.

Detaljer

Författare
  • Ben Van Calster
  • Dirk Timmerman
  • Ian T. Nabney
  • Lil Valentin
  • Antonia C. Testa
  • Caroline Van Holsbeke
  • Ignace Vergote
  • Sabine Van Huffel
Enheter & grupper
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Reproduktionsmedicin och gynekologi

Nyckelord

Originalspråkengelska
Titel på värdpublikationNEURAL COMPUTING & APPLICATIONS
FörlagSpringer
Sidor489-500
Volym17
StatusPublished - 2008
PublikationskategoriForskning
Peer review utfördJa
Evenemang28th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society - New York, NY
Varaktighet: 2006 aug 302006 sep 3

Publikationsserier

Namn
Nummer5-6
Volym17
ISSN (tryckt)0941-0643

Konferens

Konferens28th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society
Period2006/08/302006/09/03