Document Detail


An informative probability model enhancing real time echobiometry to improve fetal weight estimation accuracy.
MedLine Citation:
PMID:  18196306     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
A multinormal probability model is proposed to correct human errors in fetal echobiometry and improve the estimation of fetal weight (EFW). Model parameters were designed to depend on major pregnancy data and were estimated through feed-forward artificial neural networks (ANNs). Data from 4075 women in labour were used for training and testing ANNs. The model was implemented numerically to provide EFW together with probabilities of congruence among measured echobiometric parameters. It enabled ultrasound measurement errors to be real-time checked and corrected interactively. The software was useful for training medical staff and standardizing measurement procedures. It provided multiple statistical data on fetal morphometry and aid for clinical decisions. A clinical protocol for testing the system ability to detect measurement errors was conducted with 61 women in the last week of pregnancy. It led to decisive improvements in EFW accuracy.
Authors:
G Cevenini; F M Severi; C Bocchi; F Petraglia; P Barbini
Related Documents :
12929716 - A study on prediction of the bio-toxicity of substituted benzene based on artificial ne...
18244596 - Robust combination of neural networks and hidden markov models for speech recognition.
18309366 - The implicit function as squashing time model: a novel parallel nonlinear eeg analysis ...
17281746 - Prediction of scoliosis progression in time series using a hybrid learning technique.
23696476 - Respiratory risk score for the prediction of 3-month mortality and prolonged ventilatio...
20356856 - Estimating screening test sensitivity and tumour progression using tumour size and time...
Publication Detail:
Type:  Evaluation Studies; Journal Article; Research Support, Non-U.S. Gov't     Date:  2008-01-10
Journal Detail:
Title:  Medical & biological engineering & computing     Volume:  46     ISSN:  0140-0118     ISO Abbreviation:  Med Biol Eng Comput     Publication Date:  2008 Feb 
Date Detail:
Created Date:  2008-02-04     Completed Date:  2008-06-11     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  7704869     Medline TA:  Med Biol Eng Comput     Country:  United States    
Other Details:
Languages:  eng     Pagination:  109-20     Citation Subset:  IM    
Affiliation:
Department of Surgery and Bioengineering, University of Siena, Viale Mario Bracci 16, Siena, Italy. cevenini@unisi.it
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Anthropometry / methods
Birth Weight
Female
Fetal Weight*
Humans
Image Interpretation, Computer-Assisted / methods
Infant, Newborn
Models, Statistical*
Neural Networks (Computer)
Pregnancy
Ultrasonography, Prenatal / methods*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Keep an eye on your hands: on the role of visual mechanisms in processing of haptic space.
Next Document:  Evaluation of signal space separation via simulation.