Ara

Bu bölümde sistem içerisindeki makaleler arasında arama yapabilirsiniz.

Dergi Kimliği

Online ISSN
1305-3132

Yayın Dönemi
1993 - 2021

Editor-in-Chief
​Cihat Şen, ​Nicola Volpe

Editors
Daniel Rolnik, Mar Gil, Murat Yayla, Oluş Api

The use neural network for makıng decısıon of ıntrauterıne growth retardatıon : Sıngle versus multıple ultrasonographıc examınatıons

Fikret Gürgen, Emrah Önal, Füsun G. Varol

Künye

The use neural network for makıng decısıon of ıntrauterıne growth retardatıon : Sıngle versus multıple ultrasonographıc examınatıons. Perinatoloji Dergisi 1996;4(1):35-35

Yazar Bilgileri

Fikret Gürgen1,
Emrah Önal1,
Füsun G. Varol2

  1. Boğaziçi University Computer Engineering Department İstanbul TR
  2. Trakya University Gynecology and Obstetrics Department Edirne TR
Yayın Geçmişi
Çıkar Çakışması

Çıkar çakışması bulunmadığı belirtilmiştir.

Giriş

To evaluate the applicability of neural network for making decision of intrauterine growth retardation through the single and multiple ultrasonographic fetal growth assessments.

Study Design

By using reference fetal growth profiles, this study was undertaken to show if a feedforward neural network (NN) can leam nominal growth curves of head circumference (hc), abdominal circumference (ac), and hc/ac ratio versus gestational age. From 1 to 4 weekly ultrasonographic examinations are taken as input to NN. A multilayer perceptron (MLP) and a radial basis function (RBF) are used. Various performance measures such as mean square error (MSE), cross entropy (CE) are employed.

Bulgular

A NN can improve the accuracy of the decision of IUGR by the multiple weekly examinations which mean monitoring the dynamic process of a change in size over time. Conclusion: The applicability of NNs to the determination of IUGR is possible and it is fruitful line of inquiry for further work.
Anahtar Kelimeler

-